skills.rest
tassiovale
tassiovaleCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

pyhealth

Build clinical deep-learning pipelines for EHR, signal, and imaging datasets.

13|3|Updated Jun 10, 2026
Search Tags:#neural networks#healthcare AI#electronic health records#clinical deep learning#PyHealth#machine learning pipeline
One-click install
npx skills add https://github.com/tassiovale/claude-code-kit --skill pyhealth-tassiovale
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pyhealth
Source: https://github.com/tassiovale/claude-code-kit/tree/main/skills/pyhealth
Command: npx skills add https://github.com/tassiovale/claude-code-kit --skill pyhealth-tassiovale

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyhealth, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill addresses the challenge of building and using complex clinical/healthcare deep-learning pipelines, offering a comprehensive toolkit for data loading, task definition, model instantiation, training, and evaluation.

Core Features & Use Cases

  • Unified Pipeline: Offers a 5-stage pipeline (Dataset → Task → Model → Trainer → Metrics) for consistent and scalable workflows.
  • Data Loading: Supports loading EHR/signal/imaging datasets like MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot.
  • Task Definition: Allows defining tasks such as mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events.
  • Model Instantiation: Provides models like Transformer, RETAIN, GAMENet, SafeDrug, MICRON, StageNet, AdaCare, CNN/RNN/MLP.
  • Training and Evaluation: Facilitates training with the PyHealth Trainer and computing clinical metrics.
  • Use Case: For instance, building a pipeline for predicting mortality in hospital patients using MIMIC-III data.

Quick Start

Use the pyhealth skill to create a clinical prediction model for mortality using MIMIC-III data.

Frequently Asked Questions about pyhealth

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

FAQPage Schema
How do I build a deep learning pipeline for electronic health records?▼

To build a deep learning pipeline for electronic health records, you can use a 5-stage workflow covering Dataset, Task, Model, Trainer, and Metrics. This pipeline supports datasets like MIMIC-III, eICU, and OMOP for clinical predictions.

What clinical prediction tasks can I train machine learning models for?▼

You can train machine learning models for clinical prediction tasks including mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, and EEG event detection using supported healthcare datasets.

Can I use PyTorch to train healthcare AI models on physiological signals?▼

Yes, you can use PyTorch to train healthcare AI models on physiological signals. The toolkit supports loading physiological signal datasets like SleepEDF and training models such as CNN, RNN, Transformer, and MLP for signal analysis.

What Python version is required for clinical deep learning pipelines?▼

Python 3.12 or 3.13 is required to build clinical deep learning pipelines. You also need PyTorch and related libraries installed to support the data loading, model instantiation, and training processes.

How do I evaluate clinical deep learning models after training?▼

To evaluate clinical deep learning models after training, you use the integrated Trainer and Metrics stages. This setup facilitates training on healthcare datasets and computing specific clinical metrics to assess model performance.

Which models are available for medical imaging deep learning workflows?▼

For medical imaging deep learning workflows, available models include Transformer, RETAIN, GAMENet, SafeDrug, MICRON, StageNet, AdaCare, CNN, RNN, and MLP. These support imaging datasets like ChestXray14.

Related Skills

Explore More Data & Analytics Skills→
Lord1EgyptLord1Egypt
2

pyhealth

Build clinical deep-learning pipelines for electronic health records and physiological signals.

Community
Advanced
felixboehmfelixboehm

pyhealth

Train clinical prediction models on EHR datasets with pyhealth.

Community
Advanced
jaechang-hitsjaechang-hits
298

pyhealth

Load EHR data from MIMIC-III/IV and OMOP-CDM for ML model training.

Community
Advanced
Zeyuyang-0420Zeyuyang-0420

pyhealth

Automate 5-stage clinical deep learning pipelines with PyHealth and PyTorch.

Community
Advanced