Key result
A deep forest machine learning model incorporating 16 perioperative clinical features predicted acute kidney injury after cardiac surgery with an AUROC of 0.881.
Why the study?
Acute kidney injury is a major complication after cardiac surgery, but current diagnostic guidelines based on elevated serum creatinine or oliguria potentially delay its diagnosis.
Can machine learning models using electronic health record data accurately predict acute kidney injury after cardiac surgery?
Population
1457 adult patients who underwent cardiac surgery at Nanjing First Hospital
Design
Prediction model development and validation study
Authors
Loading...
May aid perioperative AKI risk stratification using EHR data; leaves open whether deployment improves outcomes in cardiac surgery.
Observational (n=1,457)
No
Can machine learning models using electronic health record data accurately predict acute kidney injury after cardiac surgery?
Effect estimate: AUROC 0.881 (95% CI 0.831-0.930)
Machine learning models, particularly Deep Forest, and a dynamic nomogram incorporating intraoperative features like central venous pressure, can accurately predict acute kidney injury after cardiac surgery.
Zhang et al. (2022) conducted an observational in Acute kidney injury after cardiac surgery (n=1,457). Machine learning prediction models (Deep Forest, Random Forest, XGBoost) was evaluated on Model discrimination for predicting acute kidney injury (AUROC) (AUROC 0.881, 95% CI 0.831-0.930). A deep forest machine learning model incorporating 16 perioperative clinical features predicted acute kidney injury after cardiac surgery with an AUROC of 0.881.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: