What datasets does PyHealth support?

PyHealth supports 10+ major healthcare datasets, including MIMIC-III, MIMIC-IV, eICU, OMOP, and various physiological signal datasets like SleepEDF.

Does PyHealth provide healthcare-specific deep learning models?

Yes, it includes specialized architectures such as RETAIN for interpretability, SafeDrug for medication safety, and StageNet for clinical sequence modeling.

Which clinical tasks can I implement with this skill?

You can implement mortality prediction, length of stay, readmission, drug recommendation, and signal-based tasks like sleep staging or seizure detection.

Is PyHealth optimized for large-scale clinical data?

PyHealth's data processing pipeline is designed for performance, operating up to 3x faster than standard pandas for specific healthcare data processing tasks.

Can I use PyHealth for medical code translation?

Yes, it includes specialized tools like CrossMap and InnerMap for mapping and translating between coding systems like ICD-9/10, NDC, RxNorm, and ATC.

PyHealth AI Toolkit

Name: PyHealth AI Toolkit
Author: youyinnn

byyouyinnn

0•

数据科学与机器学习

Builds, tests, and deploys healthcare AI models using clinical datasets and specialized medical coding systems.

PyHealth is a comprehensive Python library designed for healthcare AI, offering a modular 5-stage pipeline for clinical machine learning. It streamlines the development process by providing standardized interfaces for over 10 major healthcare datasets like MIMIC-IV, support for 33+ specialized models, and utilities for medical code translation across ICD, NDC, and ATC systems. This skill provides domain-specific guidance for predicting patient outcomes, recommending medications, and analyzing physiological signals while ensuring clinical interpretability and fairness.

主要功能

01Cross-system translation between medical codes like ICD, NDC, RxNorm, and ATC.

02Library of 33+ specialized models including RETAIN, SafeDrug, and StageNet.

030 GitHub stars

04Predefined clinical tasks for mortality, readmission, and medication recommendation.

05Advanced clinical evaluation metrics for fairness, calibration, and uncertainty.

06Standardized loading for 10+ healthcare datasets including MIMIC-IV, eICU, and OMOP.

使用场景

01Predicting ICU patient mortality and 30-day hospital readmission risks.

02Recommending medications while minimizing drug-drug interaction (DDI) risks.

03Classifying sleep stages and detecting seizures from EEG/ECG signal data.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add youyinnn/skills-collection pyhealth

For use in Claude.ai and ChatGPT

主要功能

01Cross-system translation between medical codes like ICD, NDC, RxNorm, and ATC.

02Library of 33+ specialized models including RETAIN, SafeDrug, and StageNet.

030 GitHub stars

04Predefined clinical tasks for mortality, readmission, and medication recommendation.

05Advanced clinical evaluation metrics for fairness, calibration, and uncertainty.

06Standardized loading for 10+ healthcare datasets including MIMIC-IV, eICU, and OMOP.

使用场景

01Predicting ICU patient mortality and 30-day hospital readmission risks.

02Recommending medications while minimizing drug-drug interaction (DDI) risks.

03Classifying sleep stages and detecting seizures from EEG/ECG signal data.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add youyinnn/skills-collection pyhealth

For use in Claude.ai and ChatGPT