pyhealth

Automate end-to-end healthcare AI model development with EHR datasets and evaluation utilities.

94|11|Updated Mar 26, 2026
One-click install
npx skills add https://github.com/swaruplab/operon --skill pyhealth-swaruplab
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pyhealth
Source: https://github.com/swaruplab/operon/tree/main/src-tauri/protocols/pyhealth
Command: npx skills add https://github.com/swaruplab/operon --skill pyhealth-swaruplab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

PyHealth provides a unified, modular toolkit to build, train, evaluate, and deploy healthcare AI models, reducing integration effort and enabling reproducible experiments.

Core Features & Use Cases

  • Modular data pipelines for datasets, tasks, models, training, and evaluation
  • Rich documentation and reference materials for clinical prediction, coding, and healthcare data
  • End-to-end workflows from raw EHR data (MIMIC, eICU, OMOP) to interpretable predictions
  • Real-world workflows: mortality prediction, readmission, LOS, drug recommendation, sleep EEG analysis

Quick Start

Install and run a basic predictive workflow with MIMIC-IV data to generate your first results.

Frequently Asked Questions about pyhealth

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I develop clinical prediction models for EHR datasets like MIMIC-III?

Build clinical prediction models for EHR datasets like MIMIC-III using a modular pipeline that provides ready-made datasets, tasks, and scalable training utilities for mortality and readmission predictions.

What healthcare AI tasks can I automate using MIMIC-IV and eICU data?

Using MIMIC-IV and eICU data, you can automate healthcare AI tasks including mortality prediction, length of stay, drug recommendation, and sleep EEG analysis through standardized end-to-end workflows.

Can I train interpretable machine learning models for medical coding?

Yes, you can train interpretable machine learning models for medical coding. The toolkit supports calibration, uncertainty quantification, and interpretable predictions directly within its standardized training pipeline.

Does this healthcare AI toolkit support sleep EEG signal processing?

Yes, the healthcare AI toolkit supports sleep EEG signal processing. It includes ready-made datasets and models specifically designed for healthcare signal processing alongside clinical prediction tasks.

What's the best way to standardize EHR data pipelines for reproducible model deployment?

Standardize EHR data pipelines for reproducible model deployment by using a unified modular toolkit that integrates datasets, tasks, models, and a Trainer to reduce integration effort and enable reproducible experiments.