cs.LGNov 11, 2026

A Cardiorespiratory Foundation Model Pretrained on Ten Physiological Signals for Perioperative and Critical Care

Authors: Cheol-Hui Lee, Wookyung Kim, Hyeonhoon Lee, Garam Lee, Da-in Eun, Hyung-Chul Lee

Organizations: Healthcare AI Research Institute, Seoul National University Hospital, Seoul, Republic of Korea · Interdisciplinary Program in Medical Informatics, College of Medicine, Seoul National University, Seoul, Republic of Korea · Department of Transdisciplinary Medicine, Seoul National University Hospital, Seoul, Republic of Korea · Department of Anesthesiology and Pain Medicine, Seoul National University College of Medicine and Seoul National University Hospital, Seoul, Republic of Korea

Abstract

Arterial, venous, pulmonary artery and intracranial pressures and ventilator waveforms guide decisions in operating rooms and intensive care units, yet foundation models for physiological waveforms have been built almost entirely on the electrocardiogram and photoplethysmogram. We present CARMEN, a single encoder pretrained without labels on ten cardiorespiratory waveforms (2.27 million modality-hours). CARMEN accepts any combination of co-recorded signals from 10 s to 5 min, and a conditioning mechanism, LSCNorm, restores the absolute signal level that normalization removes; without it, the AUROC for intraoperative hypotension fell from 0.894 to 0.780. Across 19 tasks from Korean and US cohorts, the frozen encoder outperformed supervised models on 12 of 15 and three foundation models, one general-purpose and two for biosignals, on 14 to 17 of 19, with none exceeding it on any task. Given the electrocardiogram or photoplethysmogram alone, it matched or exceeded signal-specific foundation models in most comparisons, and it retained its performance when channels were missing.

Figures & tables

Explore similar work

CardsList
  1. Training and Scaling Compute-Optimal Physiological Waveform Foundation Models

    Oct 5, 2026Pingzhi Li, Jie Peng, Shuqing Luo +2Compute-Optimal TrainingTime-Series Foundation Models

  2. Event Fields: Learning Latent Event Structure for Waveform Foundation Models

    May 9, 2026Li Na, Yuanyun Zhang, Shi LiIrregular Time-Series ModelingLatent Dynamics Modeling