Frontiers in Cardiovascular Medicine (Apr 2022)

Automatic Identification of Patients With Unexplained Left Ventricular Hypertrophy in Electronic Health Record Data to Improve Targeted Treatment and Family Screening

  • Arjan Sammani,
  • Mark Jansen,
  • Nynke M. de Vries,
  • Nicolaas de Jonge,
  • Annette F. Baas,
  • Anneline S. J. M. te Riele,
  • Folkert W. Asselbergs,
  • Folkert W. Asselbergs,
  • Marish I. F. J. Oerlemans

DOI
https://doi.org/10.3389/fcvm.2022.768847
Journal volume & issue
Vol. 9

Abstract

Read online

BackgroundUnexplained Left Ventricular Hypertrophy (ULVH) may be caused by genetic and non-genetic etiologies (e.g., sarcomere variants, cardiac amyloid, or Anderson-Fabry's disease). Identification of ULVH patients allows for early targeted treatment and family screening.AimTo automatically identify patients with ULVH in electronic health record (EHR) data using two computer methods: text-mining and machine learning (ML).MethodsAdults with echocardiographic measurement of interventricular septum thickness (IVSt) were included. A text-mining algorithm was developed to identify patients with ULVH. An ML algorithm including a variety of clinical, ECG and echocardiographic data was trained and tested in an 80/20% split. Clinical diagnosis of ULVH was considered the gold standard. Misclassifications were reviewed by an experienced cardiologist. Sensitivity, specificity, positive, and negative likelihood ratios (LHR+ and LHR–) of both text-mining and ML were reported.ResultsIn total, 26,954 subjects (median age 61 years, 55% male) were included. ULVH was diagnosed in 204/26,954 (0.8%) patients, of which 56 had amyloidosis and two Anderson-Fabry Disease. Text-mining flagged 8,192 patients with possible ULVH, of whom 159 were true positives (sensitivity, specificity, LHR+, and LHR– of 0.78, 0.67, 2.36, and 0.33). Machine learning resulted in a sensitivity, specificity, LHR+, and LHR– of 0.32, 0.99, 32, and 0.68, respectively. Pivotal variables included IVSt, systolic blood pressure, and age.ConclusionsAutomatic identification of patients with ULVH is possible with both Text-mining and ML. Text-mining may be a comprehensive scaffold but can be less specific than machine learning. Deployment of either method depends on existing infrastructures and clinical applications.

Keywords