%0 Journal Article
%@ 1438-8871
%I JMIR Publications
%V 27
%N 
%P e62853
%T A Risk Prediction Model (CMC-AKIX) for Postoperative Acute Kidney Injury Using Machine Learning: Algorithm Development and Validation
%A Min,Ji Won
%A Min,Jae-Hong
%A Chang,Se-Hyun
%A Chung,Byung Ha
%A Koh,Eun Sil
%A Kim,Young Soo
%A Kim,Hyung Wook
%A Ban,Tae Hyun
%A Shin,Seok Joon
%A Choi,In Young
%A Yoon,Hye Eun
%+ Department of Internal Medicine, Incheon St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, 56, Dongsu-ro, Bupyeong-gu, Incheon, Seoul, 21431, Republic of Korea, 82 032 280 7370, berrynana@catholic.ac.kr
%K acute kidney injury
%K general surgery
%K deep neural networks
%K machine learning
%K prediction model
%K postoperative care
%K surgery
%K anesthesia
%K mortality
%K morbidity
%K retrospective study
%K cohort analysis
%K hospital
%K South Korea
%K logistic regression
%K user-friendly
%K patient care
%K risk management
%K artificial intelligence
%K digital health
%D 2025
%7 9.4.2025
%9 Original Paper
%J J Med Internet Res
%G English
%X Background: Postoperative acute kidney injury (AKI) is a significant risk associated with surgeries under general anesthesia, often leading to increased mortality and morbidity. Existing predictive models for postoperative AKI are usually limited to specific surgical areas or require external validation. Objective: We proposed to build a prediction model for postoperative AKI using several machine learning methods. Methods: We conducted a retrospective cohort analysis of noncardiac surgeries from 2009 to 2019 at seven university hospitals in South Korea. We evaluated six machine learning models: deep neural network, logistic regression, decision tree, random forest, light gradient boosting machine, and naïve Bayes for predicting postoperative AKI, defined as a significant increase in serum creatinine or the initiation of renal replacement therapy within 30 days after surgery. The performance of the models was analyzed using the area under the curve (AUC) of the receiver operating characteristic curve, accuracy, precision, sensitivity (recall), specificity, and F1-score. Results: Among the 239,267 surgeries analyzed, 7935 cases of postoperative AKI were identified. The models, using 38 preoperative predictors, showed that deep neural network (AUC=0.832), light gradient boosting machine (AUC=0.836), and logistic regression (AUC=0.825) demonstrated superior performance in predicting AKI risk. The deep neural network model was then developed into a user-friendly website for clinical use. Conclusions: Our study introduces a robust, high-performance AKI risk prediction system that is applicable in clinical settings using preoperative data. This model’s integration into a user-friendly website enhances its clinical utility, offering a significant step forward in personalized patient care and risk management. 
%R 10.2196/62853
%U https://www.jmir.org/2025/1/e62853
%U https://doi.org/10.2196/62853