Can I use this for medical code translation?

Yes, it features comprehensive mapping tools to translate between coding systems like ICD-9, ICD-10, NDC, RxNorm, and ATC.

Which clinical prediction tasks are predefined?

The skill includes 20+ predefined tasks such as mortality prediction, length of stay, 30-day readmission, and medication recommendation.

How does it handle clinical model evaluation?

It includes specialized metrics for clinical settings, including fairness assessments for bias, calibration for reliability, and uncertainty quantification.

What healthcare datasets does the pyhealth skill support?

It provides standardized interfaces for over 10 major datasets including MIMIC-III, MIMIC-IV, eICU, OMOP, and various EEG/ECG signal datasets.

Does it include healthcare-specific model architectures?

Yes, it implements specialized models like RETAIN for interpretability, SafeDrug for DDI-aware recommendation, and StageNet for EEG analysis.

PyHealth: Healthcare AI Toolkit

Name: PyHealth: Healthcare AI Toolkit
Author: Yezez9

byYezez9

0•

数据科学与机器学习

Develops, tests, and deploys clinical machine learning models using electronic health records and physiological data.

PyHealth is a comprehensive healthcare AI skill that streamlines the development of clinical prediction models through a modular 5-stage pipeline optimized for medical data. It provides specialized tools for processing electronic health records (EHR), translating complex medical coding systems like ICD and NDC, and implementing state-of-the-art architectures such as RETAIN and SafeDrug. Designed to be 3x faster than standard data processing methods, this skill enables developers to handle large-scale datasets like MIMIC-IV while ensuring clinical reliability through built-in fairness, calibration, and interpretability metrics.

主要功能

01Clinical evaluation tools for fairness, calibration, and uncertainty

02Medical coding translation between ICD-9/10, NDC, RxNorm, and ATC

030 GitHub stars

04Standardized access to 10+ healthcare datasets including MIMIC-IV and eICU

05Library of 33+ specialized healthcare and deep learning models

06Support for 20+ clinical tasks like mortality and readmission prediction

使用场景

01Predicting ICU patient mortality and hospital readmission risk

02Automating ICD coding from clinical notes and text

03Recommending safe medications while avoiding drug-drug interactions

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add yezez9/research-agent pyhealth

For use in Claude.ai and ChatGPT