Predicting drug-resistant epilepsy — A machine learning approach based on administrative claims data

Abstract

Objective: To determine whether information in medical and pharmacy claims data can predict, at the time of prescribing the first antiepileptic drug (AED), which patients with epilepsy will become resistant to AEDs. Method: We analyzed longitudinal claims data from 1,376,756 patients with epilepsy from 2006 to 2015. Of these, 582,258 satisfied all inclusion criteria; 49,916 were ultimately AED resistant, operationally defined as a patient with claims filed for at least 4 distinct AEDs. We constructed 1,270 candidate predictors (“features”) reflecting demographics, comorbidities, medications, procedures, epilepsy status, and payer status to characterize the cohort. On the training dataset (528,640 patients) we performed ANOVA F-value tests to select predictive features and trained several prediction algorithms, including logistic regression, support vector machines (SVM), and random forests. A model with only age and gender was used as a benchmark model. Results: On a held-out test set (53,618 patients), the best model achieves an area under the receiver operating characteristic (ROC) curve (AUC) [95% CI] of 0.753 [0.747, 0.759], compared to 0.664 [0.658, 0.671] for the benchmark model. Moreover, predicted probabilities for drug resistance closely match the observed frequencies. Compared to waiting for 2 AED failures, our model predicts drug resistance on average 2.25 years earlier. Conclusion: Predictive models created from large claims data using machine learning methods can accurately predict which patients with epilepsy will prove drug resistant at the time of prescribing the first AED. The ability to predict refractoriness may help patients consider alternative therapies earlier in the course of their epilepsy.

Machine learning algorithm for early mortality prediction in patients with advanced penile cancer

“…Many machine learning models for mortality prediction in other domains include significantly more patients. Despite this, the model was able to achieve AUC 0.65, which is consistent with performance of models for similarly challenging healthcare-related prediction problems [9,26].…”

Machine learning applications in epilepsy

“…More recently, An et al compared machine learning algorithms for prediction of drug‐resistant epilepsy (defined as requiring more than three medication changes during the study period) utilizing comprehensive U.S. claims data from 2006 to 2015. The authors found that the best‐performing algorithm, a random forest classifier trained using 635 features (comprising demographic variables, comorbidities, treatment regimens, insurance data, and clinical encounters) from 175 735 records, yielded an AUC of 76.4% and could identify patients with drug‐resistant epilepsy an average of 1.97 years before failing a second medication trial, using data available at the time of the first medication prescription …”

“…The authors found that the best-performing algorithm, a random forest classifier trained using 635 features (comprising demographic variables, comorbidities, treatment regimens, insurance data, and clinical encounters) from 175 735 records, yielded an AUC of 76.4% and could identify patients with drug-resistant epilepsy an average of 1.97 years before failing a second medication trial, using data available at the time of the first medication prescription. 88 A number of studies have also demonstrated the capabilities of machine learning algorithms in predicting individual medication responses. Devinsky et al examined clinical characteristics (eg, type and number of medications used, age, and comorbidities) from records of 34 990 patients extracted from a medical claims database, and trained a random forest classifier to predict a medication regimen least likely to require changes in the following 12 months (serving as a proxy of regimen efficacy and tolerability).…”

Long-term EEG monitoring and positron emission tomography in evaluating patients with drug-resistant epilepsy

“…Failure of ≥ 2 AEDs trials is a commonly faced problem in epilepsy practice which needs meticulous assessment of patients for proper management [17]. The current study showed nearly one-third of originally diagnosed DRE patients in the epilepsy clinic had NEEE due toimprecise initial diagnosis of functional seizures because of SSA and/or EEG misinterpretation as well as faulty diagnosis of frequent pseudo-seizures occurring in controlled epileptic patients relied on the previous organic epileptic nature of their illnesses.…”