1. Introduction
An increasing demand for precision, predictability
and minimally invasive approaches is accelerating the use of
digital technologies in periodontology and implant dentistry.
Implant-supported rehabilitation has become a highly predictable
treatment modality for replacing missing teeth. The long-term
success of implant therapy depends heavily on accurate implant
positioning and prosthetically driven treatment planning. An
incorrect implant position can compromise aesthetics, biomechanics,
oral hygiene and peri-implant tissue health, and can increase the
risk of damage to adjacent anatomical structures such as nerves,
vessels and the maxillary sinus (1). Traditionally, implant placement has
been achieved with a freehand approach on the basis of clinical
examination and radiographic assessment. Experienced clinicians can
achieve satisfactory results, but freehand surgery is operator
dependent and can be associated with positional deviations from the
planned implant position (2).
Advances in cone-beam computed tomography (CBCT), digital intraoral
scanning and computer-aided design/computer-aided manufacturing
(CAD/CAM) technologies have facilitated the development of
computer-assisted surgical approaches with the goal of improving
implant placement accuracy and reducing procedural variability
(3). Computer-assisted implant
surgery has evolved considerably over the past two decades. The
first attempts to allow clinicians to transfer virtual implant
planning into the clinical setting were static surgical guides
manufactured using CAD/CAM technology. The static guides improved
the accuracy of the surgery, but they were not flexible and did not
allow for changes during the surgery. To address these limitations,
dynamic navigation systems have been developed that allow real-time
tracking and visualization of surgical instruments during the
placement of implants (4).
Recently, robotic-assisted surgical systems have emerged as
innovative developments in implant dentistry. These systems
integrate digital treatment planning, navigation technology and
robotic control mechanisms to allow the highly accurate placement
of the implant. Robotic platforms have already shown promising
results in terms of positional accuracy and consistency (5). Artificial intelligence (AI), machine
learning and augmented reality (AR) are being increasingly used in
digital workflows. These technologies have the potential to lead to
improved diagnoses, treatment planning, surgical guidance and
post-operative evaluation (5). The
integration of robotics, navigation systems and intelligent digital
technologies is likely to transform the future of periodontal and
implant surgery. The present review aimed to provide a detailed
survey of the use of robotics and navigation systems in periodontal
and implant surgery covering their development, technological
principles, clinical applications, accuracy, benefits, limitations
and future perspectives.
2. Literature search methods
Review design and literature
search
The present study provides a structured narrative
review of the development, principles, clinical applications,
accuracy, limitations and future prospects of computer-assisted
navigation and robotic systems in periodontal and implant
surgery.
A narrative review design was selected as the topic
encompasses diverse evidence, including historical reports,
technical investigations, laboratory and cadaveric studies,
clinical studies, systematic reviews and meta-analyses. The
objective was to integrate these different forms of evidence rather
than answer a single narrowly defined intervention question.
Accordingly, the preferred reporting items for systematic reviews
and meta-analyses (PRISMA) guidelines were not applied, as this
article was not designed as a systematic review or meta-analysis.
Nevertheless, methodological transparency and critical
interpretation were incorporated to reduce selective reporting and
unsupported conclusions. A structured literature search was
performed using the PubMed/MEDLINE, Scopus, Web of Science and the
Cochrane Library databases. Additional relevant publications were
identified by screening the reference lists of key systematic
reviews, meta-analyses and landmark studies. The search strategy
combined terms related to robotics, computer-assisted surgery,
navigation, implant dentistry, periodontology and emerging digital
technologies. The principal search terms included the following:
[‘robotic surgery’ OR robotics OR ‘robot-assisted surgery’ OR
‘robotic-assisted surgery’ OR ‘robot-assisted implant placement’)
AND (‘computer-assisted surgery’ OR ‘computer-aided implant
surgery’ OR ‘dynamic navigation’ OR ‘static surgical guide’ OR
‘image-guided surgery’) AND (‘dental implant’ OR ‘implant
placement’ OR periodont* OR ‘periodontal surgery’ OR ‘periodontal
regeneration’].
Additional terms included ‘artificial intelligence’,
‘augmented reality’, ‘machine learning’, ‘digital workflow’, ‘image
registration’, ‘tracking’ and ‘calibration’. The search period
should be specified according to the actual search conducted:
January, 2000 to August 2026.
Eligibility criteria. Publications were
included when they addressed the historical development, technical
principles, accuracy, clinical applications, limitations or future
potential of computer-assisted navigation or robotic systems in
implant or periodontal surgery. Systematic reviews, meta-analyses,
clinical trials, observational studies, technical investigations,
laboratory studies, cadaveric studies and relevant conceptual
articles were considered.
Publications were excluded if they were unrelated to
dental or periodontal surgery, focused exclusively on nonsurgical
dental robotics, lacked sufficient methodological information, or
consisted of promotional material, conference abstracts or
unsupported opinions. Historical and technical publications were
retained when they were critical for understanding technological
development.
Study selection and evidence synthesis.
Relevant articles were selected on the basis of their alignment
with the review objectives, methodological transparency and
scientific contribution. The literature is organized thematically
according to technological evolution, static guidance, dynamic
navigation, robotic-assisted surgery, periodontal applications,
accuracy, AI, limitations and future directions.
As this was a narrative review, no formal
quantitative pooling or meta-analysis were performed. Numerical
findings were interpreted within their original methodological
context, considering differences in study design, implant location,
imaging protocols, registration methods, operator experience and
outcome definitions.
When multiple publications addressed the same
technology or dataset, preference was given to the most
comprehensive and methodologically robust source. Original studies
were consulted when detailed information regarding surgical
protocols, accuracy measurements or clinical outcomes was needed to
avoid double-counting evidence.
Management of conflicting
evidence
Conflicting findings were examined in terms of study
design, sample size, anatomical site, bone conditions, imaging and
registration protocols, operator experience, comparator type and
outcome definitions. Greater interpretive weight was given to
well-designed prospective clinical studies, transparent systematic
reviews and investigations reporting clinically meaningful
outcomes.
Findings from in vitro or cadaveric studies
were primarily used to assess technical feasibility and positional
accuracy, whereas clinical studies were prioritized when safety,
postoperative morbidity, implant outcomes and patient-centered
effects were discussed. When discrepancies remained unresolved,
they were reported explicitly rather than selecting only favorable
results.
Evidence quality and critical
appraisal
A single formal risk-of-bias tool was not applied to
all publications as the review included heterogeneous evidence
types that require different assessment criteria. Instead, each
source was considered in terms of study design, sample
characteristics, methodological transparency, comparator
appropriateness, outcome validity, follow-up duration, statistical
reporting, potential bias, external validity and conflicts of
interest.
Technical accuracy outcomes, such as coronal, apical
and angular deviation, were distinguished from clinical outcomes
including implant survival, peri-implant health, prosthetic
complications, morbidity, patient satisfaction and
cost-effectiveness. Systematic reviews and meta-analyses were
interpreted with attention to heterogeneity, methodological quality
and whether reported differences were clinically meaningful.
The quality and transparency of the narrative review
were guided by the principles of the Scale for the Assessment of
Narrative Review Articles (SANRA), particularly the description of
the literature search, adequacy of reference, scientific reasoning
and presentation of relevant outcomes (6).
Limitations of the review. The present review
has several limitations. Although a structured search strategy was
used, the process was not based on a prospectively registered
systematic-review protocol, duplicate independent screening or
formal risk-of-bias assessment of every included study. Selection
bias and publication bias therefore cannot be excluded.
The available literature is also heterogeneous, with
substantial variation in imaging workflows, registration and
calibration methods, implant sites, surgical protocols, operator
experience and outcome definitions. Much of the evidence concerns
technical accuracy in controlled experimental settings rather than
long-term clinical outcomes. In addition, the terminology related
to navigation, robotics and autonomous surgery is inconsistently
applied across publications.
Finally, evidence concerning robotic applications in
periodontology remains considerably less developed than that
concerning computer-assisted implant placement. Accordingly,
emerging periodontal applications, AI integration and autonomous
surgical functions should be interpreted as investigational unless
supported by direct clinical evidence (5).
3. Historical evolution of computer-assisted
navigation and robotic systems in implant dentistry
The evolution of computer-assisted and robotic
technologies in implant dentistry has been driven by the need to
improve the transfer of a prosthetically determined treatment plan
to the surgical field. Conventional freehand implant placement
remains dependent on the interpretation of imaging by the
clinician, three-dimensional anatomical assessment and
intraoperative visual and tactile feedback. Although experienced
clinicians can achieve predictable outcomes using freehand
techniques, implant positioning may be influenced by restricted
surgical access, anatomical limitations, operator experience and
difficulty maintaining the planned angulation and depth throughout
osteotomy preparation. Computer-assisted technologies were
therefore developed not to replace clinical judgment, but to
improve the consistency of treatment planning and surgical
execution (7,8).
From radiographic assessment to
three-dimensional digital planning
Early implant planning relies primarily on
two-dimensional radiographs and clinical examination. Although
these methods provided useful information regarding tooth position
and general anatomical relationships, they provided limited
representation of three-dimensional bone morphology and could not
consistently demonstrate the spatial association between the
proposed implant and critical anatomical structures. The
introduction of three-dimensional imaging, particularly CBCT,
substantially improved the ability to assess available bone,
anatomical constraints and prosthetically relevant implant
positions (9,10).
The availability of three-dimensional imaging did
not resolve the problem of intraoperative plan transfer. A virtual
implant position could be planned with considerable precision, yet
the final osteotomy could still deviate from that plan during
freehand surgery. This distinction between planning accuracy and
execution accuracy was central to the subsequent development of
computer-aided implant surgery. Digital planning should therefore
be regarded as an enabling component of the surgical workflow
rather than a complete solution to intraoperative variability
(7,8).
Emergence of static computer-assisted
implant surgery
Static computer-assisted implant surgery was
developed to transfer the virtual treatment plan to the patient
through a patient-specific surgical guide. By restricting the
initial drilling direction and, in fully guided protocols,
subsequent instrumentation, static guides aimed to reduce
deviations in implant position and angulation. Their principal
contribution was the standardization of the planning-to-surgery
pathway, particularly in cases where prosthetically driven
positioning or proximity to anatomical structures required greater
positional control (8,11-13).
Nevertheless, static guidance introduced critical
trade-offs. Its accuracy depends on the quality of the CBCT and
surface-scan data, the accuracy of image registration and guide
fabrication, the stability and seating of the guide, and the
ability of the clinician to follow the prescribed drilling
sequence. In addition, a static guide provides limited flexibility
when intraoperative findings differ from those of the preoperative
plan. Restricted mouth opening, posterior access, bone quality,
flap management and the need for unanticipated surgical
modifications may further reduce its practical advantages (8,11-13).
Accordingly, although static guidance improved the
reproducibility of a predefined plan, it did not eliminate the
influence of clinical circumstances or technical errors. Its value
is therefore greatest when the preoperative plan is reliable, the
guide is accurately fabricated and the surgical situation remains
sufficiently consistent with the planned workflow (8,11-13).
Transition from static guidance to
dynamic navigation
Dynamic navigation emerged partly in response to the
limited adaptability of static surgical guides. These systems use
optical or electromagnetic tracking to display the real-time
position of the surgical handpiece or implant relative to the
virtual plan. Unlike static guidance, dynamic navigation allows the
clinician to modify the surgical trajectory during the procedure,
while maintaining access to updated positional information
(7,8,14).
This flexibility may be particularly relevant in
anatomically complex cases, limited-access regions or situations in
which intraoperative findings require modification of the original
plan. Dynamic navigation does not simply transfer the risks
associated with static guidance into a more advanced format. It
introduces additional dependencies, including accurate patient
registration, instrument calibration, uninterrupted tracking,
appropriate camera positioning and continuous interpretation of the
navigation display (7,8).
Furthermore, dynamic navigation requires the
clinician to coordinate attention between the surgical field and
the monitor. Consequently, the technology may reduce some forms of
positional uncertainty, while increasing the critical role of
training, visuomotor coordination and system familiarity. Clinical
studies and systematic reviews have reported favorable accuracy
outcomes for dynamic navigation (4,15-17);
however, differences in navigation platforms, implant sites,
registration methods, operator experience and study design limit
direct comparisons between investigations (7,8).
Reported technical advantages should therefore be interpreted as
context-dependent rather than as evidence of universal
superiority.
Development of robotic-assisted
implant surgery
Robotic-assisted implant surgery represents a
further integration of digital planning, tracking, mechanical
guidance and, in some systems, automated execution of predefined
components of the surgical task. The rationale for robotic
assistance is based on the possibility of improving the
reproducibility of planned movements and reducing selected forms of
operator-dependent variability (11-13,18).
The term ‘robotic surgery’ encompasses systems with
substantially different levels of automation and clinician control.
Some platforms provide navigational information, whereas others
constrain handpiece movement or assist in maintaining a planned
trajectory. Fully autonomous implant placement, in which a robot
independently performs the complete surgical procedure without
continuous clinician supervision, should not be considered in
established routine clinical practice. Current systems are more
appropriately understood as clinician-supervised guidance,
movement-restriction or task-assistance technologies (12,18).
The emergence of robotic systems also illustrates
why technological sophistication should not automatically be
equated with clinical superiority. Robotic performance remains
dependent on the accuracy of the digital plan, imaging data,
registration, calibration and tracking workflow. In addition, the
system must operate within the anatomical and mechanical
constraints of the clinical environment. Comparative studies have
reported favorable positional accuracy for robotic-assisted implant
placement; however, the available evidence includes in vitro
models, controlled experimental settings and relatively limited
clinical cohorts. Systematic reviews have also identified
heterogeneity in study design and insufficient evidence for some
direct comparisons, particularly between robotic and static-guided
approaches (11-13,18).
