Abstract
The quality of treatment and prognosis after pediatric congenital heart surgery remains unsatisfactory. A reliable prediction model for postoperative complications of congenital heart surgery patients is essential to enable prompt initiation of therapy and improve the quality of prognosis. Here, we develop an interpretable machine-learning-based model that integrates patient demographics, surgery-specific features and intraoperative blood pressure data for accurately predicting complications after pediatric congenital heart surgery. We used blood pressure variability and the k-means algorithm combined with a smoothed formulation of dynamic time wrapping to extract features from time-series data. In addition, SHAP framework was used to provide explanations of the prediction. Our model achieved the best performance both in binary and multi-label classification compared with other consensus-based risk models. In addition, this explainable model explains why a prediction was made to help improve the clinical understanding of complication risk and generate actionable knowledge in practice. The combination of model performance and interpretability is easy for clinicians to trust and provide insight into how they should respond before the condition worsens after pediatric congenital heart surgery.
Highlights
The quality of treatment and prognosis after pediatric congenital heart surgery remains unsatisfactory
The early detection of deterioration after congenital heart surgery enables a prompt initiation of therapy, which may result in reduced impairment and earlier rehabilitation. Several scoring systems, such as the Risk Adjustment for Congenital Heart Surgery (RACHS-1) c ategory[8], the Aristotle Basic Complexity (ABC) s core[9], the European Association for Cardiothoracic Surgery and the Society of Thoracic Surgeons (STS-EACTS) mortality s core[10], and the STS-EACTS morbidity s core[11], have been developed and used to adjust the risk of in-hospital morbidity and mortality in the community. All these consensus-based risk models only focus on the procedure themselves and cannot be adjusted for specific patient characteristics such as lower w eight[12] and longer cardiopulmonary bypass (CPB)[13], which were associated with worse outcomes after congenital heart surgery
Researches using electronic health record (EHR) data have shown that weight[12,14], perioperative blood t ransfusions15, CPB13,16, and preoperative ejection f raction[17] were associated with the risk of postoperative complications and mortality after congenital heart surgery
Summary
The quality of treatment and prognosis after pediatric congenital heart surgery remains unsatisfactory. We develop an interpretable machine-learning-based model that integrates patient demographics, surgery-specific features and intraoperative blood pressure data for accurately predicting complications after pediatric congenital heart surgery. Heart centers with the best outcomes might not report fewer complications but rather have systems in place to recognize and correct complications before deleterious outcomes e nsue[6] In these cases, the early detection of deterioration after congenital heart surgery enables a prompt initiation of therapy, which may result in reduced impairment and earlier rehabilitation. We aimed to develop and internally validate a machine learning model to predict the risk of complications and what kind of complications patients could experience using patient demographics, surgery-specific features, and intraoperative blood pressure data, all of which are routinely collected as part of medical records. We believe the combination of model performance and interpretability is an important step forwards that enables the prediction of postoperative complications prediction to be more widely used in practice
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
