wshi83/EhrAgent
[EMNLP'24] EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records
This project helps clinicians and medical researchers answer complex questions directly from Electronic Health Records (EHRs) using natural language, without needing a data engineer. You provide your medical question in plain English and access to patient EHR data. The system then generates and executes code to retrieve specific patient information or insights from the EHR tables, providing you with the relevant data.
127 stars. No commits in the last 6 months.
Use this if you are a clinician or researcher who needs to quickly extract detailed, specific information from large EHR datasets to answer complex clinical questions.
Not ideal if you need a simple report from a single data point, as this is designed for complex, multi-step data retrieval and reasoning.
Stars
127
Forks
19
Language
Python
License
—
Category
Last pushed
Dec 26, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/wshi83/EhrAgent"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.