SignalMC-MED: A Multimodal Benchmark for Evaluating Biosignal Foundation Models on Single-Lead ECG and PPG

2026-03-10

AI Summary

This work addresses the lack of a systematic evaluation benchmark for foundational models on long-duration, multimodal physiological signals—such as electrocardiography (ECG) and photoplethysmography (PPG)—which has hindered their validation and comparison in clinical settings. We propose SignalMC-MED, the first standardized multimodal benchmark for synchronized single-lead ECG and PPG, comprising 10-minute recordings from 22,256 patient encounters and spanning 20 clinical tasks. Through comprehensive evaluation of representative time-series and biosignal foundation models, we demonstrate that domain-specific models consistently outperform general-purpose temporal models, multimodal fusion of ECG and PPG significantly enhances performance, full 10-minute signals yield better results than short segments, smaller models often match or exceed larger ones, and combining handcrafted features with learned representations further improves outcomes.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Recent biosignal foundation models (FMs) have demonstrated promising performance across diverse clinical prediction tasks, yet systematic evaluation on long-duration multimodal data remains limited. We introduce SignalMC-MED, a benchmark for evaluating biosignal FMs on synchronized single-lead electrocardiogram (ECG) and photoplethysmogram (PPG) data. Derived from the MC-MED dataset, SignalMC-MED comprises 22,256 visits with 10-minute overlapping ECG and PPG signals, and includes 20 clinically relevant tasks spanning prediction of demographics, emergency department disposition, laboratory value regression, and detection of prior ICD-10 diagnoses. Using this benchmark, we perform a systematic evaluation of representative time-series and biosignal FMs across ECG-only, PPG-only, and ECG + PPG settings. We find that domain-specific biosignal FMs consistently outperform general time-series models, and that multimodal ECG + PPG fusion yields robust improvements over unimodal inputs. Moreover, using the full 10-minute signal consistently outperforms shorter segments, and larger model variants do not reliably outperform smaller ones. Hand-crafted ECG domain features provide a strong baseline and offer complementary value when combined with learned FM representations. Together, these results establish SignalMC-MED as a standardized benchmark and provide practical guidance for evaluating and deploying biosignal FMs.

Problem

• biosignal foundation models
• multimodal benchmark
• ECG
• PPG
• clinical prediction tasks

Innovation

• biosignal foundation models
• multimodal benchmark
• ECG-PPG fusion
• long-duration signals
• clinical evaluation