Machine learning prediction of moderate‐to‐severe acute kidney injury after <scp>ICU</scp> admission and cardiac surgery with urine trace elements
ML models primarily based on urinary TE can identify AKI risk in both clinical groups (ICU and cardiac surgery), with LightGBM, RF and XGBoost serving as high-performance models for early prediction of stage 2-3 AKI.
Authors
- Mark A.J. Devonald (ORCID: https://orcid.org/0000-0003-2562-4365)
- David S. Gardner (ORCID: https://orcid.org/0000-0002-6490-2412)
- Ying X. Gue (ORCID: https://orcid.org/0000-0001-9994-8915)
- Yang Chen (ORCID: https://orcid.org/0000-0002-2808-6286)
- Gregory Y H Lip
Institutions
- University of Nottingham (GB)
- Medical University of Białystok (PL)
- University of Liverpool (GB)
- Aintree University Hospitals NHS Foundation Trust (GB)
- Liverpool Heart and Chest Hospital (GB)
- Aalborg University (DK)
Publication Details
- Journal
- European Journal of Clinical Investigation
- Published
- 2025-10-03
- DOI
- https://doi.org/10.1111/eci.70131
- Primary Topic
- Acute Kidney Injury Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Institute for Health and Care Research
- Department of Health and Social Care
- Invention for Innovation