Research map / Label-efficient and robust learning / Recognition and long-tail
A robust PPG foundation model using multimodal physiological supervision
Eloy Geenjaar, Vince D. Calhoun, scott daly, Gouthaman KV, Lie Lu, Trisha Mittal, Daniel P. Darcy
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| supervise contrastive PPG pretraining with ECG+RESP-derived metrics instead of PPG morphology (PaPaGei-S) (ablation) | PPG foundation model · 15 downstream tasks, across-subject | task performance: better on 14 of 15 tasks | Improved |
| add ECG+RESP metric supervision (vs PulsePPG) on field-like HR | PPG foundation model · PPG-DaLiA HR | MAE: 10.5 -> 7.78 | Improved |
| ECG+RESP supervision versus PulsePPG on VitalVideos systolic BP | PPG foundation model · VitalVideos Sys-BP | MAE: 15.7 -> 15.9 | Hurt |
| evaluate within-subject: ECG+RESP supervision vs PulsePPG on daily activities | PPG foundation model · PPG-DaLiA activities, within-subject | macro F1: 0.49 -> 0.69 | Improved |
| use ECG-only instead of ECG+RESP supervision (ablation) | PPG foundation model · regression tasks, across-subject | average MAE: 9.45 -> 9.25 | Improved |
| use ECG+RESP instead of ECG-only or RESP-only supervision (ablation) | PPG foundation model · classification tasks, across-subject | average accuracy: 0.63 -> 0.64 | Improved |
| use RESP-only supervision (ablation) | PPG foundation model · DaLiA and WildPPG HR | MAE | Improved |
| use larger proposed backbone instead of PaPaGei backbone (ablation) | PPG foundation model · downstream tasks | task performance | Improved |
| train with only 10% of data in within-subject probing (ablation) | PPG foundation model · within-subject probing | task performance | Improved |
Closest papers by meaning
- PaPaGei: Open Foundation Models for Optical Physiological Signals (ICLR 2025 · similarity 0.91)
- Large-scale Training of Foundation Models for Wearable Biosignals (ICLR 2024 · similarity 0.87)
- WildPPG: A Real-World PPG Dataset of Long Continuous Recordings (NeurIPS 2024 · similarity 0.86)
- RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement (AAAI 2025 · similarity 0.86)
- PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological Measurement (AAAI 2025 · similarity 0.86)
- Constraint Latent Space Matters: An Anti-anomalous Waveform Transformation Solution from Photoplethysmography to Arterial Blood Pressure (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
