Identification of risk factors for infection after mitral valve surgery through machine learning approaches
BackgroundSelecting 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.Method...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Cardiovascular Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcvm.2023.1050698/full |
| _version_ | 1797805788981362688 |
|---|---|
| author | Ningjie Zhang Kexin Fan Hongwen Ji Xianjun Ma Jingyi Wu Yuanshuai Huang Xinhua Wang Rong Gui Bingyu Chen Hui Zhang Zugui Zhang Xiufeng Zhang Zheng Gong Zheng Gong Yongjun Wang |
| author_facet | Ningjie Zhang Kexin Fan Hongwen Ji Xianjun Ma Jingyi Wu Yuanshuai Huang Xinhua Wang Rong Gui Bingyu Chen Hui Zhang Zugui Zhang Xiufeng Zhang Zheng Gong Zheng Gong Yongjun Wang |
| author_sort | Ningjie Zhang |
| collection | DOAJ |
| description | BackgroundSelecting 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.MethodsParticipants 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.ResultsWe 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).ConclusionsKey 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. |
| first_indexed | 2024-03-13T05:57:22Z |
| format | Article |
| id | doaj.art-d163bf7e81bb4f119265c6aed752d33e |
| institution | Directory Open Access Journal |
| issn | 2297-055X |
| language | English |
| last_indexed | 2024-03-13T05:57:22Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cardiovascular Medicine |
| spelling | doaj.art-d163bf7e81bb4f119265c6aed752d33e2023-06-13T04:37:43ZengFrontiers Media S.A.Frontiers in Cardiovascular Medicine2297-055X2023-06-011010.3389/fcvm.2023.10506981050698Identification of risk factors for infection after mitral valve surgery through machine learning approachesNingjie Zhang0Kexin Fan1Hongwen Ji2Xianjun Ma3Jingyi Wu4Yuanshuai Huang5Xinhua Wang6Rong Gui7Bingyu Chen8Hui Zhang9Zugui Zhang10Xiufeng Zhang11Zheng Gong12Zheng Gong13Yongjun Wang14Department of Blood Transfusion, The Second Xiangya Hospital, Central South University, Changsha, ChinaDepartment of Laboratory Medicine, The Second Xiangya Hospital, Central South University, Changsha, ChinaDepartment of Anesthesiology, Fuwai Hospital National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing, ChinaDepartment of Blood Transfusion, Qilu Hospital of Shandong University, Jinan, ChinaDepartment of Transfusion, Xiamen Cardiovascular Hospital Xiamen University, Xiamen, ChinaDepartment of Transfusion, The Affiliated Hospital of Southwest Medical University, Luzhou, ChinaDepartment of Transfusion, Beijing Aerospace General Hospital, Beijing, ChinaDepartment of Transfusion, The Third Xiangya Hospital, Central South University, Changsha, ChinaDepartment of Transfusion, Zhejiang Provincial People's Hospital, Hangzhou, China0Department of Basic Medical Sciences, Changsha Medical University, Changsha, China1Institute for Research on Equity and Community Health, Christiana Care Health System, Newark, DE, United States2Department of Respiratory Medicine, Second Affiliated Hospital of Hainan Medical University, Haikou, China3Sino-Cellbiomed Institutes of Medical Cell & Pharmaceutical Proteins Qingdao University, Qingdao, Shandong, China4Department of Basic Medicine, Xiangnan University, Chenzhou, ChinaDepartment of Blood Transfusion, The Second Xiangya Hospital, Central South University, Changsha, ChinaBackgroundSelecting 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.MethodsParticipants 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.ResultsWe 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).ConclusionsKey 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.https://www.frontiersin.org/articles/10.3389/fcvm.2023.1050698/fullmachine learningcardiac valvular surgeryinfectionrandom forestLASSOartificial network |
| spellingShingle | Ningjie Zhang Kexin Fan Hongwen Ji Xianjun Ma Jingyi Wu Yuanshuai Huang Xinhua Wang Rong Gui Bingyu Chen Hui Zhang Zugui Zhang Xiufeng Zhang Zheng Gong Zheng Gong Yongjun Wang Identification of risk factors for infection after mitral valve surgery through machine learning approaches Frontiers in Cardiovascular Medicine machine learning cardiac valvular surgery infection random forest LASSO artificial network |
| title | Identification of risk factors for infection after mitral valve surgery through machine learning approaches |
| title_full | Identification of risk factors for infection after mitral valve surgery through machine learning approaches |
| title_fullStr | Identification of risk factors for infection after mitral valve surgery through machine learning approaches |
| title_full_unstemmed | Identification of risk factors for infection after mitral valve surgery through machine learning approaches |
| title_short | Identification of risk factors for infection after mitral valve surgery through machine learning approaches |
| title_sort | identification of risk factors for infection after mitral valve surgery through machine learning approaches |
| topic | machine learning cardiac valvular surgery infection random forest LASSO artificial network |
| url | https://www.frontiersin.org/articles/10.3389/fcvm.2023.1050698/full |
| work_keys_str_mv | AT ningjiezhang identificationofriskfactorsforinfectionaftermitralvalvesurgerythroughmachinelearningapproaches AT kexinfan identificationofriskfactorsforinfectionaftermitralvalvesurgerythroughmachinelearningapproaches AT hongwenji identificationofriskfactorsforinfectionaftermitralvalvesurgerythroughmachinelearningapproaches AT xianjunma identificationofriskfactorsforinfectionaftermitralvalvesurgerythroughmachinelearningapproaches AT jingyiwu identificationofriskfactorsforinfectionaftermitralvalvesurgerythroughmachinelearningapproaches AT yuanshuaihuang identificationofriskfactorsforinfectionaftermitralvalvesurgerythroughmachinelearningapproaches AT xinhuawang identificationofriskfactorsforinfectionaftermitralvalvesurgerythroughmachinelearningapproaches AT ronggui identificationofriskfactorsforinfectionaftermitralvalvesurgerythroughmachinelearningapproaches AT bingyuchen identificationofriskfactorsforinfectionaftermitralvalvesurgerythroughmachinelearningapproaches AT huizhang identificationofriskfactorsforinfectionaftermitralvalvesurgerythroughmachinelearningapproaches AT zuguizhang identificationofriskfactorsforinfectionaftermitralvalvesurgerythroughmachinelearningapproaches AT xiufengzhang identificationofriskfactorsforinfectionaftermitralvalvesurgerythroughmachinelearningapproaches AT zhenggong identificationofriskfactorsforinfectionaftermitralvalvesurgerythroughmachinelearningapproaches AT zhenggong identificationofriskfactorsforinfectionaftermitralvalvesurgerythroughmachinelearningapproaches AT yongjunwang identificationofriskfactorsforinfectionaftermitralvalvesurgerythroughmachinelearningapproaches |