Predicting renal function recovery and short-term reversibility among acute kidney injury patients in the ICU: comparison of machine learning methods and conventional regression

Abstract

Background Acute kidney injury (AKI) is one of the most frequent complications of critical illness. We aimed to explore the predictors of renal function recovery and the short-term reversibility after AKI by comparing logistic regression with four machine learning models. Methods We reviewed patients who were diagnosed with AKI in the MIMIC-IV database between 2008 and 2019. Recovery from AKI within 72 h of the initiating event was typically recognized as the short-term reversal of AKI. Conventional logistic regression and four different machine algorithms (XGBoost algorithm model, Bayesian networks [BNs], random forest [RF] model, and support vector machine [SVM] model) were used to develop and validate prediction models. The performance measures were compared through the area under the receiver operating characteristic curve (AU-ROC), calibration curves, and 10-fold cross-validation. Results A total of 12,321 critically ill adult AKI patients were included in our analysis cohort. The renal function recovery rate after AKI was 67.9%. The maximum and minimum serum creatinine (SCr) within 24 h of AKI diagnosis, the minimum SCr within 24 and 12 h, and antibiotics usage duration were independently associated with renal function recovery after AKI. Among the 8364 recovered patients, the maximum SCr within 24 h of AKI diagnosis, the minimum Glasgow Coma Scale (GCS) score, the maximum blood urea nitrogen (BUN) within 24 h, vasopressin and vancomycin usage, and the maximum lactate within 24 h were the top six predictors for short-term reversibility of AKI. The RF model presented the best performance for predicting both renal functional recovery (AU-ROC [0.8295 ± 0.01]) and early recovery (AU-ROC [0.7683 ± 0.03]) compared with the conventional logistic regression model. Conclusions The maximum SCr within 24 h of AKI diagnosis was a common independent predictor of renal function recovery and the short-term reversibility of AKI. The RF machine learning algorithms showed a superior ability to predict the prognosis of AKI patients in the ICU compared with the traditional regression models. These models may prove to be clinically helpful and can assist clinicians in providing timely interventions, potentially leading to improved prognoses.

Development and validation of a nomogram for predicting in-hospital mortality of elderly patients with persistent sepsis-associated acute kidney injury in intensive care units: a retrospective cohort study using the MIMIC-IV database

“…All data used in this study were obtained from the Medical Information Mart for Intensive Care IV (MIMIC-IV V.1.0) database—a public-access database supported by the Department of Medicine at Beth Israel Deaconess Medical Center and the Computational Physiology Laboratory at MIT, which included full information of all patients admitted to the Beth Israel Deaconess Medical Center from 2008 to 2019 (last updated in March 2021). 15 This database is freely accessible to any qualified PhysioNet user. The database consists of details of more than 500 000 hospital admissions and 70 000 intensive care unit (ICU) admissions.…”

Advancing 90-day mortality and anastomotic leakage predictions after oesophagectomy for cancer using explainable AI (XAI)

“…This implies that AL can have other more influential risk factors not accounted for by our variables. Previous medical studies have also shown improved AI prediction models compared to logistic regression models [15, 16].…”

A clinical score to predict recovery in end-stage kidney disease due to acute kidney injury

“…Despite the use of administrative data to predict kidney recovery in our study, the performance of the models was fair, with AUC within 0.70. As a comparison, other studies using biomarkers to predict kidney recovery had AUC in the range of 0.66–0.79 [ 38–40 ], whereas studies using granular data from the electronic health record had AUC ranging between 0.73 and 0.83 [ 41 , 42 ].…”