Stochastic Sparse Sampling: A Framework for Variable-Length Medical Time Series Classification

TL;DR

This paper introduces Stochastic Sparse Sampling (SSS), a new framework for classifying variable-length medical time series, demonstrating superior accuracy and interpretability in seizure localization across diverse datasets.

Contribution

The paper presents SSS, a novel framework for variable-length time series classification that effectively manages sequence variability and provides interpretability in medical applications.

Findings

SSS outperforms state-of-the-art methods on multiple datasets.

SSS maintains high accuracy on unseen medical centers.

SSS offers post-hoc interpretability through local prediction visualization.

Abstract

While the majority of time series classification research has focused on modeling fixed-length sequences, variable-length time series classification (VTSC) remains critical in healthcare, where sequence length may vary among patients and events. To address this challenge, we propose $\textbf{S}$tochastic $\textbf{S}$parse $\textbf{S}$ampling (SSS), a novel VTSC framework developed for medical time series. SSS manages variable-length sequences by sparsely sampling fixed windows to compute local predictions, which are then aggregated and calibrated to form a global prediction. We apply SSS to the task of seizure onset zone (SOZ) localization, a critical VTSC problem requiring identification of seizure-inducing brain regions from variable-length electrophysiological time series. We evaluate our method on the Epilepsy iEEG Multicenter Dataset, a heterogeneous collection of intracranial electroencephalography (iEEG) recordings obtained from four independent medical centers. SSS demonstrates superior performance compared to state-of-the-art (SOTA) baselines across most medical centers, and superior performance on all out-of-distribution (OOD) unseen medical centers. Additionally, SSS naturally provides post-hoc insights into local signal characteristics related to the SOZ, by visualizing temporally averaged local predictions throughout the signal.