Convert raw clinical data and task specifications into model-ready healthcare AI inputs.
npx skills add https://github.com/ovachiever/droid-tings --skill pyhealth
Please help me install this Agent Skill. Skill: pyhealth Source: https://github.com/ovachiever/droid-tings/tree/main/skills/pyhealth Command: npx skills add https://github.com/ovachiever/droid-tings --skill pyhealth
PyHealth provides a modular, interoperable framework for healthcare AI, enabling loading of clinical data, task definitions, model selection, training, evaluation, and deployment-ready workflows.
Load an MIMIC-4 dataset, set a mortality task, split, train a model, and evaluate.
High-intent search queries and answers about installing and using this skill.
PyHealth translates raw clinical data from sources like MIMIC into model-ready inputs through standardized data loading, task definition, and feature preprocessing pipelines. It handles EHR processing, medical coding, physiological signals, and text data to produce consistent schemas ready for training.
Yes. PyHealth includes 20+ predefined clinical prediction tasks—mortality, readmission, length of stay, and drug recommendation—with 33+ models ranging from baselines to healthcare-specific architectures, plus built-in training, evaluation, and calibration tools.
PyHealth provides a rich dataset ecosystem including MIMIC-4, eICU, OMOP, Sleep EEG, medical imaging, and clinical text data. Each integrates directly into the framework's data loading pipeline for immediate task definition and model training.
PyHealth offers evaluation, calibration, and interpretability tools to assess model performance on clinical tasks. It outputs deployment-ready workflows with standardized schemas and thorough documentation for production integration.
No. PyHealth's modular framework unifies diverse data types—EHR, medical imaging, physiological signals, and clinical text—within a single interoperable pipeline, eliminating the need for separate preprocessing tools across data modalities.
yf8578Develop and evaluate healthcare machine learning models using clinical datasets.
sports-data-hqVerify model probability outputs and calibration error with reliability diagrams and Brier score analysis.
AlterLab-IEUConfigure PyHealth pipelines to build, train, and evaluate clinical prediction models.
HolobiomicsLabDevelop and deploy clinical machine learning models for EHR data.
