JMIR Publications

ABSTRACT

Background:

Cardiovascular disorders in general are responsible for 30% of deaths worldwide. Among them, hypertrophic cardiomyopathy (HCM) is a genetic cardiac disease that is present in about 1 out of 500 young adults and can cause sudden cardiac death (SCD).

Objective:

Although the current state-of-the-art methods model the risk of SCD for patients, to our knowledge no methods are available for modeling the patient's clinical status up to 10 years ahead. In this paper, we propose a novel ML-based tool for predicting disease progression for patients diagnosed with HCM in terms of adverse remodeling of heart during a 10-year period.

Methods:

The method consists of six predictive regression models that independently predict future values of six clinical characteristics: left atrial size, left atrial volume, left ventricular ejection fraction, New York Heart Association Functional Classification (NYHA), left ventricular internal diastolic diameter, and left ventricular internal systolic diameter. We supplemented each prediction with the explanation that is generated with the Shapely additive explanation (SHAP) method.

Results:

The final experiments show that predictive error is lower on 5 out of 6 constructed models with comparison to experts or consortium of experts. The experiments revealed that semi-supervised learning and the artificial data from virtual patients helped to achieve even higher predictive accuracies.

Conclusions:

By engaging medical experts to provide interpretation and validation of the results, we determined the models' favorable performance compared to performance of experts for five out of six targets.