skills.rest
jimmc414
jimmc414COMMUNITY
Explore all skills by this author →
𝕏@JimMcM4GitHub

pyhealth

Develop, train, and evaluate clinical prediction models on healthcare datasets.

557|98|Updated Nov 7, 2025
Search Tags:#machine learning#ehr#medical data#healthcare ai#clinical prediction#pyhealth
One-click install
npx skills add https://github.com/jimmc414/Kosmos --skill pyhealth-jimmc414
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pyhealth
Source: https://github.com/jimmc414/Kosmos/tree/main/kosmos-claude-scientific-skills/scientific-skills/pyhealth
Command: npx skills add https://github.com/jimmc414/Kosmos --skill pyhealth-jimmc414

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill empowers users to develop, test, and deploy machine learning models using complex clinical data, streamlining the process of extracting actionable insights from electronic health records and other healthcare datasets.

Core Features & Use Cases

  • Data Loading & Preprocessing: Access and prepare diverse healthcare datasets (MIMIC, eICU, OMOP) with specialized tools.
  • Model Development: Implement and train state-of-the-art models for clinical prediction tasks like mortality, readmission, and drug recommendation.
  • Interpretability & Calibration: Ensure models are reliable and understandable for clinical deployment.
  • Use Case: A researcher wants to predict hospital readmission risk for patients with diabetes. They can use this Skill to load MIMIC-IV data, train a Transformer model, and evaluate its performance using AUC-PR, while also assessing fairness across different demographic groups.

Quick Start

Use the pyhealth skill to train a Transformer model for mortality prediction on the MIMIC-IV dataset.

Frequently Asked Questions about pyhealth

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

FAQPage Schema
How do I train machine learning models for clinical prediction using MIMIC-IV data?▼

To train machine learning models for clinical prediction on MIMIC-IV data, you load the electronic health records, preprocess the dataset, implement deep learning architectures like Transformers, and evaluate performance using metrics such as AUC-PR.

What is the best way to predict hospital readmission risk from electronic health records?▼

Predicting hospital readmission risk from electronic health records involves loading clinical datasets, training a model like a Transformer for the specific prediction task, and evaluating the results while assessing fairness across different demographic groups.

Can I use deep learning architectures like Transformers and GNNs for healthcare AI tasks?▼

Yes, you can use deep learning architectures like Transformers and GNNs for healthcare AI tasks. The workflow supports implementing and training these state-of-the-art models for clinical predictions such as mortality and drug recommendation.

Does this approach support data preprocessing for standard healthcare data formats like OMOP and eICU?▼

Yes, this approach supports data preprocessing for standard healthcare data formats like OMOP and eICU. It provides specialized tools to access and prepare diverse healthcare datasets for end-to-end model development.

How do I ensure my clinical prediction models are reliable and interpretable for clinical deployment?▼

To ensure clinical prediction models are reliable and interpretable for clinical deployment, you apply provided tools for model calibration, uncertainty quantification, and interpretability during the evaluation phase of model development.

Related Skills

Explore More Data & Analytics Skills→
jaechang-hitsjaechang-hits
298

pyhealth

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

Community
Advanced
SologaSologa
1

pyhealth

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

Community
Advanced
ovachieverovachiever
52

scikit-learn

Implement, evaluate, and optimize scikit-learn machine learning models with pipelines.

Community
Intermediate
youyinnnyouyinnn
1

pyhealth

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

Community
Advanced