Early identification of epilepsy surgery candidates: A multicenter, machine learning study

Abstract

Objectives: Epilepsy surgery is underutilized. Automating the identification of potential surgical candidates may facilitate earlier intervention. Our objective was to develop site-specific machine learning (ML) algorithms to identify candidates before they undergo surgery. Materials & Methods:In this multicenter, retrospective, longitudinal cohort study, ML algorithms were trained on n-grams extracted from free-text neurology notes, EEG and MRI reports, visit codes, medications, procedures, laboratories, and demographic information. Site-specific algorithms were developed at two epilepsy centers: one pediatric and one adult. Cases were defined as patients who underwent resective epilepsy surgery, and controls were patients with epilepsy with no history of surgery. The output of the ML algorithms was the estimated likelihood of candidacy for resective epilepsy surgery. Model performance was assessed using 10-fold cross-validation.Results: There were 5880 children (n = 137 had surgery [2.3%]) and 7604 adults with epilepsy (n = 56 had surgery [0.7%]) included in the study. Pediatric surgical patients could be identified 2.0 years (range: 0-8.6 years) before beginning their presurgical evaluation with AUC =0.76 (95% CI: 0.70-0.82) and PR-AUC =0.13 (95% CI: 0.07-0.18). Adult surgical patients could be identified 1.0 year (range: 0-5.4 years) before beginning their presurgical evaluation with AUC =0.85 (95% CI: 0.78-0.93) and PR-AUC =0.31 (95% CI: 0.14-0.48). By the time patients began their presurgical evaluation, the ML algorithms identified pediatric and adult surgical patients with AUC =0.93 and 0.95, respectively. The mean squared error of the predicted probability of surgical candidacy (Brier scores) was 0.018 in pediatrics and 0.006 in adults.Conclusions: Site-specific machine learning algorithms can identify candidates for epilepsy surgery early in the disease course in diverse practice settings.

Transforming epilepsy research: A systematic review on natural language processing applications

“…Most of the included studies exploited NLP techniques to identify—and discriminate between—patients based on their documented clinical history and conditions 16–30 . The process often entailed classifying patient reports or interviews into predefined categories based on the prominent differences in textual features.…”

“…A series of research extended the applicability of NLP to identifying potential patient candidates for epilepsy surgery 21–24 . Wissel and colleagues validated the ability of a machine learning‐based NLP model to recognize various types of tokenized clinical features from EHRs, such as features describing seizure types and drug resistance.…”

“…Furthermore, it may contribute to the simultaneous analysis of different clinical records, such as physician notes and brain imaging reports, to substantiate a diagnosis or treatment decision. For example, Wissel and colleagues validated the ability of an NLP model to identify pediatric surgical patients up to 2 years before the patients were referred to presurgical evaluations 24 . Ideally, one would have direct access to the information provided by these NLP algorithms.…”

“…In this respect, rule‐based algorithms may be more favorable than machine learning models, as the former offer more transparency and are not subjected to random statistical fluctuations 58 . Machine learning models that produce probabilistic scores may also allow for better verification than binary classifiers, 56 such as the score‐generating algorithm developed by Wissel and colleagues 24 …”

Artificial Intelligence Applications in Clinical Neurosurgery

“…The study revealed that AI-based models identified adult patients better than pediatrics eligible for surgery. However, it was possible to predict pediatric surgical patients 2.0 years before their presurgical evaluation (48). However, machine learning might not accurately predict long-term outcomes in some cases.…”