Title of article :
Prediction of Acute Kidney Injury After Cardiac Surgery Using Interpretable Machine Learning
Author/Authors :
Ejmalian ، Azar Deptartment of Anesthesiology - Firoozgar Hospital - Iran University of Medical Sciences , Aghaei ، Atefe Faculty of Computer Science and Engineering - Shahid Beheshti University , Nabavi ، Shahabedin Faculty of Computer Science and Engineering - Shahid Beheshti University , Abedzadeh Darabad ، Maryam Anesthesiology Research Center - Shahid Beheshti University of Medical Sciences , Tajbakhsh ، Ardeshir Anesthesiology Research Center - Shahid Beheshti University of Medical Sciences , Abin ، Ahmad Ali Faculty of Computer Science and Engineering - Shahid Beheshti University , Ebrahimi Moghaddam ، Mohsen Faculty of Computer Science and Engineering - Shahid Beheshti University , Dabbagh ، Ali Anesthesiology Research Center - Shahid Beheshti University of Medical Sciences , Jahangirifard ، Alireza Lung Transplantation Research Center, National Research Institute of Tuberculosis and Lung Diseases - Shahid Beheshti University of Medical Sciences , Memary ، Elham Anesthesiology Research Center - Shahid Beheshti University of Medical Sciences , Sayyadi ، Shahram Anesthesiology Research Center - Shahid Beheshti University of Medical Sciences
From page :
1
To page :
14
Abstract :
Background: Acute kidney injury (AKI) is a complication that occurs for various reasons after surgery, especially cardiac surgery. This complication can lead to a prolonged treatment process, increased costs, and sometimes death. Prediction of postoperative AKI can help anesthesiologists to implement preventive and early treatment strategies to reduce the risk of AKI. Objectives: This study tries to predict postoperative AKI using interpretable machine learning models. Methods: For this study, the information of 1435 patients was collected from multiple centers. The gathered data are in six categories: demographic characteristics and type of surgery, past medical history (PMH), drug history (DH), laboratory information, anesthesia and surgery information, and postoperative variables. Machine learning methods, including support vector machine (SVM), multilayer perceptron (MLP), decision tree (DT), random forest (RF), logistic regression, XGBoost, and AdaBoost, were used to predict postoperative AKI. Local interpretable model-agnostic explanations (LIME) and the Shapley methods were then leveraged to check the interpretability of models. Results: Comparing the area under the curves (AUCs) obtained for different machine learning models show that the RF and XGBoost methods with values of 0.81 and 0.80 best predict postoperative AKI. The interpretations obtained for the machine learning models show that creatinine (Cr), cardiopulmonary bypass time (CPB time), blood sugar (BS), and albumin (Alb) have the most significant impact on predictions. Conclusions: The treatment team can be informed about the possibility of postoperative AKI before cardiac surgery using machine learning models such as RF and XGBoost and adjust the treatment procedure accordingly. Interpretability of predictions for each patient ensures the validity of obtained predictions.
Keywords :
Acute Kidney Injury , AKI Prediction , Cardiac Surgery , Interpretable Machine Learning
Journal title :
Anesthesiology and Pain Medicine
Journal title :
Anesthesiology and Pain Medicine
Record number :
2738302
Link To Document :
بازگشت