RAxSS: Retrieval-Augmented Sparse Sampling for Explainable Variable-Length Medical Time Series Classification
Abstract
Medical time series analysis is challenging due to data sparsity, noise, and highly variable recording lengths. Prior work has shown that stochastic sparse sampling effectively handles variable-length signals, while retrieval-augmented approaches improve explainability and robustness to noise and weak temporal correlations. In this study, we generalize the stochastic sparse sampling framework for retrieval-informed classification. Specifically, we weight window predictions by within-channel similarity and aggregate them in probability space, yielding convex series-level scores and an explicit evidence trail for explainability. Our method achieves competitive iEEG classification performance and provides practitioners with greater transparency and explainability. We evaluate our method in iEEG recordings collected in four medical centers, demonstrating its potential for reliable and explainable clinical variable-length time series classification.
Cite
@article{arxiv.2510.02936,
title = {RAxSS: Retrieval-Augmented Sparse Sampling for Explainable Variable-Length Medical Time Series Classification},
author = {Aydin Javadov and Samir Garibov and Tobias Hoesli and Qiyang Sun and Florian von Wangenheim and Joseph Ollier and Björn W. Schuller},
journal= {arXiv preprint arXiv:2510.02936},
year = {2025}
}
Comments
Accepted at the NeurIPS 2025 Workshop on Learning from Time Series for Health