Thus, although robotic assistance may improve the
reproducibility of selected surgical movements, its technical
capabilities should not be interpreted as proof of superior implant
survival, peri-implant health, prosthetic performance or patient
satisfaction. These outcomes require independent clinical
evaluation and longer-term follow-up.
Historical progress and the
redistribution of surgical risk
The progression from freehand surgery to static
guidance, dynamic navigation and robotic assistance should not be
interpreted as a linear movement toward error-free surgery.
Alternatively, each technological generation has attempted to
reduce particular sources of uncertainty, while introducing new
technical and operational dependencies (8,11,12,18).
Freehand surgery relies heavily on the experience
and intraoperative judgment of the clinician. Although static
guidance improves the transferability of a predetermined plan, it
reduces intraoperative flexibility. Dynamic navigation provides
real-time feedback and adaptability, yet depends on accurate
registration, tracking and active operator interpretation. Robotic
systems may provide movement assistance or restrictions; however,
they remain dependent on the accuracy of the preceding digital
workflow and appropriate clinician oversight (7,8,13,18).
The historical development of these technologies
therefore represents a redistribution of surgical risks rather than
their elimination. Errors may shift from manual angulation and
depth control toward imaging artifacts, data fusion, registration,
calibration, tracking and software performance or inappropriate
reliance on automated guidance. This consideration is particularly
critical when systems are compared solely on the basis of their
reported positional accuracy (7,8,11-13,18).
From technical feasibility to clinical
relevance
Early investigations of computer-assisted implant
surgery understandably focused on technical feasibility and
positional accuracy. Outcomes, such as coronal deviation, apical
deviation and angular deviation provided measurable indicators of
how closely the achieved implant position corresponded to the
virtual plan. These outcomes remain crucial, particularly in
anatomically restricted or prosthetically demanding cases (7,8,11-13,18).
Nevertheless, technical accuracy is only an
intermediate outcome. A reduction in positional deviation does not
automatically lead to improved implant survival, peri-implant
health, prosthetic performance, post-operative morbidity, patient
satisfaction or cost-effectiveness. The clinical significance of a
numerical difference in deviation also depends on the implant
location, bone anatomy, prosthetic requirements, proximity to vital
structures and the magnitude of the deviation relative to
clinically acceptable limits (11-13,18).
More recent comparative research has attempted to
evaluate static, dynamic and robotic approaches within a common
analytical framework (19-21).
Differences in imaging protocols, surgical workflows, operator
experience, implant sites and outcome definitions continue to
complicate interpretation. For example, a robotic system
demonstrating excellent accuracy in a controlled model may not
provide the same magnitude of benefit in routine clinical practice
involving patient movement, restricted access or unexpected
anatomical findings. Consequently, evidence of improved positional
accuracy should be distinguished from evidence of improved clinical
effectiveness. The former indicates closer agreement between the
planned and achieved implant positions, whereas the latter requires
the demonstration of meaningful improvements in safety, efficiency,
biological outcomes, prosthetic outcomes or patient experience
(11,12,18).
Current interpretation of the
historical trajectory
The historical development of computer-assisted and
robotic implant surgery is best understood as an expansion of the
technological options of the clinician, rather than a replacement
of surgical expertise. Static guides, dynamic navigation and
robotic assistance may each be advantageous in selected situations;
however, their effectiveness depends on appropriate case selection,
technical reliability, operator training and integration with sound
surgical judgment (7,8,11-13,18).
The central contemporary question is therefore no
longer whether digital or robotic systems can improve the agreement
between planned and achieved implant positions. Instead, whether
these improvements produce meaningful advantages in safety,
efficiency, patient-centered outcomes and long-term treatment
success that justify their additional cost, complexity and training
requirements should be investigated. This distinction provides a
critical basis for evaluating the current evidence and defining the
future role of robotics in implant and periodontal surgery
(11-13,18).
4. Navigation system principles
Navigation systems depend on the integration of
advanced imaging, planning software, tracking technologies and
real-time feedback processes. The workflow generally begins with
the acquisition of CBCT images, which provide detailed
three-dimensional information about the anatomy of the patient.
Digital intraoral scans are often fused with CBCT data to generate
a virtual model that accurately represents hard and soft tissues.
Treatment-planning software is used following image acquisition to
determine the ideal implant position according to prosthetic
requirements, bone availability, and anatomical considerations.
Virtual implant placement allows clinicians to evaluate a variety
of treatment options and optimize implant angulation, depth and
position prior to surgery (22).
An integral part of the navigation technology is registration.
Registration establishes a relationship between the actual patient
anatomy and the virtual treatment plan. Correct registration is
crucial as even minor errors can lead to clinically relevant
deviations during surgery (8).
During surgery, the positions of the patient, handpiece and
surgical instruments are recorded using optical tracking cameras.
The navigation software uses reference markers attached to the
patient and instruments to determine their exact location in
three-dimensional space. The system constantly illustrates the
drill path in relation to the planned position of the implant
providing the clinician with the opportunity to make adjustments in
real-time (4,11). Contemporary navigation systems also
provide visual and auditory feedback to help maintain the desired
angulation and depth. These features enhance spatial awareness and
allow precise implant placement even in anatomically challenging
cases (12). The combination of
pre-operative planning, accurate registration and real-time
tracking forms the foundation of dynamic navigation technology and
is important for its clinical efficacy. The principal stages of
this integrated digital workflow for image-guided dental and
periodontal surgery are schematically illustrated in Fig. 1.
 | Figure 1Digital workflow for image-guided
dental and periodontal surgery. Schematic representation of the
digital workflow, beginning with CBCT and intraoral optical data
acquisition, followed by data integration and three-dimensional
treatment planning. The planned procedure may then be transferred
to a static surgical guide, dynamic navigation system, or
robotic-assisted platform for intraoperative guidance.
Postoperative imaging and clinical assessment were used to verify
the achieved position, surgical accuracy, and subsequent soft- and
hard-tissue healing. The figure is a conceptual synthesis of the
current digital workflow and is not intended to imply that all
technologies are routinely validated for every periodontal
procedure (2,4,14,18,20,21,25,31,66,67,80,81,85,86).
CBCT, cone-beam computed tomography. |
5. Dynamic navigation systems in dental
implantology
One of the most prominent technological advancements
in the field of implant dentistry is dynamic navigation systems.
Unlike static guides that physically constrain surgical
instruments, dynamic navigation provides real-time, while
maintaining surgical flexibility (14). Several commercially available
systems are currently in clinical use, including
X-Guide®, Navident® ImplaNav®,
DENACAM® and DCARER®(23). These systems use stereoscopic
cameras and optical tracking technology to track instrument
movement during surgery (13).
Clinical studies and systematic reviews have reported relatively
minimal positional deviations with dynamic navigation-guided
implant placement. Reported mean coronal deviations have generally
been ~0.8-1.2 mm, whereas mean angular deviations range from ~2.5˚
to 4˚ (14,18,24).
These numbers are markedly lower than the typical deviations
observed in freehand implant placement and are comparable to static
guided surgery accuracy (24). One
of the main advantages of dynamic navigation is the ability to
alter treatment plans intraoperatively. In contrast to static
guides that need to be fabricated before surgery, navigation
systems can be used by clinicians to respond to unforeseen anatomic
findings or changes in the treatment plan without sacrificing
accuracy (14). Dynamic navigation
has been found to be particularly beneficial in complex clinical
situations, such as immediate implant placement, flapless surgery,
multiple implant rehabilitation and the treatment of patients with
limited bone volume. The ability to visualize the position of the
drill in real-time improves safety by allowing clinicians to avoid
critical anatomic structures, such as the inferior alveolar nerve
and the maxillary sinus (25). A
reduction in operator-dependent variability with
navigation-assisted surgery has also been demonstrated in several
studies (16,17,26,27).
With appropriate training, acceptable levels of accuracy can be
obtained by clinicians with limited experience with implants
(25). There is a learning curve,
and proficiency depends on familiarity with digital workflow,
registration procedures and navigation protocols (28). Despite its benefits, dynamic
navigation has several limitations. Implementation and clinical
performance can be affected by high equipment costs, calibration
requirements, registration errors and the possibility of tracking
interruptions. Increasing evidence supports its use as a reliable
and accurate alternative to conventional techniques of implant
placement (13,18).
6. Robotic-assisted surgery
implantation
Robotic-assisted implant surgery is the latest step
in computer-aided dental implant placement. These systems combine
digital treatment planning, dynamic navigation and robotic guidance
to improve accuracy and consistency during surgery (21). Surgical robots can be broadly
categorized into passive, semi-active and active systems. Passive
robots are used to guide the motion of the instrument, but do not
control it. Semi-active systems provide clinicians with control,
yet limit movement beyond preset parameters. Active systems conduct
surgical tasks autonomously following preprogrammed instructions,
although fully autonomous dental implant surgery continues to be
mostly experimental (29). The
majority of the robotic systems currently available in dentistry
today are semi-active. Virtual implant planning is followed by the
use of a robotic platform to guide clinicians to maintain the
planned trajectory during osteotomy preparation. The robot
continuously monitors the drill position and provides corrective
guidance if any deviations occur (30,31).
The first clinical applications of robotic implant surgery have
exhibited promising results, with several studies reporting
improved positional accuracy compared with freehand techniques
(32,33). Recent systematic reviews have
demonstrated that compared with conventional methods of implant
placement, robotic systems can achieve lower angular, coronal and
apical deviations (20,34). Of note, deviations of <2 degrees
have been reported, highlighting the marked precision possible with
robotic guidance (28,31,35).
Robotic systems have several theoretical advantages. Increased
accuracy may improve prosthetically driven implant placement,
reduce the risk of surgical complications and allow treatment in
anatomically complex locations. Furthermore, robotic assistance may
reduce operator fatigue and improve the consistency of procedures
among clinicians with different levels of experience (28). Another key advantage is the
potential integration of robotics with AI and machine learning
algorithms. Future robotic platforms may be able to analyze
intraoperative data, identify deviations from treatment plans and
provide predictive guidance in real time. Such developments may
result in improved surgical outcomes and lower risks of the
procedure (28,31,36,37).
However, robotic implant surgery faces critical challenges. High
acquisition costs, technical complexity, training needs and limited
long-term clinical evidence still hinder widespread adoption.
Regulatory approval, medico-legal liability and ethical issues are
also obstacles that need to be overcome before fully autonomous
robotic systems can be considered standard in clinical practice
(38-42).
Nevertheless, the existing evidence points to robotic-assisted
implant surgery as a promising innovation in digital dentistry,
which could play an increasingly important role in future implant
rehabilitation strategies.
A critical distinction should be made between the
accuracy of osteotomy preparation and the accuracy of the final
implant position. Osteotomy accuracy refers to the extent to which
the prepared osteotomy follows the planned entry point, angulation,
depth and trajectory. By contrast, the final implant placement
accuracy reflects the deviation between the planned and achieved
positions of the inserted implant, including coronal, apical and
angular discrepancies. Although accurate osteotomy preparation may
contribute to precise implant placement, the two outcomes are not
interchangeable. Implant positioning may also be influenced by
factors, such as drill deviation, osteotomy enlargement, bone
density, implant insertion torque, implant-osteotomy interactions,
guide or tracking stability and intraoperative changes (43,44).
Therefore, studies reporting osteotomy accuracy should not
automatically be interpreted as demonstrating the equivalent
accuracy of final implant placement. Where possible, these outcomes
should be reported and interpreted separately.
Robotic systems in dentistry can be classified
according to the degree of human involvement, the tasks performed
and the extent of autonomy. Current platforms range from passive or
surgeon-guided systems that provide mechanical stabilization to
semi-active and task-autonomous systems capable of executing
predefined steps, such as osteotomy preparation or implant
placement. This classification is clinically relevant as the term
‘robotic surgery’ encompasses systems with substantially different
capabilities and levels of validation. A summary of the principal
categories and their current clinical status in implant and
periodontal surgery is provided in Table I.
 | Table IClassification and current clinical
status of robotic systems in implant and periodontal surgery. |
Table I
Classification and current clinical
status of robotic systems in implant and periodontal surgery.
