Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

PyHealth Clinical ML Pipeline Assistant

Builds clinical prediction pipelines (mortality, readmission, drug recommendation, sleep staging) on EHR and signal datasets using PyHealth's standard 5-stage workflow.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 9/10Last updated: Aug 9, 2026

What it does

  • Writes minimal, idiomatic code following PyHealth's Dataset → Task → Model → Trainer → Metrics pipeline.
  • Helps pick the right dataset class: MIMIC-III/IV, eICU, OMOP-CDM, EHRShot, SleepEDF, SHHS, ISRUC, ChestX-ray14, TUEV/TUAB.
  • Matches tasks (mortality, readmission, length of stay, drug recommendation, sleep staging, ICD coding, EEG events) to models (Transformer, RETAIN, GAMENet, SafeDrug, MICRON, StageNet, AdaCare, CNN/RNN/MLP).
  • Looks up and cross-maps medical codes: ICD-9-CM, ICD-10-CM, ATC, NDC, RxNorm, CCS.
  • Prevents the classic mistakes: passing a BaseDataset instead of a SampleDataset, sample-level splits that leak patients, mismatched monitor metrics, MIMIC-IV's ehr_root= quirk, and missing cache_dir caching.

Who it's for

  • Healthcare ML engineers, clinical data scientists, and medical AI researchers.
  • Grad students who just got MIMIC access and need a first working model.
  • Not needed if you only want plain PyTorch on generic tabular data.

Example uses

  1. "Build a mortality prediction pipeline on synthetic MIMIC-III" → under-20-line train/eval script pointed at the public synthetic bucket, no credentialing required.
  2. "Train SafeDrug for drug recommendation on MIMIC-IV" → uses ehr_root=, multilabel metrics like jaccard_samples for checkpoint monitoring.
  3. "Map prescription NDC codes to ATC level 3" → cross-mapping snippet with pyhealth.medcode.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/pyhealth/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/pyhealth folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/pyhealth/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone --depth 1 https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/sas && mkdir -p ~/.claude/skills && cp -r /tmp/sas/skills/pyhealth ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and make sure the skills folder exists: mkdir -p ~/.claude/skills
  2. Clone the repository: git clone --depth 1 https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/sas
  3. Copy just this skill: cp -r /tmp/sas/skills/pyhealth ~/.claude/skills/
  4. Verify with ls ~/.claude/skills/pyhealth — you should see SKILL.md plus references/ and assets/.
  5. Restart Claude Code and try a prompt like "build a mortality prediction pipeline on MIMIC-III".
  6. Set up a runtime environment: uv init my-pyhealth-project && cd my-pyhealth-project && uv python pin 3.12 && uv add pyhealth
  7. Real MIMIC/eICU data needs credentialed PhysioNet access — start with the synthetic MIMIC-III bucket the skill recommends.
View source on GitHub ↗License: MIT