harryjdavies/HeartGPT
Interpretable Pre-Trained Transformers for Heart Time-Series Data
This project helps medical researchers and data scientists analyze heart rhythm data from ECG and PPG readings. It takes raw heart time-series data and can generate future heartbeats, detect arrhythmias, or identify specific heartbeats. The output includes predictions about heart conditions and visualizations showing which parts of the heart cycle the model focused on, helping you understand its decisions.
No commits in the last 6 months.
Use this if you are a medical researcher or data scientist working with ECG or PPG data and need to build AI models that can detect heart conditions with clear explanations of their predictions.
Not ideal if you need a certified medical diagnostic tool or are looking for a simple, off-the-shelf application for immediate patient care.
Stars
50
Forks
5
Language
Python
License
MIT
Category
Last pushed
Aug 02, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/harryjdavies/HeartGPT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
VectorInstitute/odyssey
A toolkit for developing foundation models using Electronic Health Record (EHR) data.
ycq091044/BIOT
BIOT - A framework for pretraining biosignals at scale. Large EEG pre-trained models.
AntixK/PyTorch-Model-Compare
Compare neural networks by their feature similarity
woodRock/fishy-business
Machine Learning for Rapid Evaporative Ionization Mass Spectrometry for Marine Biomass Analysis...
soda-inria/carte
Repository for CARTE: Context-Aware Representation of Table Entries