Identifying Similarities in Epileptic Patients for Drug Resistance Prediction
This work addresses drug resistance prediction for epileptic patients, but it is incremental as it applies existing methods to a specific medical dataset.
This study tackled the problem of predicting drug resistance in epileptic patients by analyzing similarities between refractory and non-refractory cases, achieving an accuracy of 0.83 with a standard deviation of +/-0.3 using cross-validation.
Currently, approximately 30% of epileptic patients treated with antiepileptic drugs (AEDs) remain resistant to treatment (known as refractory patients). This project seeks to understand the underlying similarities in refractory patients vs. other epileptic patients, identify features contributing to drug resistance across underlying phenotypes for refractory patients, and develop predictive models for drug resistance in epileptic patients. In this study, epileptic patient data was examined to attempt to observe discernable similarities or differences in refractory patients (case) and other non-refractory patients (control) to map underlying mechanisms in causality. For the first part of the study, unsupervised algorithms such as Kmeans, Spectral Clustering, and Gaussian Mixture Models were used to examine patient features projected into a lower dimensional space. Results from this study showed a high degree of non-linearity in the underlying feature space. For the second part of this study, classification algorithms such as Logistic Regression, Gradient Boosted Decision Trees, and SVMs, were tested on the reduced-dimensionality features, with accuracy results of 0.83(+/-0.3) testing using 7 fold cross validation. Observations of test results indicate using a radial basis function kernel PCA to reduce features ingested by a Gradient Boosted Decision Tree Ensemble lead to gains in improved accuracy in mapping a binary decision to highly non-linear features collected from epileptic patients.