| Robotic
category | Defining
characteristics | Representative
systems or applications | Current clinical
status | Established or
reported capabilities | Principal
limitations and evidence gaps |
|---|
| Passive or
surgeon-guided robotic systems | The robot provides
mechanical support, stabilization, or trajectory guidance, while
the clinician actively controls instrument movement. | Collaborative
robotic platforms; surgeon-guided implant robots; Yomi-type systems
in clinician-controlled workflows | Early clinical use
for selected implant procedures | May reduce hand
tremor, improve instrument stabilization, and support transfer of a
digitally planned implant trajectory. | Clinical
performance remains dependent on operator control, registration,
planning, and system calibration. Evidence is primarily
implant-focused, with limited long-term comparative outcomes. |
| Semi-active or
cooperative robotic systems | The clinician
positions or guides the robotic arm, while the system assists with
trajectory alignment, drilling, depth control, or selected
procedural steps. | Remebot; Theta;
human-robot collaborative dental implant systems | Early clinical
implementation; limited but growing clinical evidence | Supports predefined
osteotomy preparation and implant positioning while retaining
direct clinician supervision and control. | Requires manual arm
positioning, instrument changes, activation, and continuous
supervision. Workflow complexity, training requirements, and
limited independent validation remain concerns. |
| Active or
task-autonomous robotic systems | The robot executes
predefined surgical tasks according to a digital plan, such as
osteotomy preparation or implant insertion, within specified safety
boundaries. | Selected autonomous
implant robots, including systems described in recent robotic
implant studies | Limited clinical
application; investigational-to-early clinical status | May provide
reproducible execution of selected planned tasks and reduce
variability associated with manual hand movements. | Autonomy is
generally restricted to specific tasks and does not encompass
independent diagnosis, treatment planning, intraoperative judgment,
or management of unexpected anatomy. |
| Fully autonomous
surgical robots | The system
independently performs the complete surgical workflow, including
diagnosis, planning, decision-making, execution, and management of
unexpected intraoperative events. | No established
fully autonomous robotic system for routine dental implant or
periodontal surgery | Not clinically
established | Conceptually could
provide highly standardized surgical execution under predefined
conditions. | Major unresolved
issues include safety, accountability, anatomical variability,
soft-tissue deformation, unexpected bleeding, ethical
responsibility, regulatory approval, and reliable failure
recovery. |
| Tele-operated
robotic systems | The surgeon
controls robotic instruments remotely through a master-slave
interface. | Primarily
experimental or adapted surgical-robotic concepts; limited dental
application | Not established for
routine periodontal or implant surgery | May facilitate
remote. manipulation, magnified visualization, and potential access
to restricted surgical fields | Requires reliable
communication, force feedback, latency control, specialized
infrastructure, and robust safety mechanisms. Dental evidence
remains limited. |
| Robotic systems for
implant osteotomy preparation | Robotic assistance
is directed mainly toward drill positioning, angulation, depth, and
trajectory control. | Robotic implant
osteotomy systems, including semi-active and task-autonomous
platforms | Most clinically
developed robotic application | Can improve the
reproducibility of planned osteotomy geometry and implant
trajectory in selected cases. | Accuracy does not
ensure adequate primary stability, ideal biological positioning, or
long-term peri-implant tissue health. |
| Robotic systems for
implant insertion | The robotic
platform assists or executes implant insertion after osteotomy
preparation. | Integrated robotic
implant placement workflows | Early clinical and
technology-development stage | May improve control
of insertion trajectory and planned implant positioning. | Evidence is limited
regarding insertion torque, tactile feedback, implant stability,
postoperative complications, and long-term survival. |
| Robotic systems for
periodontal microsurgery | Proposed use for
flap manipulation, root-surface instrumentation, microsuturing,
graft stabilization, or minimally invasive access. | Experimental or
conceptual periodontal robotic applications | Preclinical,
conceptual, or investigational | Potentially could
improve instrument stability and precision during technically
demanding microsurgical procedures. | Periodontal tissues
are deformable, inflamed, vascular, and biologically dynamic.
Current systems cannot reliably account for tissue displacement,
bleeding, wound tension, or biological healing. |
| Robotic systems for
periodontal regeneration | Proposed robotic
assistance for membrane placement, biomaterial delivery, graft
positioning, or regenerative-site stabilization. | Conceptual robotic
regenerative workflows | Conceptual or
preclinical; no established clinical standard | Could theoretically
support standardized placement of regenerative materials and
minimally invasive handling. | Mechanical
precision cannot predict vascularization, cell recruitment, wound
stability, tissue integration, or periodontal attachment gain.
Clinical evidence is currently insufficient. |
7. Clinical evidence and systematic reviews
evaluating computer-assisted implant surgery
Clinical studies and systematic reviews have
evaluated static-guided surgery, dynamic navigation, and
robotic-assisted implant placement primarily in terms of positional
accuracy, including coronal, apical and angular deviations between
planned and achieved implant positions (38-42).
The available evidence also provides insight into procedural
efficiency, complications and clinical outcomes, although
substantial heterogeneity exists in imaging protocols, guidance
systems, operator experience, study design, and outcome reporting.
A summary of representative clinical studies and systematic
reviews, their principal findings, and major methodological
limitations is presented in Table
II.
| Table IIClinical evidence and systematic
reviews evaluating computer-assisted implant surgery. |
Table II
Clinical evidence and systematic
reviews evaluating computer-assisted implant surgery.
| First author, year
of publication | Design | Technology | Sample/
comparator | Coronal
deviation | Apical
deviation | Angular
deviation | Follow-up | Main findings | Major
limitations | (Refs.) |
|---|
| Vercruyssen,
2014 | Narrative review of
guided surgery | Static
computer-assisted implant surgery | Guided implant
placement; comparison with conventional approaches discussed | NR | NR | NR | Not applicable | Reviewed the
principles, accuracy, indications, and limitations of guided
implant surgery. Emphasized the importance of accurate imaging,
planning, guide fabrication, and clinical execution. | Narrative design;
no pooled quantitative analysis; evidence largely implant-focused;
limited patient-centered outcomes. | (18) |
| Tahmaseb, 2018 | Systematic review
and meta-analysis | Static
computer-assisted implant surgery | Clinical and
laboratory studies of static-guided implant placement | Pooled deviations
reported in the original review | Pooled deviations
reported in the original review | Pooled deviations
reported in the original review | Primarily immediate
postoperative assessment | Static guidance
generally improved transfer of the virtually planned implant
position and demonstrated clinically acceptable accuracy under
selected conditions. | Considerable
heterogeneity in study design, guide support, implant site, imaging
protocols, and deviation reporting; limited long-term clinical
outcomes. | (2) |
| Jorba-García,
2021 | Systematic review
and meta-analysis | Dynamic
computer-assisted implant surgery | Clinical studies
evaluating dynamic navigation | NR in summary
data | NR in summary
data | NR in summary
data | Primarily immediate
postoperative assessment | Dynamic navigation
provided accurate implant placement while allowing intraoperative
modification of the planned trajectory. Accuracy was influenced by
registration, tracking, calibration, and operator-related
factors. | Small and
heterogeneous evidence base; variable navigation systems and
surgical protocols; limited comparative clinical trials; limited
long-term biological outcomes. | (4) |
| Khaohoen, 2024 | Systematic review
and meta-analysis of clinical trials | Static, dynamic,
and robotic-assisted surgery | 67 studies; 5,673
implants; 53 static, 15 dynamic, and 2 robotic studies | Overall: 1.11 mm
(95% CI, 1.02-1.19). Static: 1.11 mm; dynamic: 1.18 mm; robotic:
0.81 mm | Overall: 1.40 mm
(95% CI, 1.31-1.49). Static: 1.44 mm; dynamic: 1.36 mm; robotic:
0.77 mm | Overall: 3.51˚ (95%
CI, 3.27-3.75). Static: 3.58˚; dynamic: 3.51˚; robotic: 1.71˚ | Predominantly
immediate postoperative evaluation | Computer-assisted
approaches demonstrated measurable accuracy in three-dimensional
implant positioning. Robotic-assisted surgery showed the lowest
pooled deviations, although it was represented by only two clinical
studies. Fully guided protocols were more accurate than
pilot-guided protocols in the analyzed comparisons. | Robotic evidence
was very limited; substantial heterogeneity; mixed study designs
and clinical protocols; technical accuracy was not equivalent to
improved implant survival, peri-implant health, or patient
benefit. | (21) |
| Sankar, 2025 | Systematic review
and meta-analysis including clinical and in vitro
studies | Robotic-assisted
implant surgery compared with freehand, static, and dynamic
techniques | Clinical and
laboratory studies; exact clinical subgroup values should be
extracted from the full text before final submission | Clinical subgroup:
extract separately; not reported in the available summary | Clinical subgroup:
extract separately; not reported in the available summary | Clinical subgroup:
extract separately; not reported in the available summary | Primarily immediate
postoperative or model-based assessment | Evaluated whether
robotic assistance improved implant placement accuracy compared
with conventional and computer-assisted methods. The review
included risk-of-bias assessment using QUIN and JBI tools. | Combined clinical
and in vitro evidence; differences in study settings and
comparators; limited clinical evidence; possible overinterpretation
of statistically significant differences as clinically
meaningful. | (20) |
| Khaohoen, 2025 | Systematic review
and meta-analysis of clinical robotic studies | Robotic
computer-assisted implant surgery | 16 clinical
studies; 908 implants | 0.69 mm (95% CI,
0.61-0.77); I2=94% | 0.72 mm (95% CI,
0.64-0.79); I2=93% | 1.62˚ (95% CI,
1.34-1.89); I2=96% | Primarily immediate
postoperative assessment | Robotic implant
placement demonstrated relatively low pooled deviations in clinical
studies. Substantial heterogeneity was observed across all accuracy
outcomes. | Very high
statistical heterogeneity; differences in robot autonomy, camera
systems, dentition, surgical workflows, and operator experience;
limited evidence for long-term clinical effectiveness or
cost-effectiveness. | (77) |
| Wu, 2025 | Systematic review
and network meta-analysis | Robotic, dynamic,
static-guided, and freehand implant surgery | Clinical and
preclinical studies; exact sample size and subgroup extraction
should be confirmed from the final publication | NR in available
summary | NR in available
summary | NR in available
summary | Primarily immediate
postoperative accuracy assessment | Compared the
relative accuracy of robotic, dynamic, static-guided, and freehand
implant placement using network meta-analysis. | Network comparisons
may be affected by indirectness, differences in study populations,
protocols, implant sites, and risk of bias; technical accuracy does
not establish clinical superiority. | (66) |
| Nava, 2026 | Systematic review
and network meta-analysis | Static, dynamic,
and robotic guidance for immediate implant placement | 18 studies; 780
immediately placed implants; 6 RCTs, 2 prospective case series, 7
retrospective case series, and 3 retrospective studies | Extract from full
text; available summary emphasizes angular outcomes | Extract from full
text | Compared with
freehand, angular deviation decreased by 3.36˚ with robotic, 2.66˚
with dynamic, 1.73˚ with half-guided static, and 1.85˚ with fully
guided static protocols | Immediate implant
placement; primarily postoperative accuracy assessment | Guided protocols
were associated with improved angular accuracy compared with
freehand placement in immediate implant placement. The findings
suggest potential benefits in anatomically demanding immediate
implant workflows. | Mixed evidence
levels, including case series and retrospective studies; indirect
comparisons; limited long-term implant and peri-implant tissue
outcomes; immediate implant findings may not generalize to all
clinical situations. | (29) |
| Alqutaibi,
2023 | Scoping review of
clinical robotic studies | Robotic
computer-assisted implant surgery | 27 studies; 983
patients; 1,546 implants | 0.67 mm (95% CI,
0.62-0.73) | 0.71 mm (95% CI,
0.66-0.77) | 1.68° (95% CI,
1.46-1.90) | Primarily immediate
postoperative accuracy assessment | Robotic
computer-assisted implant surgery demonstrated high positional
accuracy across clinical studies and showed higher accuracy than
freehand, static, and dynamic techniques in comparative
analyses. | The evidence
remains predominantly accuracy-based; study heterogeneity, cost,
learning-curve effects, limited independent validation, and
uncertain clinical relevance of small numerical differences remain
important concerns. | (36) |
8. Technical accuracy vs. clinical
effectiveness
Technical accuracy is a key advantage of
computer-assisted implant surgery; however, it should not be
considered a surrogate for overall clinical effectiveness.
Static-guided, dynamic navigation and robotic-assisted workflows
generally demonstrate smaller deviations between the planned and
achieved implant positions than freehand surgery does, particularly
in terms of coronal, apical and angular measurements. Nevertheless,
these outcomes primarily assess the accuracy of transferring a
virtual plan to the surgical field and do not independently
establish improvements in biological healing, peri-implant tissue
health, implant survival, or patient satisfaction (2,4,20,29).
A recent systematic review and network meta-analysis
of randomized clinical trials evaluating immediate implant
placement reported that compared with freehand surgery, static and
dynamic computer-assisted approaches improved positional accuracy
(29). No significant differences
were identified between the different computer-assisted modalities
and robotic-assisted surgery was not represented in the included
randomized trials (29).
Similarly, recent evidence indicates that robotic-assisted implant
placement can achieve high positional accuracy; however, the
available studies remain predominantly focused on radiographic
deviations and include heterogeneous clinical protocols and study
designs (20).
Notably, the available clinical evidence suggests
that improvements in implant positioning do not consistently
translate into superior patient-centered or biological outcomes.
Recent international evidence has demonstrated that although
computer-assisted implant surgery provides strong evidence for
improved placement accuracy, outcomes such as primary implant
stability, implant survival, marginal bone loss, peri-implant
tissue health, and intra- and post-operative complications are
broadly comparable between guided and nonguided approaches.
Evidence regarding treatment efficiency and long-term clinical
advantages remains limited or inconsistently reported (21). Some aesthetic benefits may be
associated with more prosthetically driven implant positioning,
particularly in anatomically demanding or aesthetically sensitive
cases, but these effects are difficult to separate from case
selection, clinician expertise, prosthetic planning, and adjunctive
hard- and soft-tissue procedures (21).
The clinical value of computer-assisted surgery
therefore depends not only on positional precision, but also on the
quality of the initial diagnosis, prosthetically driven planning,
anatomical risk assessment, surgical execution, implant design,
soft- and hard-tissue management, and maintenance care. A
technically accurate implant may still produce an unsatisfactory
outcome if the treatment plan is biologically inappropriate, if the
implant is placed in an unfavorable restorative position, or if
peri-implant tissue deficiencies are not adequately managed.
Conversely, minor deviations from the virtual plan may have limited
clinical significance when they remain within the anatomical and
prosthetic tolerance of the patient.
This distinction is particularly relevant when
considering the potential application of robotics and navigation in
periodontology. Periodontal outcomes depend on factors, such as
inflammation control, wound stability, vascularity, tissue
thickness, flap adaptation, root-surface characteristics,
patient-related healing responses and regenerative potential. These
biological variables cannot be predicted solely from the accuracy
of instrument positioning (45-47).
Consequently, evidence demonstrating improved implant placement
accuracy should not be directly extrapolated to periodontal flap
surgery, root-surface instrumentation, connective tissue grafting,
microsuturing, or periodontal regeneration.
Future investigations should evaluate
computer-assisted surgery as part of the complete treatment
pathway, rather than as an isolated accuracy-enhancing procedure.
