JMIR Publications

ABSTRACT

Background:

Acute kidney injury (AKI) is a common complication in hospitalized elderly patients, associated with increased morbidity, mortality, and health care costs. Major adverse kidney events within 30 days (MAKE30), a composite of death, new renal replacement therapy (RRT), or persistent renal dysfunction (PRD), has been recommended as a patient-centered endpoint for clinical trials involving AKI. The study aimed to validate this endpoint and to establish a machine learning-based model to predict MAKE30 in hospitalized elderly patients with AKI.

Objective:

The study aimed to validate this endpoint and to establish a machine learning-based model to predict MAKE30 in hospitalized elderly patients with AKI.

Methods:

A total of 4,266 elderly patients (aged ≥ 65 years) with AKI admitted to the Second Xiangya Hospital of Central South University from January 1, 2015 to December 31, 2020 were included and randomly divided into a training set and an internal test set in a ratio of 7 to 3. An additional cohort of 11,864 eligible patients from the Medical Information Mart for Intensive Care Ⅳ database served as an external test set. The Boruta algorithm was used to select the most important predictor variables from 53 candidate variables. The eXtreme Gradient Boosting (XGBoost) algorithm was applied to establish a prediction model for MAKE30. Model discrimination was evaluated by the area under the receiver operating characteristic curve (AUROC). The SHapley Additive exPlanations (SHAP) method was used to interpret model predictions.

Results:

The overall incidence of MAKE30 in the two study cohorts was 28.3% and 26.7%, respectively. In patients alive at discharge, those with versus without new RRT or PRD had higher 30-day and 1-year mortality after discharge (log-rank P < 0.001). The model exhibited good predictive performance, with an AUROC of 0.868 (95% CI 0.852-0.881) in the training set and 0.823 (95% CI 0.798-0.846) in the internal test set. Its simplified version achieved an AUROC of 0.744 (95% CI 0.735-0.754) in the external test set. The SHAP method showed that the use of vasopressors, mechanical ventilation, blood urea nitrogen level, red blood cell distribution width-coefficient of variation, and serum albumin level were closely associated with MAKE30.

Conclusions:

MAKE30 is a common and promising endpoint in hospitalized elderly patients with AKI. The interpretable XGBoost model performs well in predicting MAKE30, which provides opportunities for risk stratification, clinical decision-making, and the conduct of clinical trials involving AKI.