Exploring the assessment of post-cardiac valve surgery pulmonary complication risks through the integration of wearable continuous physiological and clinical data
Abstract Background Postoperative pulmonary complications (PPCs) following cardiac valvular surgery are characterized by high morbidity, mortality, and economic cost. This study leverages wearable technology and machine learning algorithms to preoperatively identify high-risk individuals, thereby en...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-025-02875-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571568708911104 |
|---|---|
| author | Lixuan Li Yuekong Hu Zhicheng Yang Zeruxin Luo Jiachen Wang Wenqing Wang Xiaoli Liu Yuqiang Wang Yong Fan Pengming Yu Zhengbo Zhang |
| author_facet | Lixuan Li Yuekong Hu Zhicheng Yang Zeruxin Luo Jiachen Wang Wenqing Wang Xiaoli Liu Yuqiang Wang Yong Fan Pengming Yu Zhengbo Zhang |
| author_sort | Lixuan Li |
| collection | DOAJ |
| description | Abstract Background Postoperative pulmonary complications (PPCs) following cardiac valvular surgery are characterized by high morbidity, mortality, and economic cost. This study leverages wearable technology and machine learning algorithms to preoperatively identify high-risk individuals, thereby enhancing clinical decision-making for the mitigation of PPCs. Methods A prospective study was conducted at the Department of Cardiovascular Surgery of West China Hospital, Sichuan University, from August 2021 to December 2022. We examined 100 cardiac valvular surgery patients, where wearable technology was utilized to collect and analyze nocturnal physiological data at the 24-hour admission, in conjunction with clinical data extraction from the Hospital Information System’s electronic records. We systematically evaluated three different input types (physiological, clinical, and both) and five classifiers (XGB, LR, RF, SVM, KNN) to identify the combination with strong predictive performance for PPCs. Feature selection was conducted using Recursive Feature Elimination with Cross-Validated (RFECV) for each model, yielding an optimal feature subset for each, followed by a grid search to tune hyperparameters. Stratified 5-fold cross-validation was used to evaluate the generalization performance. The significance of AUC differences between models was tested using the DeLong test to determine the optimal prognostic model comprehensively. Additionally, univariate logistic regression analysis was conducted on the features of the best-performing model to understand the impact of individual feature on PPCs. Results In this study, 22 patients (22%) developed PPCs. Across classifiers, models combining both physiological and clinical features performed better than physiological or clinical features alone. Specifically, including physiological data in the classification model improved AUC, ACC, F1, and precision by an average of 8.32%, 1.80%, 3.28% and 6.06% compared to using clinical data only. The XGB classifier, utilizing both dataset, achieved the highest performance with an AUC of 0.82 (± 0.08) and identified eight significant features. The DeLong test indicated that the XGB model utilizing the both dataset significantly outperformed the XGB models trained on the physiological or clinical datasets alone. Univariate logistic regression analysis suggested that surgical methods, age, nni_50, and min_ven_in_mean are significantly associated with the occurrence of PPCs. Conclusion The integration of continuous wearable physiological and clinical data significantly improves preoperative risk assessment for PPCs, which helps to optimize surgical management and reduce PPCs morbidity and mortality. |
| format | Article |
| id | doaj-art-208f38b02eab49778360e5980f20e3b3 |
| institution | Kabale University |
| issn | 1472-6947 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj-art-208f38b02eab49778360e5980f20e3b32025-02-02T12:27:50ZengBMCBMC Medical Informatics and Decision Making1472-69472025-01-0125111110.1186/s12911-025-02875-2Exploring the assessment of post-cardiac valve surgery pulmonary complication risks through the integration of wearable continuous physiological and clinical dataLixuan Li0Yuekong Hu1Zhicheng Yang2Zeruxin Luo3Jiachen Wang4Wenqing Wang5Xiaoli Liu6Yuqiang Wang7Yong Fan8Pengming Yu9Zhengbo Zhang10Medical Innovation Research Division, Chinese PLA General HospitalDepartment of Rehabilitation Medicine, West China Tianfu Hospital, Sichuan UniversityPAII IncDepartment of Rehabilitation Medicine Center, West China Hospital, Sichuan UniversityGeneral Hospital of Tibet Military RegionMedical Innovation Research Division, Chinese PLA General HospitalMedical Innovation Research Division, Chinese PLA General HospitalDepartment of Cardiovascular Surgery, West China Hospital, Sichuan UniversityMedical Innovation Research Division, Chinese PLA General HospitalDepartment of Rehabilitation Medicine Center, West China Hospital, Sichuan UniversityMedical Innovation Research Division, Chinese PLA General HospitalAbstract Background Postoperative pulmonary complications (PPCs) following cardiac valvular surgery are characterized by high morbidity, mortality, and economic cost. This study leverages wearable technology and machine learning algorithms to preoperatively identify high-risk individuals, thereby enhancing clinical decision-making for the mitigation of PPCs. Methods A prospective study was conducted at the Department of Cardiovascular Surgery of West China Hospital, Sichuan University, from August 2021 to December 2022. We examined 100 cardiac valvular surgery patients, where wearable technology was utilized to collect and analyze nocturnal physiological data at the 24-hour