skills.rest
Zeyuyang-0420
Zeyuyang-0420COMMUNITY
Explore all skills by this author →
GitHub

pyhealth

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

Updated May 8, 2026
Search Tags:#deep learning#pipeline#healthcare#clinical#PyHealth
One-click install
npx skills add https://github.com/Zeyuyang-0420/bio-ai-research-skills --skill pyhealth-zeyuyang-0420
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pyhealth
Source: https://github.com/Zeyuyang-0420/bio-ai-research-skills/tree/main/categories/clinical-biomedical-ai/pyhealth
Command: npx skills add https://github.com/Zeyuyang-0420/bio-ai-research-skills --skill pyhealth-zeyuyang-0420

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the complexity and manual work involved in building clinical healthcare deep learning pipelines, offering a streamlined approach for data loading, task definition, model instantiation, and training with the PyHealth library.

Core Features & Use Cases

  • Unified Pipeline: Automates the 5-stage pipeline (Dataset → Task → Model → Trainer → Metrics) for clinical data analysis.
  • Data Handling: Supports a wide range of healthcare datasets, including EHRs, physiological signals, and medical imaging.
  • Model Training: Provides various models for specific tasks such as mortality prediction, readmission prediction, and drug recommendation.
  • Use Case: Imagine you are a healthcare researcher working on predicting patient mortality. This Skill can help you load MIMIC-III data, define the mortality prediction task, instantiate a Transformer model, and train the model with PyHealth's Trainer.

Quick Start

Load the MIMIC-III dataset and predict mortality with PyHealth by running the following command: python train.py

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 healthcare deep learning pipeline for MIMIC-III data?▼

To build a clinical healthcare deep learning pipeline, this Skill automates a 5-stage workflow covering Dataset, Task, Model, Trainer, and Metrics management for processing MIMIC-III data using PyHealth and PyTorch.

What healthcare prediction tasks can I train models for using PyHealth?▼

You can train deep learning models for specific clinical tasks such as patient mortality prediction, readmission prediction, and drug recommendation using structured healthcare datasets like EHRs.

Do I need PyTorch to manage clinical datasets and train healthcare models?▼

Yes, you need PyTorch installed because the Skill requires both PyHealth and PyTorch to process clinical datasets, instantiate models like Transformers, and execute training workflows.

What types of clinical data are supported for deep learning workflows?▼

Supported clinical data types include electronic health records (EHRs), physiological signals, and medical imaging, which are loaded and defined through the pipeline's Dataset and Task stages.

How does the 5-stage pipeline handle model training and evaluation?▼

The 5-stage pipeline handles model training and evaluation by sequentially managing Dataset loading, Task definition, Model instantiation, Trainer execution, and Metrics calculation to streamline clinical ML workflows.

Related Skills

Explore More Data & Analytics Skills→
sanand0sanand0
8

pyhealth

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

Community
Advanced
SciMate-AISciMate-AI
1

pyhealth

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

Official
Advanced
tassiovaletassiovale
13

pyhealth

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

Community
Advanced
HolobiomicsLabHolobiomicsLab
4

pyhealth

Develop and deploy clinical machine learning models for EHR data.

Official
Advanced