Jialin Liu1,2, Jinfa Wu3, Siru Liu4, Mengdie Li3, Kunchang Hu3, Ke Li3. 1. Information Center, West China Hospital, Sichuan University, Chengdu, Sichuan Province, China. 2. Department of Medical Informatics, West China Medical School, Chengdu, Sichuan Province, China. 3. School of Life Science & Technology, University of Electronic Science & Technology of China, Chengdu, Sichuan Province, China. 4. Department of Biomedical Informatics, University of Utah, Salt Lake City, UT, United States of America.
Abstract
PURPOSE: The goal of this study is to construct a mortality prediction model using the XGBoot (eXtreme Gradient Boosting) decision tree model for AKI (acute kidney injury) patients in the ICU (intensive care unit), and to compare its performance with that of three other machine learning models. METHODS: We used the eICU Collaborative Research Database (eICU-CRD) for model development and performance comparison. The prediction performance of the XGBoot model was compared with the other three machine learning models. These models included LR (logistic regression), SVM (support vector machines), and RF (random forest). In the model comparison, the AUROC (area under receiver operating curve), accuracy, precision, recall, and F1 score were used to evaluate the predictive performance of each model. RESULTS: A total of 7548 AKI patients were analyzed in this study. The overall in-hospital mortality of AKI patients was 16.35%. The best performing algorithm in this study was XGBoost with the highest AUROC (0.796, p < 0.01), F1(0.922, p < 0.01) and accuracy (0.860). The precision (0.860) and recall (0.994) of the XGBoost model rank second among the four models. CONCLUSION: XGBoot model had obvious advantages of performance compared to the other machine learning models. This will be helpful for risk identification and early intervention for AKI patients at risk of death.
PURPOSE: The goal of this study is to construct a mortality prediction model using the XGBoot (eXtreme Gradient Boosting) decision tree model for AKI (acute kidney injury) patients in the ICU (intensive care unit), and to compare its performance with that of three other machine learning models. METHODS: We used the eICU Collaborative Research Database (eICU-CRD) for model development and performance comparison. The prediction performance of the XGBoot model was compared with the other three machine learning models. These models included LR (logistic regression), SVM (support vector machines), and RF (random forest). In the model comparison, the AUROC (area under receiver operating curve), accuracy, precision, recall, and F1 score were used to evaluate the predictive performance of each model. RESULTS: A total of 7548 AKI patients were analyzed in this study. The overall in-hospital mortality of AKI patients was 16.35%. The best performing algorithm in this study was XGBoost with the highest AUROC (0.796, p < 0.01), F1(0.922, p < 0.01) and accuracy (0.860). The precision (0.860) and recall (0.994) of the XGBoost model rank second among the four models. CONCLUSION: XGBoot model had obvious advantages of performance compared to the other machine learning models. This will be helpful for risk identification and early intervention for AKI patients at risk of death.
Authors: Eric A J Hoste; John A Kellum; Nicholas M Selby; Alexander Zarbock; Paul M Palevsky; Sean M Bagshaw; Stuart L Goldstein; Jorge Cerdá; Lakhmir S Chawla Journal: Nat Rev Nephrol Date: 2018-10 Impact factor: 28.314
Authors: Sandra L Kane-Gill; Florentina E Sileanu; Raghavan Murugan; Gregory S Trietley; Steven M Handler; John A Kellum Journal: Am J Kidney Dis Date: 2014-12-06 Impact factor: 8.860
Authors: Anoop Mayampurath; L Nelson Sanchez-Pinto; Kyle A Carey; Laura-Ruth Venable; Matthew Churpek Journal: PLoS One Date: 2019-07-31 Impact factor: 3.240
Authors: Siru Liu; Kensaku Kawamoto; Guilherme Del Fiol; Charlene Weir; Daniel C Malone; Thomas J Reese; Keaton Morgan; David ElHalta; Samir Abdelrahman Journal: J Am Med Inform Assoc Date: 2022-04-13 Impact factor: 4.497
Authors: Eva María Mateo; José Vicente Gómez; Andrea Tarazona; María Ángeles García-Esparza; Fernando Mateo Journal: Toxins (Basel) Date: 2021-08-05 Impact factor: 4.546