skills.rest
SciMate-AI
SciMate-AIOFFICIAL
Explore all skills by this author →
GitHub

pyhealth

Build, evaluate, and deploy healthcare AI models across EHR, signals, imaging, and text.

1|Updated Mar 11, 2026
Search Tags:#ai#healthcare#datasets#machine-learning#interpretability#pyhealth
One-click install
npx skills add https://github.com/SciMate-AI/scicli --skill pyhealth-scimate-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pyhealth
Source: https://github.com/SciMate-AI/scicli/tree/main/internal/skills/bundled/claude-scientific-skills/skills/pyhealth
Command: npx skills add https://github.com/SciMate-AI/scicli --skill pyhealth-scimate-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

PyHealth provides a cohesive, extensible toolkit for developing, evaluating, and deploying healthcare AI models across EHR, clinical data, and multi-modal tasks, simplifying experimentation and deployment.

Core Features & Use Cases

  • Modular pipelines for electronic health records, physiological signals, medical imaging, and clinical text.
  • End-to-end workflows for data loading, task definition, preprocessing, model training, evaluation, calibration, and deployment.
  • Interpretable models (e.g., RETAIN, AdaCare) and health-specific recommendations (GAMENet, SafeDrug) with practical case studies.
  • References and example pipelines spanning datasets like MIMIC, eICU, OMOP, Sleep EEG, and COVID-19 imaging.

Quick Start

Install PyHealth and run the provided mortality prediction workflow on your local MIMIC-IV dataset.

Frequently Asked Questions about pyhealth

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

FAQPage Schema
How do I build healthcare AI models for clinical tasks like mortality prediction?▼

You can build healthcare AI models for mortality prediction by defining data loading, task setup, and preprocessing pipelines to train and evaluate clinical predictions on datasets like MIMIC-IV.

Can I use a unified framework for both EHR data and physiological signals?▼

Yes, a unified framework supports modular pipelines for electronic health records, physiological signals, medical imaging, and clinical text across multiple healthcare AI workflows.

What's the best way to deploy interpretable models for drug recommendation?▼

Deploy interpretable drug recommendation models by applying specific algorithms like GAMENet and SafeDrug through end-to-end workflows spanning training, evaluation, and calibration.

Does this healthcare AI toolkit support MIMIC and eICU datasets for readmission prediction?▼

Yes, the toolkit supports MIMIC, eICU, and OMOP datasets, providing example pipelines to train and evaluate models for clinical readmission and length of stay prediction.

When do I need a clinical AI toolkit for medical imaging and clinical text transcription?▼

You need a clinical AI toolkit when processing multi-modal data, enabling end-to-end workflows for medical imaging analysis and clinical text transcription or coding tasks.

Are there limitations when applying machine learning to COVID-19 imaging and Sleep EEG datasets?▼

Limitations depend on dataset scale and modality, but the toolkit provides reference pipelines for COVID-19 imaging and Sleep EEG to standardize model development and evaluation workflows.

Related Skills

Explore More Education & Research Skills→
yf8578yf8578
1

pyhealth

Develop and evaluate healthcare machine learning models using clinical datasets.

Community
Advanced
brainworkupbrainworkup
1

pyhealth

Develop and deploy healthcare AI models on clinical datasets with PyHealth.

Community
Advanced
Yezez9Yezez9

pyhealth

Develop, test, and deploy healthcare machine learning models with clinical data.

Community
Advanced
youyinnnyouyinnn
1

pyhealth

Develop, test, and deploy healthcare machine learning models with clinical data.

Community
Advanced