skills.rest
Estrella-231
Estrella-231COMMUNITY
Explore all skills by this author →
GitHub

pyhealth

Build clinical deep-learning pipelines with Dataset, Task, Model, Trainer, and Metrics.

Updated May 24, 2026
Search Tags:#ehr#mimic#pyhealth#clinical ml#drug recommendation#sleep staging#medical code mapping
One-click install
npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill pyhealth-estrella-231
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pyhealth
Source: https://github.com/Estrella-231/Mathematical_modeling_tongmeng/tree/main/.agents/skills/pyhealth
Command: npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill pyhealth-estrella-231

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

PyHealth turns messy clinical data work into a structured, reusable pipeline for training and evaluating healthcare deep-learning models.

Core Features & Use Cases

  • Unified clinical pipeline: Build end-to-end workflows using the Dataset → Task → Model → Trainer → Metrics pattern to avoid plumbing mistakes.
  • Multi-domain dataset support: Load EHR, physiological signals, and imaging datasets such as MIMIC-III/IV, eICU, OMOP, SleepEDF, SHHS/ISRUC, and ChestXray14.
  • Task-appropriate modeling: Train models for mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD/ATC coding, and EEG event prediction with task-matched monitor metrics.
  • Medical code utilities: Perform ICD/ATC/NDC/RxNorm lookups and cross-mapping (including cross-version mapping like ICD-9 ↔ ICD-10 and NDC → RxNorm) for feature engineering and interpretation.

Quick Start

Use the pyhealth skill to build a mortality prediction run on MIMIC-III by loading the dataset, setting a mortality task, choosing a Transformer model, training with Trainer, and reporting PR-AUC/ROC-AUC metrics.

Frequently Asked Questions about pyhealth

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

FAQPage Schema
How do I build a clinical ML pipeline for predicting patient mortality using MIMIC-III EHR data?▼

Build a clinical ML pipeline for MIMIC-III mortality prediction by loading the dataset, defining a mortality task, selecting a model, training with the Trainer, and evaluating PR-AUC and ROC-AUC metrics.

What healthcare deep-learning tasks are supported for EHR, signal, and imaging data?▼

Supported healthcare deep-learning tasks include mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG event prediction, and medical code cross-mapping for EHR, signal, and imaging datasets.

Can I map medical codes between ICD-9 and ICD-10 or convert NDC to RxNorm for feature engineering?▼

Medical code utilities support ICD, ATC, NDC, and RxNorm lookups, including cross-version mapping like ICD-9 to ICD-10 and NDC to RxNorm, to facilitate feature engineering and clinical interpretation.

What is the required pipeline structure for training deep-learning models on clinical datasets?▼

The required pipeline structure follows a Dataset, Task, Model, Trainer, and Metrics pattern, ensuring task-dataset compatibility, correct patient-level data splitting, and task-matched evaluation metrics.

Does this clinical ML workflow support physiological signal datasets like SleepEDF and SHHS for sleep staging?▼

Physiological signal datasets including SleepEDF, SHHS, and ISRUC are supported, enabling deep-learning workflows for sleep staging and EEG event prediction tasks.

Why does my clinical model training fail due to task and dataset compatibility issues?▼

Training fails when task and dataset compatibility is mismatched or patient-level splitting is incorrect; the unified Dataset to Metrics pipeline enforces proper task-dataset alignment to prevent these plumbing mistakes.

Related Skills

Explore More Data & Analytics Skills→
LeonChaoXLeonChaoX
783

pyhealth

Build healthcare AI models from electronic health records for clinical prediction tasks.

Community
Advanced
awslabsawslabs
13

hedis-measure-specification

Apply NCQA technical specifications to interpret HEDIS quality measures.

Official
Advanced
jackspacejackspace
16

scikit-learn

Build, evaluate, and deploy classical machine learning models with scikit-learn.

Community
Advanced
Yezez9Yezez9

pyhealth

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

Community
Advanced