Model-driven survival prediction after congenital heart surgery

• Verfasst von: Zürn, Christoph Manuel [VerfasserIn]
• Verfasst von: Hübner, David [VerfasserIn]
• Verfasst von: Ziesenitz, Victoria C. [VerfasserIn]
• Verfasst von: Höhn, René Gerhard Joachim [VerfasserIn]
• Verfasst von: Schuler, Lena [VerfasserIn]
• Verfasst von: Schlange, Tim [VerfasserIn]
• Verfasst von: Gorenflo, Matthias [VerfasserIn]
• Verfasst von: Kari, Fabian Alexander [VerfasserIn]
• Verfasst von: Kroll, Johannes [VerfasserIn]
• Verfasst von: Loukanov, Tsvetomir [VerfasserIn]
• Verfasst von: Klemm, Rolf [VerfasserIn]
• Verfasst von: Stiller, Brigitte [VerfasserIn]
• Titel: Model-driven survival prediction after congenital heart surgery
• Verf.angabe: Christoph Zürn, David Hübner, Victoria C. Ziesenitz, René Höhn, Lena Schuler, Tim Schlange, Matthias Gorenflo, Fabian A. Kari, Johannes Kroll, Tsvetomir Loukanov, Rolf Klemm and Brigitte Stiller
• E-Jahr: 2023
• Jahr: September 2023
• Umfang: 7 S.
• Illustrationen: Illustrationen
• Fussnoten: Online verfügbar: 05. Juni 2023, Artikelversion: 10. September 2023 ; Gesehen am 14.11.2023
• Titel Quelle: Enthalten in: Interdisciplinary cardiovascular and thoracic surgery
• Ort Quelle: Oxford : Oxford University Press, 2023
• Jahr Quelle: 2023
• Band/Heft Quelle: 37(2023), 3 vom: Sept., Artikel-ID ivad089, Seite 1-7
• ISSN Quelle: 2753-670X
• DOI: doi:10.1093/icvts/ivad089
• Datenträger: Online-Ressource
• Sprache: eng
• K10plus-PPN: 1870235193

Abstract

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.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.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%.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.