canyuchen/ClinicalBench

Code for the paper "ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?"

42
/ 100
Emerging

This project offers a benchmark for clinicians and healthcare researchers to evaluate how well different large language models (LLMs) perform compared to traditional machine learning methods for crucial clinical predictions. You can input de-identified patient data from Electronic Health Records (EHR) to predict outcomes like hospital length-of-stay, mortality, or readmission. It's designed for medical professionals, data scientists in healthcare, or researchers who need to make informed decisions about adopting AI for clinical tasks.

No commits in the last 6 months.

Use this if you need to compare the predictive accuracy of LLMs versus established machine learning models for clinical outcomes using real-world patient data.

Not ideal if you are looking for a tool to develop new LLMs or traditional ML models for clinical prediction, rather than benchmark existing ones.

clinical prediction healthcare analytics hospital operations medical research patient outcome forecasting
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

31

Forks

9

Language

Python

License

MIT

Last pushed

Jun 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/canyuchen/ClinicalBench"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.