Prediction of acute kidney injury after cardiac surgery: model development using a Chinese electronic health record dataset

Abstract

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.

Derivation and Validation a Risk Model for Acute Kidney Injury and Subsequent Adverse Events After Cardiac Surgery: A Multicenter Cohort Study

“…Given that the occurrence of AKI is a dynamic process and is particularly affected by procedurerelated factors, we suggest that all preoperative, intraoperative, and early postoperative parameters should be screened for assessment during model derivation. 26 Taken together, these data indicated that the study end point, race, and sample source are still pivotal factors and different models may be more suitable to apply to local populations.…”

Construction and validation of a nomogram for predicting survival in elderly patients with cardiac surgery

“…Creatinine is a typical indicator of kidney injury in the clinic that has been linked to various other diseases ( 28 ). Acute kidney injury is one of the most common and serious complications of cardiac surgery, and it can substantially impact the morbidity and mortality of patients ( 29 , 30 ). Cardiac surgery-associated acute kidney injury has a complicated pathogenesis, mainly involving inflammatory response, ischemia-reperfusion injury, metabolic disorder, and oxidative stress.…”

Diagnosis, pathophysiology and preventive strategies for cardiac surgery-associated acute kidney injury: a narrative review

“…Several risk scores based on these factors have been developed (Table 3 ). After the introduction of traditional clinical scores [ 40 – 43 ], new scores have applied various methods to improve predictive performance, such as adding biomarkers [ 44 , 45 ], laboratory test-based [ 46 , 47 ], and using machine learning technology [ 48 ] to build predictive models. These scores have been reported with diagnostic accuracy in the range of 70–85%.…”