justin13601/ACES
[ICLR 2025] ACES: Automatic Cohort Extraction System for Event-Streams
This tool helps researchers and clinicians easily find specific groups of patients from large medical records, like Electronic Health Records (EHR). You provide your patient event data and a simple definition of the group you're looking for (e.g., 'patients with diabetes who had a heart attack between age 40-50'). It then outputs a list of patients who meet those exact criteria, along with details like event timestamps. This is ideal for medical researchers, epidemiologists, and clinical trial designers.
Use this if you need to quickly and precisely identify patient cohorts for studies, model training, or retrospective analyses without writing complex code.
Not ideal if your data is not event-stream based or not structured, as it requires specific data formats like Medical Event Data Standard (MEDS) or EventStreamGPT.
Stars
40
Forks
5
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/justin13601/ACES"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
rvandewater/YAIB
🧪Yet Another ICU Benchmark: a holistic framework for the standardization of clinical prediction...
YerevaNN/mimic3-benchmarks
Python suite to construct benchmark machine learning datasets from the MIMIC-III 💊 clinical database.
myADLM/ADLM-2025-Data-Challenge
Build an AI Tool for Extracting Information from Laboratory Documentation
cconsta1/SexEst
SexEst is an open-source Streamlit web application for predicting biological sex from skeletal...
Mubarraqqq/gnn-challenge
This project focuses on predicting maternal-fetal health outcomes, specifically early detection...