Applicable Machine Learning Model for Predicting Contrast-induced Nephropathy Based on Pre-catheterization Variables
-
- Choi Heejung
- Department of Nephrology, Ajou University School of Medicine, Korea
-
- Choi Byungjin
- Department of Biomedical Informatics, Ajou University School of Medicine, Korea
-
- Han Sungdam
- Malgundam Internal Medicine Clinic, Korea
-
- Lee Minjeong
- Department of Nephrology, Ajou University School of Medicine, Korea
-
- Shin Gyu-Tae
- Department of Nephrology, Ajou University School of Medicine, Korea
-
- Kim Heungsoo
- Department of Nephrology, Ajou University School of Medicine, Korea
-
- Son Minkook
- Department of Physiology, College of Medicine, Dong-A University, Korea
-
- Kim Kyung-Hee
- Department of Cardiology, Cardiovascular Center, Incheon Sejong Hospital, Korea
-
- Kwon Joon-myoung
- Department of Critical Care and Emergency Medicine, Incheon Sejong Hospital, Korea Artificial Intelligence and Big Data Research Center, Sejong Medical Research Institute, Korea Medical Research Team, Medical AI, Korea
-
- Park Rae Woong
- Department of Biomedical Informatics, Ajou University School of Medicine, Korea Department of Biomedical Sciences, Ajou University Graduate School of Medicine, Korea
-
- Park Inwhee
- Department of Nephrology, Ajou University School of Medicine, Korea
抄録
<p>Objective Contrast agents used for radiological examinations are an important cause of acute kidney injury (AKI). We developed and validated a machine learning and clinical scoring prediction model to stratify the risk of contrast-induced nephropathy, considering the limitations of current classical and machine learning models. </p><p>Methods This retrospective study included 38,481 percutaneous coronary intervention cases from 23,703 patients in a tertiary hospital. We divided the cases into development and internal test sets (8:2). Using the development set, we trained a gradient boosting machine prediction model (complex model). We then developed a simple model using seven variables based on variable importance. We validated the performance of the models using an internal test set and tested them externally in two other hospitals. </p><p>Results The complex model had the best area under the receiver operating characteristic (AUROC) curve at 0.885 [95% confidence interval (CI) 0.876-0.894] in the internal test set and 0.837 (95% CI 0.819-0.854) and 0.850 (95% CI 0.781-0.918) in two different external validation sets. The simple model showed an AUROC of 0.795 (95% CI 0.781-0.808) in the internal test set and 0.766 (95% CI 0.744-0.789) and 0.782 (95% CI 0.687-0.877) in the two different external validation sets. This was higher than the value in the well-known scoring system (Mehran criteria, AUROC=0.67). The seven precatheterization variables selected for the simple model were age, known chronic kidney disease, hematocrit, troponin I, blood urea nitrogen, base excess, and N-terminal pro-brain natriuretic peptide. The simple model is available at http://52.78.230.235:8081/</p><p>Conclusions We developed an AKI prediction machine learning model with reliable performance. This can aid in bedside clinical decision making. </p>
収録刊行物
-
- Internal Medicine
-
Internal Medicine 63 (6), 773-780, 2024-03-15
一般社団法人 日本内科学会