cs.LGNov 2, 2026

Temporal Island Sparse Autoencoders for Interpreting Clinical Time-Series Models

Authors: Muhan Yeo, Bong Gyun Kang, HyunGi Kim, Sungroh Yoon

Organizations: Department of Electrical and Computer Engineering and Interdisciplinary Program in Artificial Intelligence, Seoul National University, Seoul, Republic of Korea · McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA · UNIST InnoCORE AI-Space Solar Initiative, Ulsan National Institute of Science and Technology (UNIST), Ulsan, Republic of Korea

Abstract

Deep learning models for electronic health records achieve strong predictive performance but provide little insight into what clinical concepts they represent internally. Post-hoc attribution methods produce per-cell importance scores that lack temporal coherence, cross-variable structure, and reusability across patients. We introduce the Temporal Island Sparse Autoencoder (TI-SAE), which learns a backbone-specific, patient-shared clinical concept dictionary from a frozen predictive model's representations. Each dictionary entry (latent) is defined by learned temporal Gaussian islands (specifying when the concept is active) and a sparse variable-composition vector (specifying which variables are involved). A decoupled selector then identifies which dictionary entries drive each patient's prediction, separating representation learning from attribution. We evaluate TI-SAE across five backbone architectures spanning different representation strategies on MIMIC-III and MIMIC-IV (three prediction tasks each). TI-SAE produces structured clinical concepts that go beyond transient attribution heatmaps while achieving strong performance on standard faithfulness benchmarks.

Figures & tables

Appendix figures & tables53 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction

    Apr 13, 2026Chris Sainsbury, Feng Dong, Andreas KarwathEHR Foundation ModelsSparse Autoencoders