Abstract
This article introduces a machine learning approach, based on a nonparametric, decision-tree-based random survival forest (RSF) model, for a continuous prognosis of epileptic seizure events using electroencephalogram (EEG) data. While earlier seizure prediction methods forecast seizure occurrences only at a specified future time, the RSF model allows estimation of the probability of seizure onset, in terms of a hazard function, over the entire prediction horizon. These estimates are crucial for developing individualized quantitative risk measures and management plans for epilepsy patients. Additionally, RSF can identify the key risk factors by capturing the interdependencies among the features extracted from EEG data. The performance of RSF was evaluated for prognosing seizure onsets of the rat and mice specimens in an 80 small animals cohort at the Texas A&M Department of Neuroscience and Experimental Therapeutics. The results suggest that RSF outperforms other contemporary survival models, including the popular Cox proportional hazard, with 87.5% lower integrated Brier Score (IBS) errors, and 17.5% higher concordance index (C-index). Further, a continuous seizure prediction sensitivity of 83% and specificity of 87% were obtained even over a 5-min prediction horizon (the average time between successive seizure onsets was 5 min long). These results suggest that the RSF model can be used to effectively quantify the likelihood of seizure onsets over time to the patients and caregivers, promoting informed decision making.
Acknowledgment
The authors thank the trained technician staff of the Department of Neuroscience and Experimental Therapeutics at the Texas A&M College of Medicine for carrying out the experimentation and annotating the EEG files.
Disclosure of interest
There is no conflict of interest to declare.
Consent and approval
The animal procedures were approved by Texas A&M University's institutional animal care and use committee in compliance with the guidelines of the NIH Guide for the Care and Use of Laboratory Animals (NIH, Citation1985).