CVAI Catalog

·

View Catalog

tune

1 model found

·

1 public code

·

1 public weights

AnyPPG

Peking University (PKUDigitalHealth) · 2025

graph_1

Code & model weights public

ECG-guided photoplethysmography (PPG) foundation model pretrained on over 100,000 hours of synchronized PPG-ECG recordings from 58,796 subjects across five clinical and wearable sources, using a CLIP-style contrastive alignment framework so the PPG encoder inherits physiologically grounded structure from paired ECG. Achieves state-of-the-art performance on 13 of 15 conventional physiological-analysis tasks across eight datasets, and shows meaningful discriminative capability (AUC >= 0.70) for 307 ICD-10-coded phenotypes across 16 phecode chapters, including many non-cardiovascular conditions.

PPG / wearable

Filter by Modality:
PPG / Wearable

General Purpose / Multi-task

Filter by Disease / Trait:
General / Foundation

Atrial fibrillation

Filter by Disease / Trait:
Arrhythmia

Blood pressure estimation

Filter by Disease / Trait:
Cardiac Function & Hemodynamics

Embedding

Filter by Task Type:
Representation Learning

Binary classification

Filter by Task Type:
Classification

Regression

Filter by Task Type:
Regression

CNN (1D)

Filter by Architecture:
Convolutional (CNN)

PyTorch

Filter by Framework:
PyTorch


Model ID: 0067

·

Subject Count: 58,796