skills.rest
K-Dense-AI
K-Dense-AIOFFICIAL
Explore all skills by this author →
Website𝕏@k_dense_aiGitHub

pyhealth

Train and evaluate clinical prediction models on EHR datasets.

33.0k|3.2k|Updated Oct 19, 2025
Search Tags:#ai#healthcare#datasets#model-training#clinical-prediction#training-evaluation
One-click install
npx skills add https://github.com/K-Dense-AI/scientific-agent-skills --skill pyhealth-k-dense-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pyhealth
Source: https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/scientific-skills/pyhealth
Command: npx skills add https://github.com/K-Dense-AI/scientific-agent-skills --skill pyhealth-k-dense-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

PyHealth unifies access to clinical datasets, reusable prediction tasks, model implementations, and evaluation tools, enabling researchers to rapidly build, test, and deploy healthcare AI workflows.

Core Features & Use Cases

  • Access 10+ healthcare datasets and 20+ prediction tasks with standardized interfaces.
  • Train and evaluate a wide range of models (baseline to transformer) for mortality, readmission, LOS, and drug recommendation.
  • Interpretability and deployment support with practical pipelines and documentation.

Quick Start

Load the MIMIC-IV dataset, set a mortality prediction task, and train a Transformer model to predict patient mortality.

Frequently Asked Questions about pyhealth

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

FAQPage Schema
How do I train clinical prediction models using EHR datasets?▼

To train clinical prediction models using EHR datasets, you can load standardized healthcare data, set a specific task like mortality prediction, and train models ranging from baselines to transformers using unified preprocessing and evaluation workflows.

What healthcare AI tasks can I evaluate with PyHealth?▼

You can evaluate over 20 healthcare AI tasks including mortality prediction, readmission, length of stay, and drug recommendation, using standardized interfaces across more than 10 supported EHR datasets.

Can I use transformer models for patient mortality prediction on MIMIC-IV data?▼

Yes, you can use transformer models for patient mortality prediction on MIMIC-IV data by loading the dataset, defining the mortality prediction task, and executing the provided training and evaluation pipeline.

Does this tool support model interpretability for clinical predictions?▼

Yes, the tool supports model interpretability for clinical predictions, providing deployment pipelines and documentation that help explain how models generate outcomes for healthcare applications.

What is the best way to preprocess complex clinical data for AI model training?▼

The best way to preprocess complex clinical data for AI model training is using standardized interfaces that transform raw EHR datasets into structured inputs for tasks like readmission and drug recommendation.

Are there limitations when deploying healthcare AI models for drug recommendation?▼

Limitations when deploying healthcare AI models for drug recommendation depend on dataset availability and task standardization, requiring careful evaluation of model outputs within the provided deployment pipeline.

Related Skills

Explore More Data & Analytics Skills→
SologaSologa
1

pyhealth

Develop, test, and deploy healthcare machine learning models with clinical data.

Community
Advanced
HolobiomicsLabHolobiomicsLab
4

pyhealth

Develop and deploy clinical machine learning models for EHR data.

Official
Advanced
brainworkupbrainworkup
1

pyhealth

Develop and deploy healthcare AI models on clinical datasets with PyHealth.

Community
Advanced
sparklingsparkling

flow-nexus-neural

Deploy, train, and manage neural networks with Flow Nexus.

Community
Advanced