Toggle Main Menu Toggle Search

Open Access padlockePrints

Disease Progression of Hypertrophic Cardiomyopathy: Modeling Using Machine Learning

Lookup NU author(s): Dr Guy MacGowanORCiD, Professor Djordje JakovljevicORCiD



This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).


© Matej Pičulin, Tim Smole, Bojan Žunkovič, Enja Kokalj, Marko Robnik-Šikonja, Matjaž Kukar, Dimitrios I Fotiadis, Vasileios C Pezoulas, Nikolaos S Tachos, Fausto Barlocco, Francesco Mazzarotto, Dejana Popović, Lars S Maier, Lazar Velicki, Iacopo Olivotto, Guy A MacGowan, Djordje G Jakovljević, Nenad Filipović, Zoran Bosnić. Originally published in JMIR Medical Informatics (, 02.02.2022. This is an open-access article distributed under the terms of the Creative Commons Attribution License (, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Medical Informatics, is properly cited. The complete bibliographic information, a link to the original publication on, as well as this copyright and license information must be included. 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 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 the best of 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 machine learning (ML)-based tool for predicting disease progression for patients diagnosed with HCM in terms of adverse remodeling of the heart during a 10-year period. Methods: The method consisted of 6 predictive regression models that independently predict future values of 6 clinical characteristics: left atrial size, left atrial volume, left ventricular ejection fraction, New York Heart Association functional classification, left ventricular internal diastolic diameter, and left ventricular internal systolic diameter. We supplemented each prediction with the explanation that is generated using the Shapley additive explanation method. Results: The final experiments showed that predictive error is lower on 5 of the 6 constructed models in comparison to experts (on average, by 0.34) or a consortium of experts (on average, by 0.22). The experiments revealed that semisupervised learning and the artificial data from virtual patients help improve predictive accuracies. The best-performing random forest model improved R2 from 0.3 to 0.6. Conclusions: By engaging medical experts to provide interpretation and validation of the results, we determined the models' favorable performance compared to the performance of experts for 5 of 6 targets.

Publication metadata

Author(s): Piculin M, Smole T, Zunkovic B, Kokalj E, Robnik-Sikonja M, Kukar M, Fotiadis DI, Pezoulas VC, Tachos NS, Barlocco F, Mazzarotto F, Popovic D, Maier LS, Velicki L, Olivotto I, MacGowan GA, Jakovljevic DG, Filipovic N, Bosnic Z

Publication type: Article

Publication status: Published

Journal: JMIR Medical Informatics

Year: 2022

Volume: 10

Issue: 2

Print publication date: 02/02/2022

Online publication date: 02/02/2021

Acceptance date: 04/12/2021

Date deposited: 07/03/2022

ISSN (electronic): 2291-9694

Publisher: JMIR Publications Inc.


DOI: 10.2196/30483


Altmetrics provided by Altmetric


Funder referenceFunder name
777204Commission of the European Communities