README.md

---
title: HeartWatchAI
emoji: ❤️
colorFrom: red
colorTo: pink
sdk: gradio
sdk_version: 5.6.0
app_file: app.py
pinned: false
short_description: AI-powered 12-Lead ECG Analysis
hf_oauth: false
---

# HeartWatch AI

AI-powered 12-Lead ECG analysis using deep learning models.

## Features

- **77-Class ECG Diagnosis**: Detect 77 different cardiac conditions
- **LVEF Prediction**: Predict left ventricular ejection fraction < 40% and < 50%
- **AFib Risk**: 5-year atrial fibrillation risk prediction
- **Interactive Visualization**: Clinical 4x3 lead layout with ECG paper grid

## Models

This demo uses EfficientNetV2 models from the DeepECG project:

- `heartwise/EfficientNetV2_77_Classes`
- `heartwise/EfficientNetV2_LVEF_40`
- `heartwise/EfficientNetV2_LVEF_50`
- `heartwise/EfficientNetV2_AFIB_5y`

## Input Format

- NumPy array (.npy file)
- Shape: (2500, 12) or (12, 2500)
- 12 standard leads: I, II, III, aVR, aVL, aVF, V1-V6
- 10 seconds at 250 Hz sampling rate

## Disclaimer

This is a research demonstration tool. Predictions should NOT be used for clinical decision-making. Always consult qualified healthcare professionals for medical advice.