The relevant outcomes should include postoperative morbidity,
treatment time, complications, prosthetic and aesthetic outcomes,
marginal bone and soft-tissue stability, implant survival,
patient-reported outcomes, cost-effectiveness and long-term
maintenance requirements. Such studies would clarify whether
improved technical precision produces clinically meaningful
benefits and identify the patient groups and procedural contexts in
which these technologies provide the greatest value. Evidence of
improved positional accuracy should be distinguished from evidence
of improved clinical effectiveness. The former indicates closer
agreement between the planned and achieved implant positions,
whereas the latter requires demonstration of meaningful
improvements in safety, efficiency, biological outcomes, prosthetic
outcomes, or patient experience. A comparative overview of freehand
surgery, static-guided surgery, and dynamic navigation in dental
and periodontal procedures is presented in Fig. 2.
 | Figure 2Comparison of freehand surgery,
static-guided surgery, and dynamic navigation in dental and
periodontal procedures. Comparison of the three surgical approaches
according to their operating principles, typical equipment,
intraoperative flexibility, reported accuracy, line-of-sight
requirements, learning curve, cost, advantages, limitations and
common clinical applications. Freehand surgery relies primarily on
the anatomical knowledge and intraoperative judgment of the
clinician. Static-guided surgery transfers a digitally planned
trajectory through a prefabricated surgical guide, whereas dynamic
navigation provides real-time tracking and visual guidance of
surgical instruments. The figure illustrates general functional
differences and should not be interpreted as evidence of the
universal superiority of one approach, particularly for periodontal
procedures (2,4,11,14,18,25,65). |
9. Robotics in periodontal surgery: Current
evidence, translational potential and research gaps
Compared with implant placement, the application of
robotics in periodontal surgery remains substantially less
developed. The majority of the available evidence concerning dental
robotics has focused on implant osteotomy and implant positioning,
whereas periodontal procedures involve additional biological and
technical challenges, including manipulation of deformable soft
tissues, preservation of vascularity, root-surface instrumentation,
wound stabilization and regeneration of multiple periodontal tissue
(31,36,37,48).
Therefore, the accuracy outcomes reported for robotic implant
placement cannot be directly extrapolated to periodontal
microsurgery or regenerative procedures.
Several periodontal interventions could
theoretically benefit from robotic assistance, including minimally
invasive flap design, access to intrabony defects, root-surface
instrumentation, membrane or scaffold placement, connective tissue
graft positioning and microsurgical suturing. These applications
should currently be regarded as conceptual or investigational,
rather than as having established clinical indications. The ability
of a robotic system to reproduce a predefined movement does not
necessarily demonstrate improved periodontal healing, connective
tissue attachment or long-term tooth retention (35,48,49).
Periodontal regeneration
Robotic assistance may eventually support the
standardized placement of membranes, scaffolds or biomaterials
within periodontal defects. Three-dimensional imaging and digital
planning could assist in individualized defect assessment, while
robotic or semi-active instruments might improve the positioning of
regenerative materials in anatomically complex sites.
Nevertheless, periodontal regeneration is not simply
a problem of spatial accuracy. Clinical outcomes depend on defect
morphology, wound stability, blood supply, cellular recruitment,
exclusion of epithelial migration, biomaterial characteristics and
host-related factors (46,49-53).
Current evidence supporting periodontal regeneration primarily
concerns surgical techniques, guided tissue regeneration, enamel
matrix derivatives and grafting materials rather than robotic
delivery systems. Consequently, improved membrane or scaffold
positioning would not, by itself, establish enhanced periodontal
ligament, cementum or alveolar bone regeneration (46,49-53).
Future studies should determine whether robotic
assistance improves clinically relevant outcomes such as
probing-depth reduction, clinical attachment-level gain,
radiographic defect fill, wound stability, postoperative morbidity
and long-term tooth retention. At present, direct evidence
supporting these benefits is insufficient (48,49).
Periodontal microsurgery and
soft-tissue procedures
Periodontal microsurgery and mucogingival procedures
may appear suitable for robotic assistance as they involve delicate
movements and require accurate tissue handling. Potential
applications include connective tissue graft positioning, flap
advancement, papilla reconstruction and microsuturing. The success
of these procedures depends not only on movement precision but also
on tissue thickness, elasticity, vascularity, flap tension, graft
adaptation and wound stability (54-59).
Unlike implant placement, where the target
trajectory can be defined relative to relatively stable anatomical
landmarks, periodontal soft tissues deform during retraction,
incision and suturing. Pre-programmed or mechanically constrained
movement may therefore be unsuitable if it cannot respond to tissue
resistance or unexpected anatomical changes. Robotic assistance may
ultimately be more useful for instrument stabilization, tremor
reduction or motion scaling than for autonomous execution of
complete periodontal procedures (35,49,60,61).
Evidence from periodontal microsurgery has
demonstrated that magnification and minimally invasive techniques
may improve visualization and facilitate delicate tissue handling;
however, these benefits should not be automatically attributed to
robotic technology (56-59).
Moreover, systematic reviews have reported variability in the
clinical advantages of microsurgical approaches, particularly for
patient-centered outcomes, emphasizing that technical refinement
does not always translate into clearly superior clinical results
(55-57).
Root-surface instrumentation and
periodontal debridement
Robotic or navigational assistance could
theoretically support selective root-surface instrumentation by
integrating three-dimensional imaging with instrument tracking.
Such systems may improve access to complex root morphologies or
assist in the controlled removal of calculus and contaminated
root-surface deposits.
This application presents substantial challenges.
CBCT cannot reliably identify all clinically relevant deposits,
whereas inflammation, calculus, soft-tissue coverage and bleeding
may alter the relationship between the radiographic anatomy and the
actual root surface. Effective periodontal instrumentation also
requires tactile feedback to distinguish calculus, cementum, dentin
and soft tissue (60-62).
Excessive mechanical control without adequate tactile
interpretation could increase the risk of unnecessary root-surface
removal or soft-tissue injury.
Accordingly, robotic periodontal instrumentation
should currently be regarded as a research possibility, rather than
a validated replacement for clinician-performed debridement
(48,49,62).
Future systems would require reliable tactile sensing, tissue
recognition, adaptive control and safety limits, followed by
clinical comparison with established instrumentation protocols
(35,49,60,61).
Evidence maturity of the proposed
periodontal applications
The classification of robotic and navigation-related
applications in periodontology according to the maturity of
available evidence is presented in Table III. The current evidence should
be interpreted according to the maturity of each proposed
application: The presence of a plausible technical workflow should
not be interpreted as evidence of clinical efficacy. A proposed
robotic application should be described as clinically beneficial
only when supported by appropriately designed human studies
evaluating periodontal and patient-centered outcomes.
| Table IIIClassification of robotic and
navigation-related applications in periodontology according to the
maturity of available evidence. |
Table III
Classification of robotic and
navigation-related applications in periodontology according to the
maturity of available evidence.
| Periodontal
application | Potential role of
robotics or navigation | Current evidence
status | Evidence
interpretation and principal limitations |
|---|
| Periodontal flap
surgery and minimally invasive access | Guidance of
incision design, flap elevation, instrument positioning, and
minimally invasive access to periodontal defects. |
Conceptual/investigational | No established
clinical evidence demonstrates that robotic. guidance improves
periodontal attachment gain, pocket reduction, wound healing, or
long-term tooth retention. Soft-tissue mobility, bleeding, and
anatomical variability remain major challenges |
| Root-surface
instrumentation and debridement | Potential guidance
of ultrasonic, rotary, or micro instrument positioning during
subgingival debridement and root-surface preparation. |
Preclinical/conceptual | Root morphology,
calculus distribution, tissue interference, and the need for
tactile feedback make automation challenging. Evidence supporting
superior clinical periodontal outcomes is currently lacking. |
| Periodontal
microsuturing | Assistance with
needle positioning, suture placement, knot tying, and reproducible
wound closure. | Conceptual/early
experimental | Microsuturing
requires adaptation to tissue thickness, tension, mobility, and
wound geometry. Robotic feasibility does not establish improved
wound stability, healing, or clinical attachment outcomes. |
| Connective tissue
grafting and periodontal plastic surgery | Potential
assistance with graft harvesting, graft positioning, flap
manipulation, and microsuturing. |
Investigational | Current clinical
benefits reported for periodontal microsurgery largely relate to
magnification and minimally invasive techniques rather than robotic
systems specifically. Evidence for robotic superiority in root
coverage or soft-tissue stability remains insufficient. |
| Periodontal
regeneration of intrabony defects | Potential
assistance with defect access, debridement, membrane or biomaterial
positioning, and precise wound closure. |
Conceptual/preclinical | Regenerative
outcomes depend on defect morphology, blood-clot stability,
biomaterial selection, wound closure, and biological healing.
Robotic accuracy alone cannot ensure periodontal ligament,
cementum, or bone regeneration. |
| Furcation defect
management | Potential guidance
of access, debridement, regenerative material placement, or
microsuturing in anatomically restricted furcation areas. |
Conceptual/investigational | Complex root
anatomy, restricted access, and variable defect morphology may
limit robotic implementation. Procedure-specific clinical evidence
is currently lacking. |
| Periodontal
maintenance and supportive therapy | Possible
navigation-assisted localization of residual deposits or guidance
of targeted instrumentation. | Conceptual/future
application | The clinical value
of automated or guided maintenance remains uncertain, particularly
regarding treatment efficiency, patient comfort, disease
recurrence, and long-term periodontal stability. |
| AI-assisted
periodontal assessment and treatment planning | Automated detection
of bone loss, periodontal defects, tooth morphology, and
risk-related imaging features to support treatment planning. | Early
clinical/investigational | AI may assist image
interpretation and risk stratification, but performance depends on
training datasets, image quality, external validation, and clinical
oversight. AI-generated assessments should not replace
comprehensive clinical examination. |
| Augmented- or
mixed-reality assistance in periodontal surgery | Overlay of
anatomical information, treatment plans, or surgical guidance onto
the operative field. | Preclinical/early
feasibility | Registration drift,
limited field-of-view accuracy, optical obstruction, and mismatch
between virtual images and mobile soft tissues may restrict
reliability in periodontal surgery. |
| Fully autonomous
periodontal surgery | Independent
execution of incision, instrumentation, suturing, or regenerative
procedures based on a preoperative digital plan. | Not clinically
established | Periodontal tissues
are deformable and biologically dynamic, and procedures require
continuous clinical judgment and tactile assessment. Fully
autonomous periodontal surgery remains a future research concept
rather than a routine clinical application. |
Translational barriers and research
priorities
Several factors currently limit the translation of
robotics into periodontal practice. Periodontal procedures are
highly individualized and require real-time adaptation to tissue
quality, inflammation, bleeding and defect morphology. In addition,
soft tissues are deformable and difficult to register accurately
using static three-dimensional datasets. Treatment success is
determined by biological healing and tissue integration, neither of
which can be predicted solely from instrument positioning (35,51,52).
Early research should therefore focus on
clinician-supervised and semi-active applications, such as
instrument stabilization, motion scaling, navigation-assisted
access, digitally planned placement of regenerative materials and
assistance with microsuturing. These applications should progress
through laboratory validation, and cadaveric studies where
appropriate and carefully designed clinical trials are performed
(48,56).
Clinical investigations should include
periodontal-specific outcomes, such as clinical attachment-level
gain, probing-depth reduction, gingival recession, soft-tissue
thickness, wound stability, postoperative pain, patient
satisfaction and long-term tooth retention. Technical accuracy
should be reported as a complementary endpoint rather than the sole
indicator of success (38,62,63).
Overall, robotics may eventually enhance selected
periodontal procedures; however, the current role of robotics
remains exploratory. The strongest available evidence concerns
computer-assisted implant positioning, whereas the use of robotics
in periodontal soft-tissue surgery, root-surface instrumentation
and regeneration requires independent validation. These
applications should therefore be presented as promising research
directions rather than established clinical modalities (48,52,53).
10. Potential indications and
contraindications for computer-assisted and robotic technologies in
periodontal and implant surgery
The potential indications and contraindications of
computer-assisted and robotic technologies should be interpreted
cautiously, as their clinical applicability varies according to the
procedure, platform, anatomical conditions and available supporting
evidence. Rather than representing universally established
criteria, the considerations summarized in Table IV (48,52,53)
are intended to highlight situations in which these technologies
may be considered, as well as circumstances that could limit their
reliability or clinical usefulness. This distinction is
particularly relevant for periodontal applications, where evidence
remains limited and the effects of tissue mobility, bleeding, and
intraoperative anatomical changes may reduce the direct
applicability of implant-related experience.
| Table IVPotential indications and limitations
of computer-assisted and robotic technologies in periodontal and
implant surgery. |
Table IV
Potential indications and limitations
of computer-assisted and robotic technologies in periodontal and
implant surgery.
| Category | Potential
indications or considerations |
|---|
| Potential
indications | Complex implant
placement requiring prosthetically driven positioning; anatomically
restricted sites; procedures where enhanced visualization,
planning, or instrument guidance may improve workflow; selected
research applications in periodontal microsurgery, soft-tissue
grafting, and regenerative procedures. |
| Patient
selection | Adequate
preoperative imaging; stable reference structures; sufficient mouth
opening and |
| considerations | surgical access;
ability to obtain reliable CBCT-IOS registration; and a treatment
plan suitable for digital guidance. |
| Relative
contraindications | Unstable teeth or
reference markers; extensive movement of soft tissues; inadequate
imaging |
| or limitations | quality; severe
artefacts; inability to achieve reliable registration; restricted
access; uncontrolled bleeding or poor visibility; and insufficient
space for the guide, tracking system, or robotic instruments. |
| Situations
requiring caution | Procedures
involving highly mobile or deformable periodontal tissues,
substantial intraoperative anatomical changes, unpredictable
bleeding, complex regenerative defects, or situations in which
tactile feedback and continuous clinical adaptation are
essential. |
| Operational
contraindications | Inability to
calibrate or verify the system, tracking failure, software or
hardware malfunction, inadequate operator training, lack of a safe
conventional alternative, or failure to maintain appropriate data
security and system integrity. |
Clinical accuracy and results
The main reason for using navigation and robotic
technology in periodontal and implant surgery continues to be
accuracy. Accurate implant positioning is necessary to obtain
optimal aesthetic, functional and biological results. Deviations
from the planned implant position can compromise prosthetic design,
increase biomechanical complications and contribute to peri-implant
disease (2). A number of clinical
studies have assessed the accuracy of dynamic navigation systems
(11,17,64).
Studies have repeatedly demonstrated less angular, coronal and
apical deviation with respect to freehand implant placement.
Dynamic navigation provides a continuous view of the drill position
and trajectory, enabling clinicians to make real-time adjustments
and stay within the surgical plan (4,19,65).
Robotic-assisted implant surgery has demonstrated even higher
levels of accuracy in several recent studies. Systematic reviews
have demonstrated that compared with freehand and static-guided
techniques, robotic systems tend to have lower positional
deviations (20,66). The robotic platform aids in
maintaining the planned trajectory during the preparation for
osteotomy and reduces the impact of inadvertent hand movements
(20,21,23,66,67).
Improved surgical accuracy may lead to beneficial clinical
outcomes. Proper implant positioning may lead to desirable
emergence profiles, improve prosthetic design, facilitate the
maintenance of oral hygiene and reduce the likelihood of injury to
adjacent anatomical structures. Moreover, accurate implant
placement leads to favorable stress distribution and may enhance
the long-term stability of peri-implant tissues (28,51).
Previous studies have reported excellent short-term survival rates
for implants placed with dynamic navigation and robotic guidance
(32,66). Although long-term outcome data
remain limited, the available evidence points to clinical outcomes
that are comparable to or even better than those of conventional
implant placement techniques (23,65).
It is important to realize that numerous factors other than
surgical accuracy determine implant success. Patient-related
factors, systemic health, bone quality, prosthetic design,
maintenance therapy and clinician experience continue to influence
treatment outcomes (2,54,55).
Therefore, navigation and robotic technologies should be considered
tools that support, not replace, sound clinical judgment.
11. Critical appraisal of current
evidence
Although systematic reviews and meta-analyses
generally support the technical feasibility and high positional
accuracy of computer-assisted implant surgery, the strength of the
evidence should be interpreted in light of methodological
heterogeneity. Studies evaluating dynamic navigation and
robotic-assisted implant placement differ in design, implant
location, bone characteristics, surgical protocols, registration
methods, imaging workflows and operator experience. Consequently,
reported deviations cannot always be directly compared across
studies or generalized to all clinical situations (4,19,20,23,66-68).
Comparative evidence suggests that robotic-assisted,
dynamic-navigation and static-guided approaches can achieve
favorable positional accuracy under selected conditions.
Differences in pooled estimates should not automatically be
interpreted as evidence of clinically meaningful superiority. The
relative performance of each technology may depend on the specific
surgical workflow, degree of movement restriction, registration
accuracy and operator familiarity with the system (20,21,65,66).
A further limitation is that an ample amount of the
available literature focuses on technical endpoints, including
coronal, apical and angular deviations, rather than
patient-centered outcomes. Although improved positional accuracy
may facilitate prosthetically driven implant placement and help
avoid anatomical structures, it does not independently improve
long-term implant survival, peri-implant tissue health, prosthetic
complications, postoperative morbidity, patient satisfaction or
cost-effectiveness. These outcomes are influenced by multiple
patient-, implant-, prosthetic- and maintenance-related factors
(2,19-21,23,28,55,66).
Evidence for robotic applications in periodontal
surgery remains substantially less developed than that for
computer-assisted implant placement. Proposed applications in
periodontal regeneration, mucogingival surgery, connective tissue
grafting and tissue-engineered scaffold placement should therefore
be distinguished from established clinical applications. At
present, these areas represent emerging or investigational
possibilities rather than validated alternatives to conventional
periodontal microsurgery.
Overall, the current evidence supports the use of
navigation and robotic technologies as tools that may improve
surgical guidance and positional accuracy in appropriately selected
implant cases. Nevertheless, the clinical significance of these
technical improvements, their cost-effectiveness and their
potential benefits in periodontal surgery require further
prospective clinical investigation with standardized outcome
measures and longer follow-up.
12. AI and augmented/mixed reality in
periodontology
AI, digital planning software, navigation systems
and autonomous robotic control represent distinct technological
levels. Diagnostic AI analyses clinical or imaging data, whereas
planning software supports treatment design and navigation systems
provide real-time procedural guidance. Autonomous control involves
the performance of selected surgical actions with limited direct
human intervention. Evidence supporting diagnostic AI or digital
planning should therefore not be interpreted as evidence for
autonomous periodontal surgery (35,69,70).
AI applications in periodontology exhibit potential
for radiographic bone-loss assessment, periodontal classification,
risk prediction and treatment-planning support. Their performance
depends on training-data quality, annotation standards, disease
characteristics and validation methods. Studies use retrospective
or single-center datasets, and external validation remains limited.
Consequently, performance may vary across populations, disease
severities, scanners, CBCT devices, imaging protocols and clinical
settings (69,71).
Explainability and clinician oversight remain
essential, particularly when AI outputs influence diagnosis or
treatment decisions. Algorithmic bias may also occur when datasets
underrepresent specific demographic groups, geographic populations,
disease presentations, or imaging conditions. AI-generated results
should therefore be interpreted alongside clinical examination and
conventional diagnostic findings, with final responsibility
retained by the treating clinician (71-73).
AI and AR/MR technologies also raise concerns
regarding patient-data privacy, cybersecurity, accountability,
informed consent and compliance with applicable medical-device
regulations. CBCT scans, intraoral scans, photographs and treatment
plans require appropriate security, access control, and transparent
data governance (72-74).
AR/MR systems may display virtual anatomical
structures or treatment plans within the visual field of the
clinician. Their periodontal applications remain limited, with
potential challenges including registration drift, tracking errors,
optical obstruction, a restricted field of view, and mismatch
between virtual overlays and mobile or deformable periodontal
tissues. Thus, the potential of AI and AR/MR should not be equated
with demonstrated improvements in periodontal healing, clinical
attachment gain, regenerative outcomes, patient safety, or
long-term tooth retention. Their current role is best regarded as
adjunctive or investigational, pending robust prospective
validation and evidence of meaningful clinical benefit (75,76).
13. Limitations, challenges and
technology-specific evidence gaps
Technical limitations of
computer-assisted and robotic workflows
The technical limitations affecting
computer-assisted and robotic workflows in periodontal and implant
surgery are summarized in Table V
(2,4,19,77).
The clinical implications of robotics and navigation systems should
be interpreted according to the specific function and maturity of
each technology. Static guides, dynamic navigation, robotic
systems, AI, AR, and haptic interfaces are not interchangeable.
They differ in how they transfer digital information to the
operative field, the type of error they are designed to reduce, and
the degree of dependence on the surgeon. Furthermore, the evidence
base is uneven. The majority of comparative studies evaluate
implant placement accuracy, whereas direct clinical evidence for
robotic periodontal flap surgery, root-surface instrumentation,
periodontal regeneration, connective tissue grafting, and
microsuturing remains limited. Consequently, improvements in
geometric accuracy should not automatically be interpreted as
evidence of improved periodontal healing, tooth retention, or
patient-reported outcomes (2,4,19,77).
| Table VTechnical limitations affecting
computer-assisted and robotic workflows in periodontal and implant
surgery. |
Table V
Technical limitations affecting
computer-assisted and robotic workflows in periodontal and implant
surgery.
| Technical
domain | Specific
limitations and clinical implications |
|---|
| Registration and
calibration | Accurate
registration depends on stable fiducial or reference markers and
reliable identification of anatomical landmarks. Marker movement or
instability can generate registration errors and compromise the
relationship between the virtual plan and the patient. Inaccurate
calibration of the handpiece, drill, robotic arm, or instrument tip
may introduce deviations into the planned surgical trajectory. |
| Patient movement
and tracking | Patient movement or
displacement of the reference array may invalidate registration.
Dynamic navigation may also be affected by tracking interruption,
optical obstruction from the surgeon's hands, instruments,
retractors, blood, or saliva, and loss of the camera's line of
sight. These problems may require repeated registration and
increase procedural time. |
| Imaging and
data-fusion errors | CBCT resolution,
voxel size, patient movement, metallic artifacts, scatter, and
reconstruction parameters may influence anatomical identification
and planning accuracy. Additional errors may occur during
CBCT-intraoral scanner (IOS) registration because of incomplete
scans, stitching inaccuracies, reflective surfaces, saliva, mobile
teeth, or inadequate stable reference structures. |
| Soft-tissue
mismatch | Digital datasets
may not accurately represent soft-tissue position during surgery.
Differences between the scanned anatomy and the tissues after
retraction, flap elevation, inflammation, edema, or manipulation
may reduce the reliability of digitally transferred plans. |
| Intraoperative
anatomical changes | Virtual planning
represents anatomy at the time of imaging and may not fully reflect
intraoperative soft-tissue position. This is particularly relevant
in periodontal surgery, where bleeding, tissue tension, flap
elevation, and retraction can alter the surgical field and limit
direct extrapolation from implant-related navigation data. |
| Clinical access and
visibility | Posterior regions,
limited mouth opening, restricted interarch space, and interference
from the cheeks or tongue may limit access for cameras, robotic
arms, reference arrays, guides, and handpieces. Saliva, blood,
irrigation, retractors, and soft-tissue displacement may further
compromise visibility, tracking, or instrument access. |
| Training and
learning curve | Effective use
requires competency in digital planning, registration, calibration,
navigation or robotic interfaces, error recognition, and
contingency management. Operator experience may influence workflow
efficiency and accuracy, particularly during early adoption.
Training should include supervised use and the ability to revert
safely to conventional surgery when technical problems occur. |
| Cost and
maintenance | Implementation
involves acquisition of the platform, imaging and scanning
equipment, software licenses, calibration devices, consumables,
service contracts, upgrades, and staff training. Periodic
maintenance and calibration are necessary to preserve system
reliability, while evidence regarding long-term cost-effectiveness
remains limited. |
| Data governance and
cybersecurity | Integration of CBCT
data, IOS files, treatment plans, cloud-based platforms, and
robotic systems introduces risks related to unauthorized access,
insecure data transfer, software vulnerabilities, and alteration of
digital treatment files. Secure authentication, encryption, access
control, audit trails, validated software updates, and clinician
verification of automated outputs are therefore necessary. |
Static computer-assisted surgery
Static computer-assisted surgery uses a digitally
designed surgical template to transfer a virtually planned implant
position to the operative field. Its principal function is to
constrain the drilling trajectory and, in fully guided workflows,
control the angulation and depth of osteotomy preparation. This can
reduce the dependence on freehand spatial estimation and improve
the reproducibility of implant positioning (2,4).
The accuracy of static guidance depends on the
quality of CBCT imaging, segmentation, prosthetic planning,
template fabrication, guide support, sleeve-drill tolerance and
intraoperative seating. Errors may be introduced during image
acquisition, virtual planning, manufacturing, or placement of the
guide. Tooth-supported guides may provide relatively stable
support, whereas mucosa-supported guides are susceptible to tissue
compressibility and movement. Bone-supported guides may require
additional surgical exposure and may be inconsistent with minimally
invasive treatment objectives (2,4,21).
Static guides also have limited intraoperative
adaptability. Once fabricated, they cannot readily accommodate
unexpected anatomical findings, changes in prosthetic requirements,
inadequate bone quality, or a need to modify the planned
trajectory. The guide may reduce visibility, interfere with
irrigation, and complicate treatment in posterior regions or
patients with restricted mouth opening. Importantly, a guide can
accurately reproduce an inappropriate plan; it does not
independently assess biological suitability, prosthetic emergence,
bone quality, or the risk of anatomical injury (2,4).
The majority of studies on static guidance report
implant deviation rather than long-term peri-implant tissue
stability, implant survival, postoperative morbidity, or
patient-centered outcomes. Therefore, static guidance should be
understood as a tool for improving the execution of a preoperative
plan rather than as an independent determinant of treatment
success.
Dynamic navigation
Dynamic navigation provides real-time visual
feedback regarding the position of the surgical instrument relative
to the planned trajectory. Unlike static guides, it allows
clinicians to modify the osteotomy path during surgery and may be
useful when intraoperative adaptation is needed. Its performance
depends on accurate patient registration, calibration, handpiece
tracking, maintenance of the tracking field, and effective
integration of the navigation display into the surgical workflow
(4,19,65,77).
The principal limitation of dynamic navigation is
that it remains operator-dependent. Registration errors, movement
of tracking markers, calibration inaccuracies, instrument
replacement, optical obstruction, tracking loss and display latency
may reduce accuracy. Surgeons must also divide attention between
the operative field and the navigation screen, potentially
increasing the cognitive workload. Consequently, dynamic navigation
does not eliminate human error but transfers some sources of error
from freehand spatial estimation to registration, tracking,
calibration, visual interpretation and human-computer interaction
(4,19,65,77).
Evidence from implant surgery suggests that
compared with freehand placement, dynamic navigation can improve
positional accuracy. Nevertheless, performance is influenced by
operator experience, the learning curve, anatomical access and the
complexity of the surgical site (11,78,79).
