Machine learning model for predicting oliguria in critically ill patients

Abstract

AbstractBackground: Oliguria is an important indicator for the early detection of acute kidney injury (AKI) and prediction of poor outcomes in critically ill patients; however, the accuracy of a prediction model using machine learning has rarely been investigated. This study aimed to develop and evaluate a machine learning algorithm for predicting oliguria in patients admitted to the intensive care unit (ICU). Methods: This retrospective cohort study used electronic health record data of consecutive patients admitted to the ICU between 2010 and 2019. Oliguria was defined as urine output of less than 0.5 mL/kg/h. We developed a machine learning model using a light-gradient boosting machine to predict oliguria between 6 to 72 h. The accuracy of the model was evaluated using receiver operating characteristic curves. We calculated the Shapley additive explanations (SHAP) value to identify important variables in the prediction model. Subgroup analyses were conducted to compare the accuracy of the models in predicting oliguria based on sex, age, and furosemide administration. Results: Among 9,241 patients in the study, the proportions of patients with urine output < 0.5 mL/kg/h for 6 h and those with AKI during the ICU stay were 27.4% and 30.2%, respectively. The area under the curve (AUC) of the prediction algorithm for the onset of oliguria at 6 h and 72 h using 50 clinically relevant variables was 0.966 (95% confidence interval [CI] 0.965–0.968) and 0.923 (95% CI 0.921–0.926), respectively. The SHAP analysis for predicting oliguria at 6 h identified urine-related values, severity scores, serum creatinine, interleukin-6, fibrinogen/fibrin degradation products, and vital signs as important variables. Subgroup analyses revealed that males had a higher AUC than did females (0.969 and 0.952, respectively), and the non-furosemide group had a higher AUC than did the furosemide group (0.971 and 0.957, respectively). Conclusions: The present study demonstrated that a machine learning algorithm could accurately predict oliguria onset in ICU patients, suggesting a potential role for oliguria in the early diagnosis and optimal management of AKI.