Predicting In-Hospital Acute Kidney Injury after Cardiac Surgery Using Machine Learning

Kuroush Nezafati, Sreekanth Cheruku, Tingyi Wanyan, Donghan M. Yang, Qinbo Zhou, Michael E. Jessen, Javier A. Neyra, Xiaowei Zhan, Yang Xie, Amanda Fox,
Predicting In-Hospital Acute Kidney Injury after Cardiac Surgery Using Machine Learning,
Journal of Cardiothoracic and Vascular Anesthesia,
2025,
,
ISSN 1053-0770,
https://doi.org/10.1053/j.jvca.2025.09.045.
(https://www.sciencedirect.com/science/article/pii/S1053077025008146)
Abstract: Objective
We aimed to develop and evaluate cardiac surgery–associated acute kidney injury (CSA-AKI) machine learning prediction models that included clinical variables, biomarkers, and high-frequency hemodynamic measurements.
Design
A prospective, observational study.
Setting
A single-center university hospital.
Participants
Six hundred sixty-seven adult patients undergoing elective and urgent cardiac surgery between May 2015 and March 2023.
Measurements and Main Results
After excluding patients for clinical and administrative reasons and those with missing data, 602 patients were included in the predictive models. Random forest (RF) and long short-term memory (LSTM) models were trained on data from 492 patients, which included hemodynamic data from throughout the perioperative period, and BNP and [TIMP-2] × [IGFBP7] biomarkers. These models were evaluated in a test set of 110 patients to predict CSA-AKI, which was defined as a serum creatinine rise of 0.3 mg/dL in the first 48 hours after surgery or 1.5 times baseline creatinine between postoperative day 1 to day 7. The RF model achieved an AUC of 0.73 (0.72-0.74) and accuracy of 0.77 (0.76-0.79) on the test set. The RF model achieved a sensitivity and specificity of 0.59 (0.57-0.62) and 0.81 (0.79-0.84), respectively. The LSTM model achieved an AUC of 0.68 (0.67-0.70) and accuracy of 0.72 (0.69-0.74) on the test set. The sensitivity of the LSTM model was 0.60 (0.57-0.64), and the specificity was 0.74 (0.71-0.78).
Conclusions
We developed two machine learning models that incorporated perioperative biomarkers and hemodynamics as input data to predict CSA-AKI. The models exhibited competitive performance for prediction of the outcome and laid the foundation for further advancement in this critical area of research in kidney injury prevention.
Keywords: acute kidney injury; cardiac surgery; prediction; machine learning; TIMP-2; IGFBP7; BNP