Automate healthcare AI pipelines for EHR data with PyTorch models.
npx skills add https://github.com/JosephWoodall/noosphere --skill pyhealth-josephwoodall
Please help me install this Agent Skill. Skill: pyhealth Source: https://github.com/JosephWoodall/noosphere/tree/main/.agent/skills/pyhealth Command: npx skills add https://github.com/JosephWoodall/noosphere --skill pyhealth-josephwoodall
PyHealth accelerates end-to-end healthcare AI development by providing datasets, task definitions, models, training pipelines, evaluation metrics, and interpretability tools for clinical data.
Install the library, load a healthcare dataset (e.g., MIMIC4), set a mortality prediction task, and train a Transformer model to evaluate its performance.
High-intent search queries and answers about installing and using this skill.
Clinical prediction models using EHR datasets like MIMIC-IV are built by loading standardized event-patient-visit data, setting a predefined task such as mortality prediction, and training architectures like Transformer within an automated pipeline.
Yes, PyTorch is required for healthcare AI tasks like readmission and length of stay prediction, providing modular components for datasets, tasks, models, and trainer steps to ensure reproducible clinical ML pipelines.
Applying deep learning to physiological signals and medical imaging is best handled through an end-to-end healthcare AI toolkit that automates data loading, model training, evaluation, and interpretability for clinical data.
PyHealth supports model calibration and interpretability for clinical ML pipelines through built-in trainer modules, uncertainty quantification, evaluation metrics, and explanation tools designed for deployment readiness.
Predefined clinical prediction tasks available for OMOP and eICU datasets include 20+ options such as mortality prediction, readmission, length of stay, and drug recommendation, alongside easy custom task creation.
A Python 3.7+ environment with PyTorch installed is needed to run healthcare AI pipelines utilizing architectures like RETAIN, SafeDrug, GAMENet, and GNN for MIMIC and OMOP dataset processing.
Yezez9Develop, test, and deploy healthcare machine learning models with clinical data.
jimmc414Develop, train, and evaluate clinical prediction models on healthcare datasets.
JuanMS20Automate PyTorch training workflows with LightningModule and Trainer orchestration.
felixboehmTrain clinical prediction models on EHR datasets with pyhealth.
