8000 Digital Health Lab @ Peking University · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
@PKUDigitalHealth

Digital Health Lab @ Peking University

Led by Shenda Hong at Peking University, our lab is dedicated to advancing deep learning techniques for temporal medical data and physiological signals.

About Us

Our lab primarily focuses on the following two areas of research:

  • Deep learning for temporal medical data: temporal events, time series (e.g. longitudinal data, cohort, electronic health records), and physiological signals (e.g. ECG, EEG, PPG, PCG, PSG). We won the first place of the 18th PhysioNet/Computing in Cardiology Challenge, and released a DNN backbone Net1D. Currently working on learning in label scarce environment, generative methods, integrating with medical knowledge and other modality data (e.g. texts).

  • Digital health: enhancing smart devices with AI and applications in healthcare, portable ECG device, flexible ECG patch, smart watch (with PPG/ECG sensor), smart ring (with PPG sensor), smart stethoscope (with PCG sensor), smart eyemask (with EEG sensor). Currently collaborating closely with affiliated hospitals of Peking University, working on smart devices for sleep disorders, cardiovascular disease, and fetal monitoring.

News

We are recruiting PostDoc (Opening, Doctors of Public Health are also welcomed), Ph.D. (two positions available for 2026 at School of Intelligence Science Technology (SIST, 智能学院)), and Interns (Opening always) who have a strong passion for health data science with coding skills. If you are interested, please send email with your CV.

Pinned Loading

  1. ECGFounder ECGFounder Public

    Forked from NickLJLee/ECGFounder

    This is the official implementation of our paper "An Electrocardiogram Foundation Model Built on over 10 Million Recordings with External Evaluation across Multiple Domains".

    Python 13 2

  2. HeartLang HeartLang Public

    [ICLR 2025] The official implementation of our paper "Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model".

    Python 23 3

  3. DiffuSETS DiffuSETS Public

    The official implementation of our paper "DiffuSETS: 12-lead ECG Generation Conditioned on Clinical Text Reports and Patient-Specific Information".

    Python 8 1

  4. resnet1d resnet1d Public

    Forked from hsd1503/resnet1d

    PyTorch implementations of several SOTA backbone deep neural networks (such as ResNet, ResNeXt, RegNet) on one-dimensional (1D) signal/time-series data.

    Python 3

  5. SDI SDI Public

    Forked from sczzz3/SDI

    The official implementation of our paper "Continuous Sleep Depth Index Annotation with Deep Learning Yields Novel Digital Biomarkers for Sleep Health".

    Python 5

  6. FeatureDB FeatureDB Public

    Forked from hsd1503/ECG_feature_extraction

    Pattern recognition methods for feature extraction from ECG (open source version)

    Python 6

Repositories

Showing 10 of 16 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…

0