SignalMC-MED: A Multimodal Benchmark for Evaluating Biosignal Foundation Models on Single-Lead ECG and PPG
2026-03-10 • Machine Learning
Machine Learning
AI summaryⓘ
The authors created SignalMC-MED, a new test set to check how well computer models understand heart and blood flow signals recorded together over 10 minutes. They tested different models using either heart signals (ECG), blood flow signals (PPG), or both, and found that models focused specifically on these biosignals do better than general ones. Using both types of signals together was better than using just one, and longer recordings helped improve predictions. They also found that traditional expert-designed features still add useful information alongside the machine-learned features. This work helps researchers compare and improve models analyzing biosignals.
biosignalfoundation modelelectrocardiogram (ECG)photoplethysmogram (PPG)time-series datamultimodal fusionICD-10 diagnosisfeature engineeringclinical predictionbenchmark dataset
Authors
Fredrik K. Gustafsson, Xiao Gu, Mattia Carletti, Patitapaban Palo, David W. Eyre, David A. Clifton
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.