Model-driven survival prediction after congenital heart surgery

Christoph Zürn; David Hübner; Victoria C Ziesenitz; René Höhn; Lena Schuler; Tim Schlange; Matthias Gorenflo; Fabian A Kari; Johannes Kroll; Tsvetomir Loukanov; Rolf Klemm; Brigitte Stiller

doi:10.1093/icvts/ivad089

Model-driven survival prediction after congenital heart surgery

Interdiscip Cardiovasc Thorac Surg. 2023 Sep 2;37(3):ivad089. doi: 10.1093/icvts/ivad089.

Authors

Affiliations

¹ Department of Congenital Heart Defects and Paediatric Cardiology, University Heart Center Freiburg-Bad Krozingen, Medical Center-University of Freiburg, Faculty of Medicine, University of Freiburg, Germany.
² Machine learning for medical applications, Averbis GmbH, Freiburg, Germany.
³ Department of Paediatric Cardiology and Congenital Heart Disease Center for Child and Adolescent Health, Medical Center-University of Heidelberg, Faculty of Medicine, University of Heidelberg, Germany.
⁴ Faculty of Psychology, Ruhr University, Bochum, Germany.
⁵ Department of Cardiovascular Surgery, University Heart Center Freiburg-Bad Krozingen, Medical Center-University of Freiburg, Faculty of Medicine, University of Freiburg, Germany.
⁶ Department of Cardiothoracic Surgery, Medical Center-University of Heidelberg, Faculty of Medicine, University of Heidelberg, Germany.

Abstract

Objectives: The objective of the study was to improve postoperative risk assessment in congenital heart surgery by developing a machine-learning model based on readily available peri- and postoperative parameters.

Methods: Our bicentric retrospective data analysis from January 2014 to December 2019 of established risk parameters for dismal outcome was used to train and test a model to predict postoperative survival within the first 30 days. The Freiburg training data consisted of 780 procedures; the Heidelberg test data comprised 985 procedures. STAT mortality score, age, aortic cross-clamp time and postoperative lactate values over 24 h were considered.

Results: Our model showed an area under the curve (AUC) of 94.86%, specificity of 89.48% and sensitivity of 85.00%, resulting in 3 false negatives and 99 false positives.The STAT mortality score and the aortic cross-clamp time each showed a statistically highly significant impact on postoperative mortality. Interestingly, a child's age was barely statistically significant. Postoperative lactate values indicated an increased mortality risk if they were either constantly at a high level or low during the first 8 h postoperatively with an increase afterwards.When considering parameters available before, at the end of and 24 h after surgery, the predictive power of the complete model achieved the highest AUC. This, compared to the already high predictive power alone (AUC 88.9%) of the STAT mortality score, translates to an error reduction of 53.5%.

Conclusions: Our model predicts postoperative survival after congenital heart surgery with great accuracy. Compared with preoperative risk assessments, our postoperative risk assessment reduces prediction error by half. Heightened awareness of high-risk patients should improve preventive measures and thus patient safety.

Keywords: Congenital heart surgery; Machine learning; Paediatric intensive care; Survival prediction.