iheallab/apricotM

This repository contains the official code for the paper "Real-time prediction of intensive care unit patient acuity and therapy requirements using state-space modelling" (Nature Communications), which presents a deep learning framework for real-time patient acuity prediction using EHR data.

29
/ 100
Experimental

This project helps critical care teams predict real-time patient acuity and therapy needs in the ICU by analyzing electronic health record (EHR) data. You input a patient's historical EHR data, and it outputs continuous predictions of their stability and potential need for interventions. ICU clinicians, nurses, and hospital administrators can use this to anticipate changes in patient condition and allocate resources proactively.

No commits in the last 6 months.

Use this if you need to build or evaluate a system for real-time, continuous prediction of patient deterioration and therapy requirements within an Intensive Care Unit using historical EHR data.

Not ideal if you lack access to large, granular Electronic Health Record (EHR) datasets from ICU patients, or if your primary need is not real-time acuity prediction.

critical-care patient-monitoring EHR-analytics hospital-operations clinical-decision-support
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

16

Forks

3

Language

Python

License

Last pushed

Jul 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/iheallab/apricotM"

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