Classifying Clinical Outcome of Epilepsy Patients with Ictal Chirp Embeddings

TL;DR

This paper introduces a novel approach combining t-SNE visualizations, chirp feature analysis, and machine learning classifiers to improve clinical outcome prediction in epilepsy patients, providing interpretable insights into the data's structure.

Contribution

The study develops an integrated framework using t-SNE embeddings and feature attribution maps for clinical outcome classification in epilepsy, enhancing interpretability and decision support.

Findings

Random Forest and k-NN achieved up to 88.8% accuracy.

t-SNE effectively visualized complex chirp features.

SHAP maps revealed localized feature importance.

Abstract

This study presents a pipeline leveraging t-Distributed Stochastic Neighbor Embedding (t-SNE) for interpretable visualizations of chirp features across diverse outcome scenarios. The dataset, comprising chirp-based temporal, spectral, and frequency metrics. Using t-SNE, local neighborhood relationships were preserved while addressing the crowding problem through Student t-distribution-based similarity optimization. Three classification tasks were formulated on the 2D t-SNE embeddings: (1) distinguishing clinical success from failure/no-resection, (2) separating high-difficulty from low-difficulty cases, and (3) identifying optimal cases, defined as successful outcomes with minimal clinical difficulty. Four classifiers, namely, Random Forests, Support Vector Machines, Logistic Regression, and k-Nearest Neighbors, were trained and evaluated using stratified 5-fold cross-validation. Across tasks, the Random Forest and k-NN classifiers demonstrated superior performance, achieving up to 88.8% accuracy in optimal case detection (successful outcomes with minimal clinical difficulty). Additionally, feature influence sensitivity maps were generated using SHAP explanations applied to model predicting t-SNE coordinates, revealing spatially localized feature importance within the embedding space. These maps highlighted how specific chirp attributes drive regional clustering and class separation, offering insights into the latent structure of the data. The integrated framework showcases the potential of interpretable embeddings and local feature attribution for clinical stratification and decision support.