cs.LGNov 13, 2026

SLICES: A Benchmark and Evaluation Framework for Self-Supervised Learning on Sparse ICU Time Series

Authors: Hannes Ill, Dimitrios Proios, Leo Anthony Celi, Peter J. Schüffler

Organizations: Laboratory for Computational Physiology, Massachusetts Institute of Technology, USA · Institute of Pathology, Technical University of Munich, TUM School of Medicine and Health, Munich, Germany · Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Geneva, Switzerland · Division of Pulmonary, Critical Care and Sleep Medicine, Beth Israel Deaconess Medical Center, USA · 

Abstract

Self-supervised learning (SSL) results for intensive care unit (ICU) time series are hard to compare when data processing, encoders, and adaptation vary together. We present SLICES, a benchmark and evaluation framework for comparing and extending SSL methods under a shared clinical setup. It fixes 24-hour value and observation-mask inputs, a Transformer encoder, patient-level splits, four endpoints, two adaptation protocols, and five matched seeds across MIMIC-IV, eICU-CRD, and their pooled union. Masked autoencoding (MAE), joint-embedding prediction (JEPA), and contrastive learning provide reference implementations. Among these objectives, MAE leads mean AUPRC in all nine frozen classification comparisons, also under converged probes, and in seven of nine fine-tuning comparisons. Fine-tuned MAE leads hospital mortality at full labels and scores higher than a supervised Transformer of the same architecture at every label fraction, and SSL fine-tuning gives the lowest length-of-stay error. Supervised baselines remain strong elsewhere: GRU-D leads 24-hour mortality and XGBoost leads acute kidney injury in all three regimes. Rankings depend on the adaptation protocol, the comparator set, and whether the probe loss matches the metric. A two-seed MIMIC-IV rerun with the maintained code stays within two across-seed SDs of the reference in all 48 downstream runs. The code repository supports new objectives, shared downstream evaluation, and regeneration of the reference results, so new SSL methods can be compared with these references under the same conditions. Generalization to unseen hospitals is not tested here and is the natural next extension.

Figures & tables

Appendix figures & tables25 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning

    Jul 1, 2026Alexander Chemeris, Ming Jin, Randall BalestrieroTime Series ClassificationSelf-Supervised Time Series Representation Learning

  2. A Framework for Early Sepsis Prediction via Self-Supervised (JEPA) and Federated Representation Learning

    Jul 18, 2026Umair bin Mansoor, Munaf Rashid, Roomi NaqviSepsis PredictionSelf-Supervised Pre-Training

  3. 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