An Artificial Neural Network Prediction Model for Posttraumatic Epilepsy: A Retrospective Cohort Study

Abstract

Background: Artificial neural network (ANN) is commonly used to develop risk prediction model and outperformed than conventional model. Here we aimed to train and validate ANN to predict risk of posttraumatic epilepsy (PTE). Methods: 1301 individuals diagnosed as traumatic brain injury (TBI) were enrolled from West China Hospital. We used a 5-fold cross-validation approach to train and test ANN models. Sensitivity, specificity, accuracy of ANN model was obtained and compared it with a nomogram prediction model built in our former work. The performance of this model was evaluated in patients registered at Chengdu Shang Jin Nan Fu Hospital (testing 1 cohort) and Sichuan Provincial People’s Hospital (testing 2 cohort). Findings: The ANN performed well in the training (AUC = 0.907, 95% CI: 0.889-0.924)) and testing cohorts (testing 1 cohort: AUC = 0.867, 95% CI: 0.842-0.893; testing 2 cohort: AUC = 0.859, 95% CI: 0.826-0.890). The average precision (AP) was 0.557 (95% CI: 0.510-0.620) in training cohort, 0.470 (95% CI: 0.414-0.526) in testing 1 cohort and 0.344 (95% CI: 0.287-0.401) in testing 2 cohort. Sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) in the training cohort (testing 1 and testing 2 cohort) were 0.80 (0.83 and 0.80), 0.86 (0.80 and 0.84), 91% (85% and 78%) and 86% (80% and 83%). ANN model had a higher accuracy than nomogram model (P = 0.04). Interpretation: This study suggests the ANN model could be used to predict the risk of PTE and outperformed than nomogram model and we need to calibrate this model on large-sample-size set. Funding Statement: This study was funded by 1·3·5 project for disciplines of excellence– Clinical Research Incubation Project, West China Hospital, Sichuan University (2019HXFH048). Declaration of Interests: The authors have declared that they have no competing interests. Ethics Approval Statement: The West China Hospital of Sichuan University Ethics Committee approved this study (approval no. 2019-936). Subjects or their proxies gave informed verbal consent to participate in this study.