A deep forest machine learning model incorporating 16 perioperative clinical features predicted acute kidney injury after cardiac surgery with an AUROC of 0.881.
Observational (n=1,457)
No
Can machine learning models using electronic health record data accurately predict acute kidney injury after cardiac surgery?
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.
Effect estimate: AUROC 0.881 (95% CI 0.831-0.930)
BACKGROUND: Acute kidney injury (AKI) is a major complication following cardiac surgery that substantially increases morbidity and mortality. Current diagnostic guidelines based on elevated serum creatinine and/or the presence of oliguria potentially delay its diagnosis. We presented a series of models for predicting AKI after cardiac surgery based on electronic health record data. METHODS: We enrolled 1457 adult patients who underwent cardiac surgery at Nanjing First Hospital from January 2017 to June 2019. 193 clinical features, including demographic characteristics, comorbidities and hospital evaluation, laboratory test, medication, and surgical information, were available for each patient. The number of important variables was determined using the sliding windows sequential forward feature selection technique (SWSFS). The following model development methods were introduced: extreme gradient boosting (XGBoost), random forest (RF), deep forest (DF), and logistic regression. Model performance was accessed using the area under the receiver operating characteristic curve (AUROC). We additionally applied SHapley Additive exPlanation (SHAP) values to explain the RF model. AKI was defined according to Kidney Disease Improving Global Outcomes guidelines. RESULTS: In the discovery set, SWSFS identified 16 important variables. The top 5 variables in the RF importance matrix plot were central venous pressure, intraoperative urine output, hemoglobin, serum potassium, and lactic dehydrogenase. In the validation set, the DF model exhibited the highest AUROC (0.881, 95% confidence interval CI 0.831-0.930), followed by RF (0.872, 95% CI 0.820-0.923) and XGBoost (0.857, 95% CI 0.802-0.912). A nomogram model was constructed based on intraoperative longitudinal features, achieving an AUROC of 0.824 (95% CI 0.763-0.885) in the validation set. The SHAP values successfully illustrated the positive or negative contribution of the 16 variables attributed to the output of the RF model and the individual variable's effect on model prediction. CONCLUSIONS: Our study identified 16 important predictors and provided a series of prediction models to enhance risk stratification of AKI after cardiac surgery. These novel predictors might aid in choosing proper preventive and therapeutic strategies in the perioperative management of AKI patients.
Zhang et al. (Sat,) conducted a 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.