In periodontal surgery, these limitations may be amplified as the
target structures are not always rigid or stable. Flap reflection,
retraction, bleeding, tissue displacement and changes in the
operative field can compromise the reliability of registration on
the basis of preoperative anatomy. Therefore, the accuracy
demonstrated in rigid implant osteotomy models should not be
directly extrapolated to periodontal soft-tissue procedures
(51,54).
Robotic-assisted surgery
Robotic-assisted systems combine digital planning
with mechanical guidance, tracking, motion control, and, in some
platforms, haptic or movement-constraining functions. Depending on
the system, the robot may guide the instrument along a planned
trajectory, restrict movement beyond predefined boundaries, reduce
tremor, or support shared control between the surgeon and the
robotic arm (35,80).
The strongest current evidence concerns
robotic-assisted implant placement. Recent systematic reviews and
meta-analyses have reported more favorable coronal, apical and
angular accuracy with respect to freehand surgery and, in selected
analyses, compared with dynamic navigation or static guidance
(2,4,19,77).
These findings require cautious interpretation. The available
literature includes a substantial proportion of in vitro
studies, small clinical cohorts and nonrandomized comparisons. A
recent systematic review comparing robotic, static and dynamic
implant surgery identified only a limited number of clinical
studies and reported a high risk of bias in several included
investigations (77). Another
review concluded that although robotic systems may demonstrate
improved accuracy, the clinical significance of relatively small
geometric differences remains uncertain (19).
Robotic precision is also dependent on the accuracy
of the CBCT data, segmentation, virtual planning, patient
registration, robotic-arm calibration, mechanical stability,
tracking and software performance. A robot can reproduce a planned
trajectory consistently, but cannot correct an inaccurate image,
faulty segmentation, incorrect registration, or an inappropriate
treatment plan. Thus, robotics may reduce execution error while
leaving diagnostic and planning errors unresolved (35,77,80).
Practical limitations include high acquisition and
maintenance costs, proprietary hardware and software, dedicated
training requirements, technical support needs, additional setup
time, and uncertain cost-effectiveness. The economic justification
for robotic systems remains unclear as only a limited number of
studies have examined whether improved accuracy translates to
shorter procedures, fewer complications, better long-term outcomes,
or improved patient satisfaction (2,4,19,35,77).
Specific challenges in periodontal
surgery
The translation of robotics from implant placement
to periodontal surgery is more complex. Implant osteotomy
preparation generally involves a defined trajectory within
relatively rigid tissues. By contrast, periodontal surgery involves
deformable soft tissues, inflammatory changes, bleeding, irregular
root morphology, variable flap positions, and biologically active
wound surfaces (35,51,54).
Robotic assistance has been proposed conceptually
for minimally invasive flap access, intrabony defect debridement,
membrane or scaffold positioning, connective tissue graft placement
and microsuturing. These applications require more than geometric
control. The system would need to recognize soft-tissue boundaries,
accommodate tissue deformation, preserve vascularity, respond to
tissue tension, and support wound stability. These requirements are
not adequately addressed by conventional image-based navigation or
trajectory control (35,51,55).
Furthermore, periodontal regeneration depends on
biological factors, such as defect morphology, blood supply, wound
stability, space maintenance, inflammatory regulation and cellular
responses. These outcomes cannot be predicted from the accuracy of
robotic positioning alone (19,71).
Robotic periodontal applications should therefore currently be
regarded as investigational or translational research opportunities
rather than established clinical indications.
AI and automated image
interpretation
AI can assist with the segmentation of teeth,
roots, alveolar bone, periodontal defects, anatomical landmarks and
implant-related structures. It may also support treatment planning,
image registration, risk assessment and the identification of
anatomical constraints. Its primary role is therefore information
processing and decision support rather than direct surgical
execution (5,69,71).
AI performance depends heavily on the quality and
representativeness of the training data. Algorithms may perform
differently across CBCT devices, voxel sizes, image artifacts,
patient populations, dentition patterns and degrees of periodontal
destruction. Metallic restorations, missing teeth, severe bone loss
and distorted anatomy may reduce segmentation reliability. High
performance in a curated dataset may not translate to equivalent
performance in routine clinical practice (5,69,71).
AI systems may also reproduce biases in their
training data and generate apparently confident but clinically
incorrect outputs. External validation, calibration, transparent
reporting, and assessment of failure cases are therefore essential.
In periodontology, automated identification of bone loss does not
necessarily establish disease activity, prognosis, or appropriate
regenerative treatment. Similarly, an algorithmic treatment
recommendation cannot replace periodontal examination, clinical
attachment measurements, patient preferences, or professional
judgment (5,69,71,72).
The principal evidence gap is whether AI-supported
planning improves clinically meaningful outcomes rather than merely
reducing planning time or increasing segmentation accuracy. Future
studies should report external validation, subgroup performance,
calibration, clinically relevant errors and the effect of AI
assistance on treatment decisions (5,69,71,72).
AR and mixed-reality systems
AR and mixed-reality systems overlay digital
information onto the visual field of the patient or clinician.
Their intended functions include improving spatial orientation,
displaying anatomical structures, and reducing the need to shift
attention between the operative field and an external monitor
(81,82).
Their limitations include registration error,
display latency, optical distortion, a restricted field of view,
occlusion, head movement and instability of the virtual overlay.
Even small alignment errors may be clinically important when
working near vital anatomical structures. Visual distraction and
information overload may also impair rather than improve
workflow.
The current value of AR in dentistry is more
strongly supported for education, visualization, and procedural
orientation than for improved periodontal outcomes. In periodontal
surgery, tissue displacement during flap reflection or retraction
may cause the virtual overlay to become misaligned with the actual
anatomy. Accordingly, AR should currently be viewed primarily as an
adjunct to planning and orientation rather than as an independent
guarantee of surgical precision (81,82).
Haptic and force-feedback
technologies
Haptic systems aim to provide tactile information
or constrain instrument movement according to predefined anatomical
or procedural boundaries. This is potentially relevant to dentistry
as tactile feedback contributes to the recognition of root
contours, tissue resistance, bone density, and instrumentation
endpoints (60,61).
Reproducing biological tactile sensation is
technically challenging. Periodontal tissues vary in compliance,
inflammation, fibrosis and anatomical structure. A force-feedback
system calibrated using simplified models may not accurately
reproduce clinical tissue behavior. Appropriate force thresholds
may also differ across patients, anatomical sites, instruments, and
procedural stages (60,61).
Haptic guidance may assist with motion control or
boundary awareness; however, it should not be assumed to reliably
identify calculus, distinguish healthy from diseased root surfaces,
or determine when debridement is biologically adequate. Robotic
root-surface instrumentation remains an early-stage research
concept requiring validation in clinically representative models
before clinical adoption can be considered (46,53).
Robotics in periodontal regeneration
and microsurgery
Periodontal regenerative procedures differ
fundamentally from implant placement because their outcomes depend
on wound stability, defect morphology, vascularity, biomaterial
properties, soft-tissue management and biological healing.
Minimally invasive and microsurgical approaches may improve access
and tissue handling; however, these benefits should not be
automatically attributed to robotics (51,55,83).
A robotic system could theoretically assist with
access to intrabony defects, membrane placement, graft
stabilization, or microsuturing. Nevertheless, a system that
positions a membrane accurately may not be able to maintain
adaptation, avoid dead space, preserve vascularity, or respond to
unexpected flap tension. Similarly, robotic suturing may improve
needle trajectory consistency but cannot independently determine
the appropriate suture tension, tissue choice, or biological
suitability of wound closure.
Systematic reviews of periodontal microsurgery and
regenerative treatment have demonstrated that clinical outcomes are
influenced by case selection, defect characteristics, operator
expertise, surgical technique, and biological healing. They also
reveal variation in study designs, outcome measures, and certainty
of evidence. Roboticshould therefore be evaluated as an enabling
adjunct rather than as a replacement for periodontal surgical
judgment or biological principles (51,55,83,84).
Cross-cutting methodological and
translational limitations
The available evidence is limited by heterogeneity
in study design, imaging protocols, registration methods, accuracy
definitions, surgical workflows and outcome assessment. Studies
have variously reported coronal, apical, angular, depth, or
three-dimensional deviations, rendering direct comparison difficult
(2,4,77).
The literature also includes in vitro models, small clinical
cohorts, retrospective studies and non-randomized comparisons,
which may not reproduce patient movement, bleeding, soft-tissue
deformation, or intraoperative decision-making (19,67,77).
The risk of bias, inconsistent reporting of
operator experience, learning-curve effects, and limited
independent validation further restrict the certainty of the
conclusions (19,77,77).
Moreover, the majority of studies focus on technical accuracy,
rather than clinically meaningful outcomes such as post-operative
morbidity, peri-implant tissue stability, periodontal attachment
gain, tooth retention, long-term implant survival, or
patient-reported outcomes (2,4,19,67,77).
A more accurate trajectory does not necessarily translate into
superior biological or patient-centered outcomes.
External validity is particularly problematic when
implant-related findings are extrapolated to periodontal surgery.
Periodontal procedures involve deformable and inflamed tissues,
bleeding, variable flap positioning, irregular root surfaces and
biologically dynamic wound healing. Therefore, implant accuracy
data cannot be directly applied to robotic periodontal flap
surgery, root-surface instrumentation, connective tissue grafting,
or periodontal regeneration.
Additional barriers include high acquisition and
maintenance costs, proprietary systems, technical support
requirements, training needs, workflow integration and uncertain
cost-effectiveness. Future research should use standardized
accuracy definitions, prospective multicenter designs, independent
outcome assessments, transparent reporting of operator experience,
and longer follow-up. Studies should prioritize periodontal- and
implant-specific clinical outcomes rather than technical precision
alone (2,4,19,67,77).
Overall critical interpretation
The current evidence supports a graded
interpretation of these technologies. Static guides and dynamic
navigation have established roles in selected implant workflows,
although their performance depends on planning quality, guide
stability, registration, tracking, and operator factors. Robotic
systems demonstrate promising technical precision; however,
clinical evidence remains less mature and does not yet establish
universal superiority or cost-effectiveness. AI, augmented reality,
haptic technologies, and robotic periodontal applications remain
primarily adjunctive, developmental, or investigational (2,4,19,77).
The central limitation is the gap between technical
feasibility and demonstrated biological or patient-centered
benefit. Successful translation into periodontology will require
systems capable of accounting for deformable tissues, inflammatory
status, tactile feedback, wound biology and the dynamic nature of
periodontal healing. Until such evidence becomes available,
robotics and navigation should be presented as technologies that
may enhance selected components of clinical care rather than as
replacements for diagnosis, surgical judgment, or established
biological treatment principles (14,21,35,36,51,54,59,77,85,86).
14. Conclusion and future directions
The future of robotics and navigation systems in
periodontics and implant dentistry will be closely tied to the
continued evolution of AI, machine learning, digital imaging and
robotic engineering. These technologies are expected to further
improve the precision, efficiency and predictability of surgical
treatment (80,82). AI is likely to play an increasingly
critical role in diagnosis and treatment planning. In the future,
radiographic data may be automatically analyzed to determine bone
quality, identify anatomic landmarks, and generate optimized
implant treatment plans with minimal operator intervention
(80,85). Machine-learning algorithms may also
assist in risk assessment by predicting implant success, the
susceptibility to peri-implant disease and patient-specific
treatment outcomes. Such capabilities may enable truly personalized
implant therapy (85,86). AR technologies are expected to
evolve rapidly and may eventually allow clinicians to visualize
surgical plans directly through smart glasses or in head-mounted
displays. This capability could eliminate the need for external
monitoring and enhance ergonomics during navigation-guided surgery.
Future robotic systems might evolve from semi-active assistance to
higher levels of autonomy. While complete autonomy in implant
surgery remains a long-term goal, the ongoing advances in sensor
technology, AI and robot control systems are steadily pushing the
boundaries of surgical robotics toward more complex capabilities.
Digital workflows will also continue to grow in periodontology.
Intraoral scanners, CBCT imaging, AI, navigation systems, and
robotic technologies may be combined to create seamless digital
treatment pathways that improve efficiency and clinical outcomes.
As the cost of technology decreases and clinical evidence continues
to accrue, robotics and navigation systems will likely become more
affordable and used more widely. Their implementation in
periodontal and implant practices may eventually result in more
accurate, minimally invasive and patient-centered treatment
strategies (21,31,35).
In conclusion, the use of robotics and navigation
systems represents a major step forward in modern periodontal and
implant surgery. These systems have improved surgical precision,
and procedural predictability and have decreased operator-dependent
variability by combining digital imaging, virtual treatment
planning, real-time tracking technologies and robotic assistance.
Dynamic navigation systems have become reliable clinical tools that
provide both high accuracy and intraoperative flexibility, whereas
the use of robot-assisted implant surgery is the latest evolution
in computer assisted dental procedures. Current evidence suggests
that these technologies may improve implant placement accuracy and
favor minimally invasive treatment approaches. The implementation
of such technologies in routine practice is still restricted
because of limitations such as costs, technical complexity,
training needs and the absence of long-term clinical evidence. The
future of periodontal and implant surgery is expected to be
influenced by the growing incorporation of AI, machine learning, AR
and advanced robotic technologies. These innovations may enhance
treatment planning, optimize surgical execution, and improve
patient outcomes. As technology evolves and more clinical data
accumulates, robotics and navigation systems will play an
increasingly important role in delivering accurate, personalized
and minimally invasive periodontal and implant therapy.
Acknowledgements
Not applicable.
Funding
Funding: No funding was received.
Availability of data and materials
Not applicable.
Authors' contributions
DK was involved in the conceptualization of the
study, and in the study methodology, literature search,
investigation, the writing of the original draft of the manuscript,
in the writing, reviewing and editing of the manuscript, as well as
in visualization and project administration. MS was involved in the
literature search, investigation, critical revision of the
manuscript, in the writing, reviewing and editing of the manuscript
and in the validation of findings obtained from the literature. SUN
was involved in the study supervision, in the conceptualization of
the study, in the critical appraisal of the scientific content, and
in the writing, reviewing and editing of the manuscript. All the
authors have read and approved the final version of the manuscript
and agree to be accountable for all the aspects of the work. Data
authentication is not applicable.
