Development and validation of a novel risk-predicted model for early sepsis-associated acute kidney injury in critically ill patients: a retrospective cohort study.

Objectives: This study aimed to develop a prediction model for the detection of early sepsis-associated acute kidney injury (SA-AKI), which is defined as AKI diagnosed within 48 hours of a sepsis diagnosis.

Design: A retrospective study design was employed. It is not linked to a clinical trial. Data for patients with sepsis included in the development cohort were extracted from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. The least absolute shrinkage and selection operator regression method was used to screen the risk factors, and the final screened risk factors were constructed into four machine learning models to determine an optimal model. External validation was performed using another single-centre intensive care unit (ICU) database.

Setting: Data for the development cohort were obtained from the MIMIC-IV 2.0 database, which is a large publicly available database that contains information on patients admitted to the ICUs of Beth Israel Deaconess Medical Center in Boston, Massachusetts, USA, from 2008 to 2019. The external validation cohort was generated from a single-centre ICU database from China.

Participants: A total of 7179 critically ill patients with sepsis were included in the development cohort and 269 patients with sepsis were included in the external validation cohort.

Results: A total of 12 risk factors (age, weight, atrial fibrillation, chronic coronary syndrome, central venous pressure, urine output, temperature, lactate, pH, difference in alveolar-arterial oxygen pressure, prothrombin time and mechanical ventilation) were included in the final prediction model. The gradient boosting machine model showed the best performance, and the areas under the receiver operating characteristic curve of the model in the development cohort, internal validation cohort and external validation cohort were 0.794, 0.725 and 0.707, respectively. Additionally, to aid interpretation and clinical application, SHapley Additive exPlanations techniques and a web version calculation were applied.

Conclusions: This web-based clinical prediction model represents a reliable tool for predicting early SA-AKI in critically ill patients with sepsis. The model was externally validated using another ICU cohort and exhibited good predictive ability. Additional validation is needed to support the utility and implementation of this model.