Machine Learning to Predict Outcomes and Cost by Phase of Care After Coronary Artery Bypass Grafting

Rodrigo Zea-Vera, Christopher T. Ryan, Jim Havelka, Stuart J. Corr, Tom C. Nguyen, Subhasis Chatterjee, Matthew J. Wall, Joseph S. Coselli, Todd K. Rosengart, Ravi K. Ghanta

Research output: Contribution to journalArticlepeer-review

12 Scopus citations

Abstract

BACKGROUND: Machine learning may enhance prediction of outcomes after coronary artery bypass grafting (CABG). We sought to develop and validate a dynamic machine learning model to predict CABG outcomes at clinically relevant pre- and postoperative time points.

METHODS: The Society of Thoracic Surgeons (STS) registry data elements from 2086 isolated CABG patients were divided into training and testing datasets and input into Extreme Gradient Boosting decision-tree machine learning algorithms. Two prediction models were developed based on data from preoperative (80 parameters) and postoperative (125 parameters) phases of care. Outcomes included operative mortality, major morbidity or mortality, high cost, and 30-day readmission. Machine learning and STS model performance were assessed using accuracy and the area under the precision-recall curve (AUC-PR).

RESULTS: Preoperative machine learning models predicted mortality (accuracy, 98%; AUC-PR = 0.16; F1 = 0.24), major morbidity or mortality (accuracy, 75%; AUC-PR = 0.33; F1 = 0.42), high cost (accuracy, 83%; AUC-PR = 0.51; F1 = 0.52), and 30-day readmission (accuracy, 70%; AUC-PR = 0.47; F1 = 0.49) with high accuracy. Preoperative machine learning models performed similarly to the STS for prediction of mortality (STS AUC-PR = 0.11; P = .409) and outperformed STS for prediction of mortality or major morbidity (STS AUC-PR = 0.28; P < .001). Addition of intraoperative parameters further improved machine learning model performance for major morbidity or mortality (AUC-PR = 0.39; P < .01) and high cost (AUC-PR = 0.64; P < .01), with cross-clamp and bypass times emerging as important additive predictive parameters.

CONCLUSIONS: Machine learning can predict mortality, major morbidity, high cost, and readmission after isolated CABG. Prediction based on the phase of care allows for dynamic risk assessment through the hospital course, which may benefit quality assessment and clinical decision-making.

Original languageEnglish (US)
Pages (from-to)711-719
Number of pages9
JournalAnnals of Thoracic Surgery
Volume114
Issue number3
DOIs
StatePublished - Sep 2022

Keywords

  • Algorithms
  • Coronary Artery Bypass
  • Humans
  • Machine Learning
  • Patient Readmission
  • Risk Assessment
  • Risk Factors

ASJC Scopus subject areas

  • Cardiology and Cardiovascular Medicine
  • Pulmonary and Respiratory Medicine
  • Surgery

Fingerprint

Dive into the research topics of 'Machine Learning to Predict Outcomes and Cost by Phase of Care After Coronary Artery Bypass Grafting'. Together they form a unique fingerprint.

Cite this