Skip to content

Renal Health Prediction

Identifying acute kidney injury (AKI) patients at higher risk of requiring ITU, needing renal support (dialysis), or likely to have a higher potential for mortality.

diagram showing the renal health prediction workflow. At the top there are three boxes that say "electronic observations", "medication data", and "blood test results". All three boxes flow into a box that says "time series data builders (with missing data handling)", which flows into "Machine learning model". This then flows out into a box that says "Time series prediction of: no change, ITU bed, dialysis, Death. At least 24h in advance."

Renal Health Prediction was selected as a project in Spring 2022 following a successful pitch to the AI Skunkworks problem-sourcing programme.

Results

A proof-of-concept demonstrator written in Python (machine learning models, command line interface (CLI), Jupyter Notebooks).

Output Link
Open Source Code & Documentation Github
Technical report PDF
Pre-print (MedRxiv) PDF