pyhealth

Develop and test machine learning models for clinical data with pyhealth.

8|Updated Nov 19, 2025

Search Tags:#data processing #ehr #healthcare ai #clinical machine learning #medical prediction #medical coding

Ready to run

npx skills add https://github.com/sanand0/scientific-research --skill pyhealth-sanand0

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pyhealth
Source: https://github.com/sanand0/scientific-research/tree/main/.claude/skills/pyhealth
Command: npx skills add https://github.com/sanand0/scientific-research --skill pyhealth-sanand0

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the development, testing, and deployment of AI models for healthcare by providing specialized tools and datasets for clinical machine learning.

Core Features & Use Cases

Data Loading: Access and process diverse healthcare datasets (EHR, signals, imaging).
Clinical Prediction: Build models for tasks like mortality prediction, readmission risk, and drug recommendation.
Medical Coding: Translate between various medical coding systems (ICD, NDC, ATC).
Use Case: Predict patient mortality using the MIMIC-IV dataset by loading the data, defining the mortality prediction task, selecting a suitable model like Transformer, training it, and evaluating its performance.

Quick Start

Use the pyhealth skill to load the MIMIC-IV dataset and set up a mortality prediction task.

Frequently Asked Questions about pyhealth

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

FAQPage Schema

How do I build a clinical prediction model using MIMIC-IV EHR data?▼

To build a clinical prediction model with MIMIC-IV EHR data, load the dataset, define the prediction task like mortality or readmission risk, select a deep learning model such as a Transformer, train it, and evaluate its performance.

What healthcare prediction tasks can I implement with clinical machine learning?▼

Clinical machine learning supports implementing prediction tasks such as patient mortality prediction, readmission risk assessment, and drug recommendation using electronic health records and physiological signals.

Can I translate between different medical coding systems for EHR datasets?▼

Yes, you can translate between various medical coding systems including ICD, NDC, and ATC to standardize electronic health record datasets for downstream machine learning processing.

Does this toolkit support deep learning models for healthcare applications?▼

Yes, it supports implementing deep learning models for healthcare applications, enabling the development, testing, and deployment of machine learning models trained on diverse clinical data.

What's the best way to load diverse healthcare datasets for AI models?▼

The best way to load healthcare datasets is using the toolkit's data loading features to access and process diverse data types including EHR, physiological signals, and imaging for clinical machine learning.

Can I use physiological signals for medical prediction tasks?▼

Yes, you can use physiological signals alongside electronic health records to train machine learning models for various medical prediction tasks and clinical healthcare applications.