Interpretable machine learning-based predictive modeling of patient outcomes following cardiac surgery

Adeel Abbasi; Cindy Li; Max Dekle; Christian A Bermudez; Daniel Brodie; Frank W Sellke; Neel R Sodha; Corey E Ventetuolo; Carsten Eickhoff

doi:10.1016/j.jtcvs.2023.11.034

Interpretable machine learning-based predictive modeling of patient outcomes following cardiac surgery

J Thorac Cardiovasc Surg. 2023 Nov 29:S0022-5223(23)01110-8. doi: 10.1016/j.jtcvs.2023.11.034. Online ahead of print.

Authors

Adeel Abbasi¹, Cindy Li², Max Dekle², Christian A Bermudez³, Daniel Brodie⁴, Frank W Sellke⁵, Neel R Sodha⁵, Corey E Ventetuolo⁶, Carsten Eickhoff⁷

Affiliations

¹ Division of Pulmonary, Critical Care, and Sleep Medicine, Department of Medicine, Warren Alpert School of Medicine at Brown University, Providence, RI. Electronic address: adeel_abbasi@brown.edu.
² Brown University, Providence, RI.
³ Division of Cardiovascular Surgery, Department of Surgery, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, Pa.
⁴ Division of Pulmonary and Critical Care, Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, Md.
⁵ Division of Cardiothoracic Surgery, Department of Surgery, Warren Alpert School of Medicine at Brown University, Providence, RI.
⁶ Division of Pulmonary, Critical Care, and Sleep Medicine, Department of Medicine, Warren Alpert School of Medicine at Brown University, Providence, RI; Department of Health Services, Policy and Practice, Brown School of Public Health, Providence, RI.
⁷ Department of Computer Science, Brown University, Providence, RI; Faculty of Medicine, University of Tübingen, Tübingen, Germany; Institute for Bioinformatics and Medical Informatics, University of Tübingen, Tübingen, Germany.

PMID: 38040328
DOI: 10.1016/j.jtcvs.2023.11.034

Abstract

Background: The clinical applicability of machine learning predictions of patient outcomes following cardiac surgery remains unclear. We applied machine learning to predict patient outcomes associated with high morbidity and mortality after cardiac surgery and identified the importance of variables to the derived model's performance.

Methods: We applied machine learning to the Society of Thoracic Surgeons Adult Cardiac Surgery Database to predict postoperative hemorrhage requiring reoperation, venous thromboembolism (VTE), and stroke. We used permutation feature importance to identify variables important to model performance and a misclassification analysis to study the limitations of the model.

Results: The study dataset included 662,772 subjects who underwent cardiac surgery between 2015 and 2017 and 240 variables. Hemorrhage requiring reoperation, VTE, and stroke occurred in 2.9%, 1.2%, and 2.0% of subjects, respectively. The model performed remarkably well at predicting all 3 complications (area under the receiver operating characteristic curve, 0.92-0.97). Preoperative and intraoperative variables were not important to model performance; instead, performance for the prediction of all 3 outcomes was driven primarily by several postoperative variables, including known risk factors for the complications, such as mechanical ventilation and new onset of postoperative arrhythmias. Many of the postoperative variables important to model performance also increased the risk of subject misclassification, indicating internal validity.

Conclusions: A machine learning model accurately and reliably predicts patient outcomes following cardiac surgery. Postoperative, as opposed to preoperative or intraoperative variables, are important to model performance. Interventions targeting this period, including minimizing the duration of mechanical ventilation and early treatment of new-onset postoperative arrhythmias, may help lower the risk of these complications.

Keywords: Society of Thoracic Surgeons Adult Cardiac Surgery Database; adult cardiac surgery; explainable machine learning; hemorrhage requiring reoperation; patient outcomes; stroke; venous thromboembolism.

Abstract

Grants and funding