pyhealth - Develop and evaluate healthcare AI models
Loads clinical datasets, defines prediction tasks, preprocesses data, trains models, and evaluates healthcare AI systems.
Tags
Updated: 2026-10-03Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Load healthcare datasets
- Define clinical prediction tasks
- Translate medical codes
- Preprocess clinical data
- Select healthcare models
- Train machine learning models
- Evaluate clinical predictions
- Calibrate model predictions
- Interpret model outputs
- Assess prediction fairness
Inputs
- Healthcare datasets
- Clinical prediction objectives
- Medical coding systems
- Physiological signals
- Clinical text
- Medical images
- Model configurations
- Training parameters
Outputs
- Trained model checkpoints
- Evaluation metrics
- Prediction results
- Calibrated predictions
- Interpretability results
- Fairness assessments
Requirements
- Python 3.7 or later
- PyTorch 1.8 or later
- NumPy
- pandas
- scikit-learn