Open Access

A comparison of machine learning classifiers for pediatric epilepsy using resting‑state functional MRI latency data

  • Authors:
    • Ryan D. Nguyen
    • Matthew D. Smyth
    • Liang Zhu
    • Ludovic P. Pao
    • Shannon K. Swisher
    • Emmett H. Kennady
    • Anish Mitra
    • Rajan P. Patel
    • Jeremy E. Lankford
    • Gretchen Von Allmen
    • Michael W. Watkins
    • Michael E. Funke
    • Manish N. Shah
  • View Affiliations

  • Published online on: July 23, 2021     https://doi.org/10.3892/br.2021.1453
  • Article Number: 77
  • Copyright: © Nguyen et al. This is an open access article distributed under the terms of Creative Commons Attribution License.

Metrics: Total Views: 0 (Spandidos Publications: | PMC Statistics: )
Total PDF Downloads: 0 (Spandidos Publications: | PMC Statistics: )


Abstract

Epilepsy affects 1 in 150 children under the age of 10 and is the most common chronic pediatric neurological condition; poor seizure control can irreversibly disrupt normal brain development. The present study compared the ability of different machine learning algorithms trained with resting‑state functional MRI (rfMRI) latency data to detect epilepsy. Preoperative rfMRI and anatomical MRI scans were obtained for 63 patients with epilepsy and 259 healthy controls. The normal distribution of latency z‑scores from the epilepsy and healthy control cohorts were analyzed for overlap in 36 seed regions. In these seed regions, overlap between the study cohorts ranged from 0.44‑0.58. Machine learning features were extracted from latency z‑score maps using principal component analysis. Extreme Gradient Boosting (XGBoost), Support Vector Machines (SVM), and Random Forest algorithms were trained with these features. Area under the receiver operating characteristics curve (AUC), accuracy, sensitivity, specificity and F1‑scores were used to evaluate model performance. The XGBoost model outperformed all other models with a test AUC of 0.79, accuracy of 74%, specificity of 73%, and a sensitivity of 77%. The Random Forest model performed comparably to XGBoost across multiple metrics, but it had a test sensitivity of 31%. The SVM model did not perform >70% in any of the test metrics. The XGBoost model had the highest sensitivity and accuracy for the detection of epilepsy. Development of machine learning algorithms trained with rfMRI latency data could provide an adjunctive method for the diagnosis and evaluation of epilepsy with the goal of enabling timely and appropriate care for patients.
View Figures
View References

Related Articles

Journal Cover

September-2021
Volume 15 Issue 3

Print ISSN: 2049-9434
Online ISSN:2049-9442

Sign up for eToc alerts

Recommend to Library

Copy and paste a formatted citation
x
Spandidos Publications style
Nguyen RD, Smyth MD, Zhu L, Pao LP, Swisher SK, Kennady EH, Mitra A, Patel RP, Lankford JE, Von Allmen G, Von Allmen G, et al: A comparison of machine learning classifiers for pediatric epilepsy using resting‑state functional MRI latency data. Biomed Rep 15: 77, 2021
APA
Nguyen, R.D., Smyth, M.D., Zhu, L., Pao, L.P., Swisher, S.K., Kennady, E.H. ... Shah, M.N. (2021). A comparison of machine learning classifiers for pediatric epilepsy using resting‑state functional MRI latency data. Biomedical Reports, 15, 77. https://doi.org/10.3892/br.2021.1453
MLA
Nguyen, R. D., Smyth, M. D., Zhu, L., Pao, L. P., Swisher, S. K., Kennady, E. H., Mitra, A., Patel, R. P., Lankford, J. E., Von Allmen, G., Watkins, M. W., Funke, M. E., Shah, M. N."A comparison of machine learning classifiers for pediatric epilepsy using resting‑state functional MRI latency data". Biomedical Reports 15.3 (2021): 77.
Chicago
Nguyen, R. D., Smyth, M. D., Zhu, L., Pao, L. P., Swisher, S. K., Kennady, E. H., Mitra, A., Patel, R. P., Lankford, J. E., Von Allmen, G., Watkins, M. W., Funke, M. E., Shah, M. N."A comparison of machine learning classifiers for pediatric epilepsy using resting‑state functional MRI latency data". Biomedical Reports 15, no. 3 (2021): 77. https://doi.org/10.3892/br.2021.1453