PMID- 37383697 OWN - NLM STAT- PubMed-not-MEDLINE LR - 20230703 IS - 2297-055X (Print) IS - 2297-055X (Electronic) IS - 2297-055X (Linking) VI - 10 DP - 2023 TI - Identification of risk factors for infection after mitral valve surgery through machine learning approaches. PG - 1050698 LID - 10.3389/fcvm.2023.1050698 [doi] LID - 1050698 AB - BACKGROUND: Selecting features related to postoperative infection following cardiac surgery was highly valuable for effective intervention. We used machine learning methods to identify critical perioperative infection-related variables after mitral valve surgery and construct a prediction model. METHODS: Participants comprised 1223 patients who underwent cardiac valvular surgery at eight large centers in China. The ninety-one demographic and perioperative parameters were collected. Random forest (RF) and least absolute shrinkage and selection operator (LASSO) techniques were used to identify postoperative infection-related variables; the Venn diagram determined overlapping variables. The following ML methods: random forest (RF), extreme gradient boosting (XGBoost), Support Vector Machine (SVM), Gradient Boosting Decision Tree (GBDT), AdaBoost, Naive Bayesian (NB), Logistic Regression (LogicR), Neural Networks (nnet) and artificial neural network (ANN) were developed to construct the models. We constructed receiver operating characteristic (ROC) curves and the area under the ROC curve (AUC) was calculated to evaluate model performance. RESULTS: We identified 47 and 35 variables with RF and LASSO, respectively. Twenty-one overlapping variables were finally selected for model construction: age, weight, hospital stay, total red blood cell (RBC) and total fresh frozen plasma (FFP) transfusions, New York Heart Association (NYHA) class, preoperative creatinine, left ventricular ejection fraction (LVEF), RBC count, platelet (PLT) count, prothrombin time, intraoperative autologous blood, total output, total input, aortic cross-clamp (ACC) time, postoperative white blood cell (WBC) count, aspartate aminotransferase (AST), alanine aminotransferase (ALT), PLT count, hemoglobin (Hb), and LVEF. The prediction models for infection after mitral valve surgery were established based on these variables, and they all showed excellent discrimination performance in the test set (AUC > 0.79). CONCLUSIONS: Key features selected by machine learning methods can accurately predict infection after mitral valve surgery, guiding physicians in taking appropriate preventive measures and diminishing the infection risk. CI - (c) 2023 Zhang, Fan, Ji, Ma, Wu, Huang, Wang, Gui, Chen, Zhang, Zhang, Zhang, Gong and Wang. FAU - Zhang, Ningjie AU - Zhang N AD - Department of Blood Transfusion, The Second Xiangya Hospital, Central South University, Changsha, China. FAU - Fan, Kexin AU - Fan K AD - Department of Laboratory Medicine, The Second Xiangya Hospital, Central South University, Changsha, China. FAU - Ji, Hongwen AU - Ji H AD - Department of Anesthesiology, Fuwai Hospital National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing, China. FAU - Ma, Xianjun AU - Ma X AD - Department of Blood Transfusion, Qilu Hospital of Shandong University, Jinan, China. FAU - Wu, Jingyi AU - Wu J AD - Department of Transfusion, Xiamen Cardiovascular Hospital Xiamen University, Xiamen, China. FAU - Huang, Yuanshuai AU - Huang Y AD - Department of Transfusion, The Affiliated Hospital of Southwest Medical University, Luzhou, China. FAU - Wang, Xinhua AU - Wang X AD - Department of Transfusion, Beijing Aerospace General Hospital, Beijing, China. FAU - Gui, Rong AU - Gui R AD - Department of Transfusion, The Third Xiangya Hospital, Central South University, Changsha, China. FAU - Chen, Bingyu AU - Chen B AD - Department of Transfusion, Zhejiang Provincial People's Hospital, Hangzhou, China. FAU - Zhang, Hui AU - Zhang H AD - Department of Basic Medical Sciences, Changsha Medical University, Changsha, China. FAU - Zhang, Zugui AU - Zhang Z AD - Institute for Research on Equity and Community Health, Christiana Care Health System, Newark, DE, United States. FAU - Zhang, Xiufeng AU - Zhang X AD - Department of Respiratory Medicine, Second Affiliated Hospital of Hainan Medical University, Haikou, China. FAU - Gong, Zheng AU - Gong Z AD - Sino-Cellbiomed Institutes of Medical Cell & Pharmaceutical Proteins Qingdao University, Qingdao, Shandong, China. AD - Department of Basic Medicine, Xiangnan University, Chenzhou, China. FAU - Wang, Yongjun AU - Wang Y AD - Department of Blood Transfusion, The Second Xiangya Hospital, Central South University, Changsha, China. LA - eng PT - Journal Article DEP - 20230613 PL - Switzerland TA - Front Cardiovasc Med JT - Frontiers in cardiovascular medicine JID - 101653388 PMC - PMC10294678 OTO - NOTNLM OT - LASSO OT - artificial network OT - cardiac valvular surgery OT - infection OT - machine learning OT - random forest COIS- The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. EDAT- 2023/06/29 13:42 MHDA- 2023/06/29 13:43 PMCR- 2023/01/01 CRDT- 2023/06/29 11:55 PHST- 2022/09/22 00:00 [received] PHST- 2023/05/31 00:00 [accepted] PHST- 2023/06/29 13:43 [medline] PHST- 2023/06/29 13:42 [pubmed] PHST- 2023/06/29 11:55 [entrez] PHST- 2023/01/01 00:00 [pmc-release] AID - 10.3389/fcvm.2023.1050698 [doi] PST - epublish SO - Front Cardiovasc Med. 2023 Jun 13;10:1050698. doi: 10.3389/fcvm.2023.1050698. eCollection 2023.