Frontiers in Cardiovascular Medicine (Sep 2022)

Machine learning prediction of atrial fibrillation in cardiovascular patients using cardiac magnetic resonance and electronic health information

  • Steven Dykstra,
  • Steven Dykstra,
  • Alessandro Satriano,
  • Alessandro Satriano,
  • Alessandro Satriano,
  • Aidan K. Cornhill,
  • Aidan K. Cornhill,
  • Lucy Y. Lei,
  • Lucy Y. Lei,
  • Dina Labib,
  • Dina Labib,
  • Yoko Mikami,
  • Yoko Mikami,
  • Yoko Mikami,
  • Jacqueline Flewitt,
  • Sandra Rivest,
  • Sandra Rivest,
  • Rosa Sandonato,
  • Rosa Sandonato,
  • Patricia Feuchter,
  • Patricia Feuchter,
  • Patricia Feuchter,
  • Andrew G. Howarth,
  • Andrew G. Howarth,
  • Andrew G. Howarth,
  • Carmen P. Lydell,
  • Carmen P. Lydell,
  • Carmen P. Lydell,
  • Nowell M. Fine,
  • Derek V. Exner,
  • Carlos A. Morillo,
  • Stephen B. Wilton,
  • Marina L. Gavrilova,
  • James A. White,
  • James A. White,
  • James A. White

DOI
https://doi.org/10.3389/fcvm.2022.998558
Journal volume & issue
Vol. 9

Abstract

Read online

BackgroundAtrial fibrillation (AF) is a commonly encountered cardiac arrhythmia associated with morbidity and substantial healthcare costs. While patients with cardiovascular disease experience the greatest risk of new-onset AF, no risk model has been developed to predict AF occurrence in this population. We hypothesized that a patient-specific model could be delivered using cardiovascular magnetic resonance (CMR) disease phenotyping, contextual patient health information, and machine learning.MethodsNine thousand four hundred forty-eight patients referred for CMR imaging were enrolled and followed over a 5-year period. Seven thousand, six hundred thirty-nine had no prior history of AF and were eligible to train and validate machine learning algorithms. Random survival forests (RSFs) were used to predict new-onset AF and compared to Cox proportional-hazard (CPH) models. The best performing features were identified from 115 variables sourced from three data domains: (i) CMR-based disease phenotype, (ii) patient health questionnaire, and (iii) electronic health records. We evaluated discriminative performance of optimized models using C-index and time-dependent AUC (tAUC).ResultsA RSF-based model of 20 variables (CIROC-AF-20) delivered an overall C-index of 0.78 for the prediction of new-onset AF with respective tAUCs of 0.80, 0.79, and 0.78 at 1-, 2- and 3-years. This outperformed a novel CPH-based model and historic AF risk scores. At 1-year of follow-up, validation cohort patients classified as high-risk of future AF by CIROC-AF-20 went on to experience a 17.3% incidence of new-onset AF, being 24.7-fold higher risk than low risk patients.ConclusionsUsing phenotypic data available at time of CMR imaging we developed and validated the first described risk model for the prediction of new-onset AF in patients with cardiovascular disease. Complementary value was provided by variables from patient-reported measures of health and the electronic health record, illustrating the value of multi-domain phenotypic data for the prediction of AF.

Keywords