kbressem/LongHealth
LongHealth: A Question Answering Benchmark with Long Clinical Documents
This project helps evaluate how well large language models (LLMs) can understand and extract information from very long medical documents. It takes in fictional patient cases, each thousands of words long, and provides 400 multiple-choice questions to test the LLM's ability to extract, negate, and sort clinical information. Healthcare AI researchers and developers would use this to assess and improve their models' performance on complex medical texts.
No commits in the last 6 months.
Use this if you are a researcher or developer focused on building and improving AI models for healthcare, specifically those that need to accurately interpret lengthy clinical notes.
Not ideal if you are looking for a tool for clinical decision-making or for training an LLM, as the data is fictional and solely for research evaluation.
Stars
28
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/kbressem/LongHealth"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Sam-Osian/PFD-toolkit
Analyse Prevention of Future Death (PFD) reports with AI
SmartFlowAI/EmoLLM
心理健康大模型 (LLM x Mental Health), Pre & Post-training & Dataset & Evaluation & Depoly & RAG, with...
AI-in-Health/MedLLMsPracticalGuide
[Nature Reviews Bioengineering🔥] Application of Large Language Models in Medicine. A curated...
Zlasejd/HuangDI
黄帝(Huang-Di)模型仓库，基于Ziya-LLaMA-13B-V1的中医古籍知识问答大模型。
mims-harvard/Madrigal
Madrigal: Multimodal AI predicts clinical outcomes of drug combinations from preclinical data