![Sample our Bioscience journals, sign in here to start your access, Latest two full volumes FREE to you for 14 days]({"type":"image" , "src" : "/sda/5925/TOC-Subject-Sample-2021-Bioscience.jpg"})
Abstract
Objective
Low cardiac output syndrome (LCOS) is a severe complication after valve surgery, with no uniform standard for early identification. We developed interpretative machine learning (ML) models for predicting LCOS risk preoperatively and 0.5 h postoperatively for intervention in advance.
Methods
A total of 2218 patients undergoing valve surgery from June 2019 to Dec 2021 were finally enrolled to construct preoperative and postoperative models. Logistic regression, support vector machine (SVM), random forest classifier, extreme gradient boosting, and deep neural network were executed for model construction, and the performance of models was evaluated by area under the curve (AUC) of the receiver operating characteristic and calibration curves. Our models were interpreted through SHapley Additive exPlanations, and presented as an online tool to improve clinical operability.
Results
The SVM algorithm was chosen for modeling due to better AUC and calibration capability. The AUCs of the preoperative and postoperative models were 0.786 (95% CI 0.729–0.843) and 0.863 (95% CI 0.824–0.902), and the Brier scores were 0.123 and 0.107. Our models have higher timeliness and interpretability, and wider coverage than the vasoactive-inotropic score, and the AUC of the postoperative model was significantly higher. Our preoperative and postoperative models are available online at http://njfh-yxb.com.cn:2022/lcos.
Conclusions
The first interpretable ML tool with two prediction periods for online early prediction of LCOS risk after valve surgery was successfully built in this study, in which the SVM model has the best performance, reserving enough time for early precise intervention in critical care.
Ethical approval
The study protocol was conducted in accordance with the Declaration of Helsinki and was approved by the Ethics Committee of Nanjing First Hospital, Nanjing Medical University (KY20220518-KS-01, 18 May 2022), who waived the need for informed consent.
Author contributions
L.H., T.F., R.Q. and S.L. contributed equally to this work, and C.Z., R.Q. and J.Z. share the corresponding authorship. L.H., R.Q., S.L. and J.Z. conceived the conception of the study. Y.X., C.C., R.X. and S.S. acquired the data. L.H. and S.L. participated in data analyses. T.F., R.Q. and S.L. prepared the manuscript. K.H. and J.W. polished this article. C.Z. and J.Z. led the project and supervised the study. All authors were involved in preparing or editing the manuscript, and approved the submission.
Disclosure statement
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.
Central picture
Machine learning models show good performance for predicting low cardiac output syndrome.
Central message
We developed machine learning models for predicting low cardiac output syndrome associated with valve surgery, which performed well and were interpreted and deployed online.
Perspective statement
The low cardiac output syndrome complicating valve surgery leads to poor outcomes and lacks reliable means for early recognition. We developed machine learning models for predicting the complication preoperatively and 0.5h postoperatively, which performed well and have been interpreted and deployed online, reserving enough time for early intervention.
Data availability statement
The original contributions presented in this study are included in the Supplementary materials, further inquiries can be directed to the corresponding authors.