admission, in conjunction with clinical data extraction from the Hospital Information System’s electronic records. We systematically evaluated three different input types (physiological, clinical, and both) and five classifiers (XGB, LR, RF, SVM, KNN) to identify the combination with strong predictive performance for PPCs. Feature selection was conducted using Recursive Feature Elimination with Cross-Validated (RFECV) for each model, yielding an optimal feature subset for each, followed by a grid search to tune hyperparameters. Stratified 5-fold cross-validation was used to evaluate the generalization performance. The significance of AUC differences between models was tested using the DeLong test to determine the optimal prognostic model comprehensively. Additionally, univariate logistic regression analysis was conducted on the features of the best-performing model to understand the impact of individual feature on PPCs. Results In this study, 22 patients (22%) developed PPCs. Across classifiers, models combining both physiological and clinical features performed better than physiological or clinical features alone. Specifically, including physiological data in the classification model improved AUC, ACC, F1, and precision by an average of 8.32%, 1.80%, 3.28% and 6.06% compared to using clinical data only. The XGB classifier, utilizing both dataset, achieved the highest performance with an AUC of 0.82 (± 0.08) and identified eight significant features. The DeLong test indicated that the XGB model utilizing the both dataset significantly outperformed the XGB models trained on the physiological or clinical datasets alone. Univariate logistic regression analysis suggested that surgical methods, age, nni_50, and min_ven_in_mean are significantly associated with the occurrence of PPCs. Conclusion The integration of continuous wearable physiological and clinical data significantly improves preoperative risk assessment for PPCs, which helps to optimize surgical management and reduce PPCs morbidity and mortality.https://doi.org/10.1186/s12911-025-02875-2Postoperative pulmonary complicationsWearable devicesContinuous physiological signalsHeart valve surgeryPreoperative assessment |
| spellingShingle | Lixuan Li Yuekong Hu Zhicheng Yang Zeruxin Luo Jiachen Wang Wenqing Wang Xiaoli Liu Yuqiang Wang Yong Fan Pengming Yu Zhengbo Zhang Exploring the assessment of post-cardiac valve surgery pulmonary complication risks through the integration of wearable continuous physiological and clinical data BMC Medical Informatics and Decision Making Postoperative pulmonary complications Wearable devices Continuous physiological signals Heart valve surgery Preoperative assessment |
| title | Exploring the assessment of post-cardiac valve surgery pulmonary complication risks through the integration of wearable continuous physiological and clinical data |
| title_full | Exploring the assessment of post-cardiac valve surgery pulmonary complication risks through the integration of wearable continuous physiological and clinical data |
| title_fullStr | Exploring the assessment of post-cardiac valve surgery pulmonary complication risks through the integration of wearable continuous physiological and clinical data |
| title_full_unstemmed | Exploring the assessment of post-cardiac valve surgery pulmonary complication risks through the integration of wearable continuous physiological and clinical data |
| title_short | Exploring the assessment of post-cardiac valve surgery pulmonary complication risks through the integration of wearable continuous physiological and clinical data |
| title_sort | exploring the assessment of post cardiac valve surgery pulmonary complication risks through the integration of wearable continuous physiological and clinical data |
| topic | Postoperative pulmonary complications Wearable devices Continuous physiological signals Heart valve surgery Preoperative assessment |
| url | https://doi.org/10.1186/s12911-025-02875-2 |
| work_keys_str_mv | AT lixuanli exploringtheassessmentofpostcardiacvalvesurgerypulmonarycomplicationrisksthroughtheintegrationofwearablecontinuousphysiologicalandclinicaldata AT yuekonghu exploringtheassessmentofpostcardiacvalvesurgerypulmonarycomplicationrisksthroughtheintegrationofwearablecontinuousphysiologicalandclinicaldata AT zhichengyang exploringtheassessmentofpostcardiacvalvesurgerypulmonarycomplicationrisksthroughtheintegrationofwearablecontinuousphysiologicalandclinicaldata AT zeruxinluo exploringtheassessmentofpostcardiacvalvesurgerypulmonarycomplicationrisksthroughtheintegrationofwearablecontinuousphysiologicalandclinicaldata AT jiachenwang exploringtheassessmentofpostcardiacvalvesurgerypulmonarycomplicationrisksthroughtheintegrationofwearablecontinuousphysiologicalandclinicaldata AT wenqingwang exploringtheassessmentofpostcardiacvalvesurgerypulmonarycomplicationrisksthroughtheintegrationofwearablecontinuousphysiologicalandclinicaldata AT xiaoliliu exploringtheassessmentofpostcardiacvalvesurgerypulmonarycomplicationrisksthroughtheintegrationofwearablecontinuousphysiologicalandclinicaldata AT yuqiangwang exploringtheassessmentofpostcardiacvalvesurgerypulmonarycomplicationrisksthroughtheintegrationofwearablecontinuousphysiologicalandclinicaldata AT yongfan exploringtheassessmentofpostcardiacvalvesurgerypulmonarycomplicationrisksthroughtheintegrationofwearablecontinuousphysiologicalandclinicaldata AT pengmingyu exploringtheassessmentofpostcardiacvalvesurgerypulmonarycomplicationrisksthroughtheintegrationofwearablecontinuousphysiologicalandclinicaldata AT zhengbozhang exploringtheassessmentofpostcardiacvalvesurgerypulmonarycomplicationrisksthroughtheintegrationofwearablecontinuousphysiologicalandclinicaldata |