pyhealth
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).
Security Assessment
About pyhealth
The pyhealth skill provides a comprehensive toolkit designed specifically for healthcare AI applications, enabling users to develop, test, and deploy machine learning models that leverage clinical data. This skill addresses the challenges associated with working with electronic health records (EHR) and executing various clinical prediction tasks such as mortality prediction, readmission rates, and drug recommendations. By utilizing a modular approach, pyhealth streamlines the process of handling complex healthcare datasets, making it easier for healthcare professionals and data scientists to derive insights from clinical data.
FAQ
What types of datasets can I work with using pyhealth?
Pyhealth supports various healthcare datasets, including MIMIC-III, MIMIC-IV, eICU, and OMOP.
Is pyhealth compatible with deep learning models?
Yes, pyhealth includes support for deep learning models specifically tailored for healthcare applications.
What are the system requirements to run pyhealth?
Pyhealth requires a Python environment and is optimized for performance, being 3x faster than pandas for healthcare data processing.
Can I create custom clinical prediction tasks with pyhealth?
Yes, pyhealth allows users to apply predefined clinical prediction tasks or create custom tasks as needed.
Does pyhealth provide evaluation metrics for clinical models?
Yes, it includes features for evaluating clinical models, focusing on fairness metrics, calibration, interpretability, and uncertainty quantification.
Install pyhealth
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
davila7/claude-code-templates