Machine learning modeling for the risk of acute kidney injury in inpatients receiving amikacin and etimicin

Pei Zhang¹Qiong Chen²Jiahui Lao³Juan Shi⁴Jia Cao³Xiao Li^1*Xin Huang¹

• ¹The First Affiliated Hospital of Shandong First Medical University, Shandong Provincial Qianfoshan Hospital, Jinan, China
• ²Department of Dermatology, The First People’s Hospital of Jinan, Jinan, China
• ³Center for Big Data Research in Health and Medicine, The First Affilated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan, Shandong Province, China
• ⁴Department of Clinical Pharmacy, The First People's Hospital of Jinan, Jinan, China

Background: Acute kidney injury (AKI) is a significant concern among hospitalized patients receiving aminoglycosides. Identifying the risk factors associated with aminoglycoside-induced AKI and developing machine learning models are imperative in clinical practice. Objective: This study aims to identify the risk factors associated with AKI in hospitalized patients receiving aminoglycosides, and develop machine learning models for evaluation of the AKI risk in these patients. Methods: This study retrospectively analyzed 7028 hospitalized patients who received treatment with amikacin or etimicin between 2018 and 2020. According to the type of medication used, patients were divided into amikacin group (n=307) and etimicin group (n=6901). Univariate analyses and the least absolute shrinkage and selection operator algorithm were used to screen risk factors and construct the model. The machine learning models were developed using five different algorithms, including logistic regression (LR), random forest (RF), gradient boosting machine (GBM), extreme gradient boosting model (XGBoost), and light gradient boosting machine (Light GBM). Results: The XGBoost model exhibited the most superior performance in predicting amikacin-associated AKI among the developed machine learning models. For the training set, the area under the receiver-operator characteristic curve (AUC) was 0.916, and for the test set, it was 0.841. The model can be accessed online. Regarding AKI risk in etimicin-treated patients, the GBM model demonstrated the best overall performance, with AUC values of 0.886 for the training set and 0.900 for the test set. The model was also made available online.Conclusions: These predictive models may offer a valuable tool for estimating the risk of AKI in patients receiving amikacin or etimicin, facilitating clinical decision-making and aiding in the prevention of AKI.