Ethics approval and consent to
participate
Not applicable.
Patient consent for publication
Not applicable.
Competing interests
The authors declare that they have no competing
interests.
Use of artificial intelligence tools
During the preparation of this work, the authors
utilized OpenAI's ChatGPT and Microsoft Copilot and Notebook LM to
generate summaries of research articles. Tables and figures related
to the topic were then created. These summaries were evaluated by
comparison to manually written summaries by experts in the field.
Rubriq was also utilized for language editing. Subsequently, the
authors revised and edited the content produced by the AI tools as
necessary, taking full responsibility for the ultimate content of
the present manuscript.
References
|
1
|
Greenstein G, Cavessa V and Cavallaro J:
Dental implantology: Current concepts and controversies. Compend
Contin Educ Dent. 29:520–528. 2008.
|
|
2
|
Tahmaseb A, Wu V, Wismeijer D, Coucke W
and Evans C: The accuracy of static computer-aided implant surgery:
A systematic review and meta-analysis. Clin Oral Implants Res. 29
(Suppl 16):S416–S435. 2018.PubMed/NCBI View Article : Google Scholar
|
|
3
|
Joda T and Gallucci GO: The virtual
patient in dental medicine. Clin Oral Implants Res. 26:725–726.
2015.PubMed/NCBI View Article : Google Scholar
|
|
4
|
Jorba-García A, Figueiredo R,
González-Barnadas A, Camps-Font O and Valmaseda-Castellón E:
Accuracy of dynamic computer-aided implant placement: A systematic
review and meta-analysis. Clin Oral Investig. 25:2479–2494.
2021.PubMed/NCBI View Article : Google Scholar
|
|
5
|
Schwendicke F, Samek W and Krois J:
Artificial intelligence in dentistry: Chances and challenges. J
Dent Res. 99:769–774. 2020.PubMed/NCBI View Article : Google Scholar
|
|
6
|
Baethge C, Goldbeck-Wood S and Mertens S:
SANRA-a scale for the quality assessment of narrative review
articles. Res Integr Peer Rev. 4(5)2019.PubMed/NCBI View Article : Google Scholar
|
|
7
|
Buser D, Martin W and Belser UC:
Optimizing esthetics for implant restorations in the anterior
maxilla: Anatomic and surgical considerations. Int J Oral
Maxillofac Implants. 19 (Suppl):S43–S61. 2004.PubMed/NCBI
|
|
8
|
Widmann G and Bale RJ: Accuracy in
computer-aided implant surgery-a review. Int J Oral Maxillofac
Implants. 21:305–313. 2006.PubMed/NCBI
|
|
9
|
Tyndall DA, Price JB, Tetradis S, Ganz SD,
Hildebolt C and Scarfe WC: Position statement of the American
Academy of Oral and Maxillofacial Radiology on selection criteria
for the use of radiology in dental implantology with emphasis on
cone beam computed tomography. Oral Surg Oral Med Oral Pathol Oral
Radiol. 113:817–826. 2012.PubMed/NCBI View Article : Google Scholar
|
|
10
|
Tyndall DA and Brooks SL: Selection
criteria for dental implant site imaging: A position paper of the
American Academy of Oral and Maxillofacial Radiology. Oral Surg
Oral Med Oral Pathol Oral Radiol Endod. 89:630–637. 2000.PubMed/NCBI View Article : Google Scholar
|
|
11
|
Block MS and Emery RW: Static or dynamic
navigation for implant placement-choosing the method of guidance. J
Oral Maxillofac Surg. 74:269–277. 2016.PubMed/NCBI View Article : Google Scholar
|
|
12
|
Emery RW, Merritt SA, Lank K and Gibbs JD:
Accuracy of dynamic navigation using implant-mounted fiducial
markers. J Oral Implantol. 42:46–50. 2016.
|
|
13
|
Stefanelli LV, DeGroot BS, Lipton DI and
Mandelaris GA: Accuracy of a dynamic dental implant navigation
system in a private practice. Int J Oral Maxillofac Implants.
34:205–213. 2019.PubMed/NCBI View Article : Google Scholar
|
|
14
|
Gargallo-Albiol J, Barootchi S,
Salomó-Coll O and Wang HL: Advantages and disadvantages of implant
navigation surgery: A systematic review. Ann Anat. 225:1–10.
2019.PubMed/NCBI View Article : Google Scholar
|
|
15
|
Jorba-García A, González-Barnadas A,
Camps-Font O, Figueiredo R and Valmaseda-Castellón E: Accuracy
assessment of dynamic computer-aided implant placement: A
systematic review and meta-analysis. Clin Oral Investig.
25:2479–2494. 2021.PubMed/NCBI View Article : Google Scholar
|
|
16
|
Wei SM, Zhu Y, Wei JX, Zhang CN, Shi JY
and Lai HC: Accuracy of dynamic navigation in implant surgery: A
systematic review and meta-analysis. Clin Oral Implants Res.
32:383–393. 2021.PubMed/NCBI View Article : Google Scholar
|
|
17
|
Aydemir CA and Arısan V: Accuracy of
dental implant placement via dynamic navigation or the freehand
method: A split-mouth randomized controlled clinical trial. Clin
Oral Implants Res. 31:255–263. 2020.PubMed/NCBI View Article : Google Scholar
|
|
18
|
Vercruyssen M, Hultin M, Van Assche N,
Svensson B, Naert I and Quirynen M: Guided surgery: Accuracy and
efficacy. Periodontol 2000. 66:228–246. 2014.PubMed/NCBI View Article : Google Scholar
|
|
19
|
Khan M, Javed F, Haji Z and Ghafoor R:
Comparison of the positional accuracy of robotic guided dental
implant placement with static guided and dynamic navigation
systems: A systematic review and meta-analysis. J Prosthet Dent.
132:746.e1–746.e8. 2024.PubMed/NCBI View Article : Google Scholar
|
|
20
|
Sankar H, Shalini M, Rajagopalan A, Gupta
S, Kumar A and Shouket R: Dental implant placement accuracy with
robotic surgery compared to free-hand, static and dynamic computer
assisted techniques: Systematic review and meta-analysis. J Oral
Biol Craniofac Res. 15:69–76. 2025.PubMed/NCBI View Article : Google Scholar
|
|
21
|
Khaohoen A, Powcharoen W, Sornsuwan T,
Chaijareenont P, Rungsiyakull C and Rungsiyakull P: Accuracy of
implant placement with computer-aided static, dynamic, and
robot-assisted surgery: A systematic review and meta-analysis of
clinical trials. BMC Oral Health. 24(359)2024.PubMed/NCBI View Article : Google Scholar
|
|
22
|
Wang XY, Liu L, Guan MS, Liu Q, Zhao T and
Li HB: The accuracy and learning curve of active and passive
dynamic navigation-guided dental implant surgery: An in vitro
study. J Dent. 124(104240)2022.PubMed/NCBI View Article : Google Scholar
|
|
23
|
Matvijenko K and Borusevičius R:
Comparison of dynamic navigation systems in dental implantology: A
systematic literature review of in vitro studies. Int J Oral
Maxillofac Surg. 54:647–656. 2025.PubMed/NCBI View Article : Google Scholar
|
|
24
|
D'haese J, Van De Velde T, Komiyama A,
Hultin M and De Bruyn H: Accuracy and complications using
computer-designed stereolithographic surgical guides for oral
rehabilitation by means of dental implants: A review of the
literature. Clin Implant Dent Relat Res. 14:321–335.
2012.PubMed/NCBI View Article : Google Scholar
|
|
25
|
Sun TM, Lee HE, Lan TH, Pan CY and Lee SY:
The influence of dental implant surgical guide support and implant
placement methods on the accuracy of implant placement: A
systematic review and meta-analysis. J Prosthet Dent.
122:601–611.e1. 2019.
|
|
26
|
Xu Z, Zhou L, Zheng M, Lin Y, Huang W,
Chen J, Li Y and Wu D: The effect of implant surgery experience on
the learning curve of a dynamic navigation system: An in vitro
study. BMC Oral Health. 23(89)2023.PubMed/NCBI View Article : Google Scholar
|
|
27
|
Goyal L, Saroya KK, Sankar H, Dewan M,
Chawla K and Pruthi G: Influence of clinician's experience on the
accuracy of dental implant placement by dynamic computer-assisted
surgery systems: A systematic review and meta-analysis. Clin Oral
Implants Res. 36:1361–1381. 2025.PubMed/NCBI View Article : Google Scholar
|
|
28
|
Wang J, Gao M, Zhao Y, Shi B, Wu X, Zhang
Y and Yan Q: Comparison of dental implant placement accuracy
between robotic and static or dynamic computer-assisted surgeries:
A systematic review and meta-analysis. Med Oral Patol Oral Cir
Bucal. 31:e1–e10. 2026.PubMed/NCBI View Article : Google Scholar
|
|
29
|
Nava S, Sabri H, Hazrati P, Nava C, Saleh
MHA and Wang HL: Accuracy of static, dynamic, and robotic guided
surgery in immediate implant placement: A systematic review and
network meta-analysis. Clin Oral Implants Res. 37:525–542.
2026.PubMed/NCBI View Article : Google Scholar
|
|
30
|
Zhang S, Cai Q, Chen W, Lin Y, Gao Y, Wu D
and Chen J: Accuracy of implant placement via dynamic navigation
and autonomous robotic computer-assisted implant surgery methods: A
retrospective study. Clin Oral Implants Res. 35:220–229.
2024.PubMed/NCBI View Article : Google Scholar
|
|
31
|
Huang S, Wang Z, Li M, Song Y and Li Y:
Current Status and Future Perspectives of Robot-Assisted Dental
Implant Surgery. Int Dent J. 75:1608–1620. 2025.PubMed/NCBI View Article : Google Scholar
|
|
32
|
Chen J, Wang Y, Bai Y, Chen Y, Chen Z, Yan
Q and Zhang Y: Accuracy, safety, and efficiency in robotic-assisted
vs. freehand dental implant surgery: A 6-month follow-up randomized
controlled trial. Clin Oral Implants Res. 36:662–670.
2025.PubMed/NCBI View Article : Google Scholar
|
|
33
|
Yang F, Chen J, Cao R, Tang Q, Liu H,
Zheng Y, Liu B, Huang M, Wang Z, Ding Y and Wang L: Comparative
analysis of dental implant placement accuracy: Semi-active robotic
versus free-hand techniques: A randomized controlled clinical
trial. Clin Implant Dent Relat Res. 26:1149–1161. 2024.PubMed/NCBI View Article : Google Scholar
|
|
34
|
Jia J, Yu Y, Cao X, Fu D, Lv C and Li Y:
Accuracy of robotic computer-assisted implant surgery in clinical
dental implant placement: A systematic review and meta-analysis. J
Dent. 166(106321)2026.PubMed/NCBI View Article : Google Scholar
|
|
35
|
Yang GZ, Cambias J, Cleary K, Daimon T,
Drake J, Dupont PE, Hata N, Kazanzides P, Martel S, Patel RV, et
al: Medical robotics-regulatory, ethical, and legal considerations
for increasing levels of autonomy. Sci Robot.
2(eaam8638)2017.PubMed/NCBI View Article : Google Scholar
|
|
36
|
Alqutaibi AY, Hamadallah HH, Abu Zaid B,
Aloufi AM and Tarawah RA: Applications of robots in implant
dentistry: A scoping review. J Prosthet Dent. 134:1052–1061.
2025.PubMed/NCBI View Article : Google Scholar
|
|
37
|
Tuygunov N, Mattheos N, Tsoi J, Ruzikulova
M, Osathanon T and Samaranayake L: Contemporary applications of
robotic systems in dental implantology: A review. Int Dent J.
76(109335)2026.PubMed/NCBI View Article : Google Scholar
|
|
38
|
Avila-Ortiz G, Ambruster J, Barootchi S,
Chambrone L, Chen CY, Dixon DR, Geisinger ML, Giannobile WV, Goss
K, Gunsolley JC, et al: American Academy of Periodontology best
evidence consensus statement on the use of biologics in clinical
practice. J Periodontol. 93:1763–1770. 2022.PubMed/NCBI View Article : Google Scholar
|
|
39
|
Tonetti MS, Greenwell H and Kornman KS:
Staging and grading of periodontitis: Framework and proposal of a
new classification and case definition. J Periodontol. 89 (Suppl
1):S159–S172. 2018.PubMed/NCBI View Article : Google Scholar
|
|
40
|
Tavelli L, Barootchi S, Nguyen TVN, Tattan
M, Ravidà A and Wang HL: Efficacy of tunnel technique in the
treatment of localized and multiple gingival recessions: A
systematic review and meta-analysis. J Periodontol. 89:1075–1090.
2018.PubMed/NCBI View Article : Google Scholar
|
|
41
|
Avila-Ortiz G, Elangovan S, Kramer KWO,
Blanchette D and Dawson DV: Effect of implant placement accuracy on
clinical outcomes and complications. Clin Oral Implants Res. 32
(Suppl 21):S61–S78. 2021.
|
|
42
|
Buser D, Sennerby L and De Bruyn H: Modern
implant dentistry based on osseointegration: 50 years of progress,
current trends and open questions. Periodontol 2000. 73:7–21.
2017.PubMed/NCBI View Article : Google Scholar
|
|
43
|
Sharma S, Tan E, Tran B, Siow HY, Tafesse
E, Thong YHJ, Tan RJM, Son J, Todaro L, Teo J and Abduo J: Effect
of pilot-guided implant placement concept on the accuracy of
osteotomy preparation and implant placement. J Oral Sci. 66:20–25.
2024.PubMed/NCBI View Article : Google Scholar
|
|
44
|
Takács A, Marada G, Turzó K, Nagy Á,
Németh O, Mijiritsky E, Kivovics M and Mühl A: Does implant drill
design influence the accuracy of dental implant placement using
static computer-assisted implant surgery? An in vitro study. BMC
Oral Health. 23(575)2023.PubMed/NCBI View Article : Google Scholar
|
|
45
|
Aslan S and Rasperini G: Fundamental
concepts and new perspectives for periodontal regeneration. Curr
Oral Health Rep. 12(15)2025.PubMed/NCBI View Article : Google Scholar
|
|
46
|
Sculean A, Nikolidakis D and Schwarz F:
Regeneration of periodontal tissues: combinations of barrier
membranes and grafting materials-biological foundation and
preclinical evidence: A systematic review. J Clin Periodontol. 35
(8 Suppl):S106–S116. 2008.PubMed/NCBI View Article : Google Scholar
|
|
47
|
Rojas MA, Marini L, Pilloni A and Sahrmann
P: Early wound healing outcomes after regenerative periodontal
surgery with enamel matrix derivatives or guided tissue
regeneration: A systematic review. BMC Oral Health.
19(76)2019.PubMed/NCBI View Article : Google Scholar
|
|
48
|
Alghamdi A, Alqahtani G, Dashti A,
Aljameel N, Almadluh A, Agili A, Baqazi F, Kutbi A, Muhyedin N,
Alsaeed F, et al: Robot-Assisted dentistry: What the evidence
supports and which outcomes are still missing. Cureus.
18(e108601)2026.PubMed/NCBI View Article : Google Scholar
|
|
49
|
Marcus HJ, Ramirez PT, Khan DZ, Layard
Horsfall H, Hanrahan JG, Williams SC, Beard DJ, Bhat R, Catchpole
K, Cook A, et al: The IDEAL framework for surgical robotics:
Development, comparative evaluation and long-term monitoring. Nat
Med. 30(1213)2024.PubMed/NCBI View Article : Google Scholar
|
|
50
|
Cortellini P and Tonetti MS: Clinical
concepts for regenerative therapy in intrabony defects: The
periodontal regeneration S3-level clinical practice guideline. J
Clin Periodontol. 42 (Suppl 16):S61–S76. 2015.PubMed/NCBI View Article : Google Scholar
|
|
51
|
Cortellini P and Tonetti MS: Clinical
concepts for regenerative therapy in intrabony defects. Periodontol
2000. 68:282–307. 2015.PubMed/NCBI View Article : Google Scholar
|
|
52
|
Kao RT, Nares S and Fong NW: Periodontal
regeneration-intrabony defects: A systematic review and
meta-analysis. J Evid Based Dent Pract. 15:50–61. 2015.PubMed/NCBI View Article : Google Scholar
|
|
53
|
Kao RT, Nares S and Reynolds MA:
Periodontal regeneration-intrabony defects: A systematic review
from the AAP Regeneration Workshop. J Periodontol. 86 (2
Suppl):S77–S104. 2015.
|
|
54
|
Zuhr O, Bäumer D and Hürzeler M: The
addition of soft-tissue replacement grafts in plastic periodontal
and implant surgery: Critical elements in design and execution. J
Clin Periodontol. 41 (Suppl 15):S123–S142. 2014.PubMed/NCBI View Article : Google Scholar
|
|
55
|
Chambrone L and Tatakis DN: Periodontal
soft tissue root coverage procedures: A systematic review from the
AAP Regeneration Workshop. J Periodontol. 86 (2 Suppl):S8–S51.
2015.PubMed/NCBI View Article : Google Scholar
|
|
56
|
Goyal L and Chawla K: Efficacy of
microsurgery in treatment of localized or multiple gingival
recession: A systematic review. J Oral Biol Craniofac Res.
11:237–244. 2021.PubMed/NCBI View Article : Google Scholar
|
|
57
|
Sabri H, Alhachache S, Saxena P, Dubey P,
Nava P, Rufai SH and Sarkarat F: Microsurgery in periodontics and
oral implantology: A systematic review of current clinical
applications and outcomes. Evid Based Dent. 25:211–212.
2024.PubMed/NCBI View Article : Google Scholar
|
|
58
|
Pasqualini E, Castro F, Curado D,
Martelete A, Heboyan A, Saleh MH, Fernandes JCH and Fernandes GVO:
Minimally invasive periodontal regeneration with the buccal
approach: A systematic review and meta-analysis of clinical
studies. Evid Based Dent. 25(54)2024.PubMed/NCBI View Article : Google Scholar
|
|
59
|
Zuhr O and Hürzeler MB: Plastic-Esthetic
Periodontal and Implant Surgery: A Microsurgical Approach. 1st ed.
London: Quintessence Publishing, 2012. ISBN: 9781850972266.
|
|
60
|
Burdea GC: Haptic feedback for virtual
reality. pp87-96. Pascal and Francis Bibliographic Databases.
https://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=1368767.
|
|
61
|
Laga Boul-Atarass I, Rubio Manzanares
Dorado M, Padillo-Eguía A, Racero-Moreno J, Eguía-Salinas I,
Pereira-Arenas S, Jiménez-Rodríguez RM and Padillo-Ruiz J: Role of
haptic feedback technologies and novel engineering developments for
surgical training and robot-assisted surgery. Front Robot AI.
12(1567955)2025.PubMed/NCBI View Article : Google Scholar
|
|
62
|
Perussolo J, Cavalli N, Calciolari E,
Goldoni M and Donos N: Clinical efficacy of hand and power-driven
instruments for subgingival instrumentation during periodontal
surgical therapy: A systematic review. Clin Oral Investig. 27:1–13.
2023.PubMed/NCBI View Article : Google Scholar
|
|
63
|
Ardila CM, González-Arroyave D and
Vivares-Builes AM: A systematic review of randomized clinical
trials evaluating the efficacy of minimally invasive surgery for
soft tissue management: Aesthetics, postoperative morbidity, and
clinical results. Medicina (Kaunas). 59(924)2023.PubMed/NCBI View Article : Google Scholar
|
|
64
|
Jorba-García A, Bara-Casaus JJ, Camps-Font
O, Sánchez-Garcés MA, Figueiredo R and Valmaseda-Castellón E:
Accuracy of dental implant placement with or without the use of a
dynamic navigation assisted system: A randomized clinical trial.
Clin Oral Implants Res. 34:438–449. 2023.PubMed/NCBI View Article : Google Scholar
|
|
65
|
Schnutenhaus S, Edelmann C, Knipper A and
Luthardt RG: Accuracy of dynamic Computer-assisted implant
placement: A systematic review and Meta-analysis of clinical and in
vitro studies. J Clin Med. 10(704)2021.PubMed/NCBI View Article : Google Scholar
|
|
66
|
Wu XY, Huang ZL, Liu BL, Lv XL, Shi JY and
Lai HC: Accuracy of implant placement with robotic surgery, dynamic
navigation, fully static guide, and freehand surgery: A systematic
review and network meta-analysis. Int J Oral Maxillofac Implants.
41:567–576. 2026.PubMed/NCBI View Article : Google Scholar
|
|
67
|
Pisla D, Bulbucan V, Hedesiu M, Vaida C,
Pusca A, Mocan R, Tucan P, Dinu C and Pisla D: Accuracy of
navigation and robot-assisted systems for dental implant placement:
A systematic review. Dent J (Basel). 13(537)2025.PubMed/NCBI View Article : Google Scholar
|
|
68
|
Xu Z, Zhou L, Han B, Wu S, Xiao Y, Zhang
S, Chen J, Guo J and Wu D: Accuracy of dental implant placement
using different dynamic navigation and robotic systems: An in vitro
study. NPJ Digit Med. 7(182)2024.PubMed/NCBI View Article : Google Scholar
|
|
69
|
Tichy A and Werner N: Artificial
intelligence in periodontology: A systematic review. J Periodontal
Res. 61:639–661. 2026.PubMed/NCBI View Article : Google Scholar
|
|
70
|
Pitchika V, Büttner M and Schwendicke F:
Artificial intelligence and personalized diagnostics in
periodontology: A narrative review. Periodontol 2000. 95:220–231.
2024.PubMed/NCBI View Article : Google Scholar
|
|
71
|
Yadavalli P, Sampoornam Pape Reddy SS and
Kesavalu LK: Artificial intelligence in periodontics and
peri-implant medicine: From diagnosis to precision care. Front Dent
Med. 7(1816844)2026.PubMed/NCBI View Article : Google Scholar
|
|
72
|
World Health Organization. Ethics and
governance of artificial intelligence for health: WHO guidance.
Geneva: World Health Organization, 2021. https://www.who.int/publications/i/item/9789240029200.
|
|
73
|
European Commission. Ethics guidelines for
trustworthy AI. Brussels: European Commission, 2019. https://digital-strategy.ec.europa.eu/en/library/ethics-guidelines-trustworthy-ai.
|
|
74
|
U.S. Food, Drug Administration. Artificial
intelligence and machine learning in software as a medical device.
Silver Spring, MD, FDA, 2023. https://www.fda.gov/medical-devices/digital-health-center-excellence/artificial-intelligence-enabled-medical-devices.
|
|
75
|
Sadilina S, Unkovskiy A, Jung R, Balmer M
and Joda T: Augmented and mixed reality in implant dentistry: A
scoping review exploring clinician- and patient-reported outcomes.
Int J Comput Dent. 29:121–138. 2026.PubMed/NCBI View Article : Google Scholar
|
|
76
|
Perry R, Singh G, Dame A, Mohamed SA,
Idiculla AM and Garg R: The integration of artificial intelligence
and augmented reality in dental education: Current applications and
future potential. Compend Contin Educ Dent. 46:216–222.
2025.PubMed/NCBI
|
|
77
|
Khaohoen A, Powcharoen W, Yoda N,
Rungsiyakull C and Rungsiyakull P: Accuracy in dental implant
placement: A systematic review and meta-analysis comparing
computer-assisted (static, dynamic, robotics) and
noncomputer-assisted (freehand, conventional guide) approaches. J
Prosthet Dent. 134:91.e1–91.e25. 2025.PubMed/NCBI View Article : Google Scholar
|
|
78
|
Jung RE, Schneider D, Ganeles J, Wismeijer
D, Zwahlen M, Hämmerle CH and Tahmaseb A: Computer technology
applications in surgical implant dentistry: A systematic review.
Int J Oral Maxillofac Implants. 24 (Suppl):S92–S109.
2009.PubMed/NCBI
|
|
79
|
Vercruyssen M, Fortin T, Widmann G, Jacobs
R and Quirynen M: Different techniques of static and dynamic
computer-assisted implant surgery: A systematic review. Periodontol
2000. 66:214–227. 2014.PubMed/NCBI View Article : Google Scholar
|
|
80
|
Banerjee S, Rana MM, Akash MMH, Mridula
AT, Al Mamoon I and Rahman QB: Robotics, artificial intelligence,
and computer vision in dental implant surgery: A systematic review
of accuracy, efficiency, and future directions. J Robot Surg.
20(42)2025.PubMed/NCBI View Article : Google Scholar
|
|
81
|
Mai HN, Dam VV and Lee DH: Accuracy of
augmented reality-assisted navigation in dental implant surgery:
Systematic review and meta-analysis. J Med Internet Res.
25(e42040)2023.PubMed/NCBI View
Article : Google Scholar
|
|
82
|
Badiali G, Ferrari V, Cutolo F, Freschi C,
Caramella D, Bianchi A and Marchetti C: Augmented reality as an aid
in maxillofacial surgery: Validation of a wearable system allowing
maxillary repositioning. J Craniomaxillofac Surg. 42:1970–1976.
2014.PubMed/NCBI View Article : Google Scholar
|
|
83
|
Sanz M, Herrera D, Kebschull M, Chapple I,
Jepsen S, Berglundh T, Sculean A and Tonetti MS: EFP Workshop
Participants and Methodological Consultants. Treatment of stage
I-III periodontitis-the EFP S3-level clinical practice guideline. J
Clin Periodontol. 47 (Suppl 22):S4–S60. 2020.PubMed/NCBI View Article : Google Scholar
|
|
84
|
Tonetti MS, Jepsen S, Jin L and
Otomo-Corgel J: Impact of the global burden of periodontal diseases
on health, nutrition and wellbeing of mankind: A call for global
action. J Clin Periodontol. 44:456–462. 2017.PubMed/NCBI View Article : Google Scholar
|
|
85
|
Dawood EA, Abumaylih R, Elgarba BM,
Fontenele RC and Jacobs R: Advances in artificial intelligence
enhanced robotics for dental implant placement: A scoping review. J
Dent. 169(106628)2026.PubMed/NCBI View Article : Google Scholar
|
|
86
|
Menon SS, Jacob SA, Paul AE, Vasudevan AK,
Balakrishnan B and Peter MR: Use of artificial intelligence in
dental implant navigation systems: A scoping review. Cureus.
18(e100776)2026.PubMed/NCBI View Article : Google Scholar
|
|
87
|
Yu X, Tao B, Wang F and Wu Y: Accuracy
assessment of dynamic navigation during implant placement: A
systematic review and meta-analysis of clinical studies in the last
10 years. J Dent. 134(104567)2023.PubMed/NCBI View Article : Google Scholar
|
|
88
|
Pedrinaci I, Gallucci GO, Lanis A,
Friedland B, Pala K and Hamilton A: Computer-assisted implant
planning: A review of data registration techniques. Int J
Periodontics Restorative Dent. 45:652–665. 2025.PubMed/NCBI View Article : Google Scholar
|
