TY  - JOUR
AU  - Smole, Tim
AU  - Žunkovič, Bojan
AU  - Pičulin, Matej
AU  - Kokalj, Enja
AU  - Robnik-Šikonja, Marko
AU  - Kukar, Matjaž
AU  - Fotiadis, Dimitrios I.
AU  - Pezoulas, Vasileios C.
AU  - Tachos, Nikolaos S.
AU  - Barlocco, Fausto
AU  - Mazzarotto, Francesco
AU  - Popović, Dejana
AU  - Maier, Lars
AU  - Velicki, Lazar
AU  - MacGowan, Guy A.
AU  - Olivotto, Iacopo
AU  - Filipović, Nenad
AU  - Jakovljević, Đorđe G.
AU  - Bosnić, Zoran
PY  - 2021
UR  - https://farfar.pharmacy.bg.ac.rs/handle/123456789/3928
AB  - Background: Machine learning (ML) and artificial intelligence are emerging as important components of precision medicine that enhance diagnosis and risk stratification. Risk stratification tools for hypertrophic cardiomyopathy (HCM) exist, but they are based on traditional statistical methods. The aim was to develop a novel machine learning risk stratification tool for the prediction of 5-year risk in HCM. The goal was to determine if its predictive accuracy is higher than the accuracy of the state-of-the-art tools. Method: Data from a total of 2302 patients were used. The data were comprised of demographic characteristics, genetic data, clinical investigations, medications, and disease-related events. Four classification models were applied to model the risk level, and their decisions were explained using the SHAP (SHapley Additive exPlanations) method. Unwanted cardiac events were defined as sustained ventricular tachycardia occurrence (VT), heart failure (HF), ICD activation, sudden cardiac death (SCD), cardiac death, and all-cause death. Results: The proposed machine learning approach outperformed the similar existing risk-stratification models for SCD, cardiac death, and all-cause death risk-stratification: it achieved higher AUC by 17%, 9%, and 1%, respectively. The boosted trees achieved the best performing AUC of 0.82. The resulting model most accurately predicts VT, HF, and ICD with AUCs of 0.90, 0.88, and 0.87, respectively. Conclusions: The proposed risk-stratification model demonstrates high accuracy in predicting events in patients with hypertrophic cardiomyopathy. The use of a machine-learning risk stratification model may improve patient management, clinical practice, and outcomes in general.
PB  - Elsevier Ltd
T2  - Computers in Biology and Medicine
T1  - A machine learning-based risk stratification model for ventricular tachycardia and heart failure in hypertrophic cardiomyopathy
VL  - 135
DO  - 10.1016/j.compbiomed.2021.104648
ER  - 

@article{
author = "Smole, Tim and Žunkovič, Bojan and Pičulin, Matej and Kokalj, Enja and Robnik-Šikonja, Marko and Kukar, Matjaž and Fotiadis, Dimitrios I. and Pezoulas, Vasileios C. and Tachos, Nikolaos S. and Barlocco, Fausto and Mazzarotto, Francesco and Popović, Dejana and Maier, Lars and Velicki, Lazar and MacGowan, Guy A. and Olivotto, Iacopo and Filipović, Nenad and Jakovljević, Đorđe G. and Bosnić, Zoran",
year = "2021",
abstract = "Background: Machine learning (ML) and artificial intelligence are emerging as important components of precision medicine that enhance diagnosis and risk stratification. Risk stratification tools for hypertrophic cardiomyopathy (HCM) exist, but they are based on traditional statistical methods. The aim was to develop a novel machine learning risk stratification tool for the prediction of 5-year risk in HCM. The goal was to determine if its predictive accuracy is higher than the accuracy of the state-of-the-art tools. Method: Data from a total of 2302 patients were used. The data were comprised of demographic characteristics, genetic data, clinical investigations, medications, and disease-related events. Four classification models were applied to model the risk level, and their decisions were explained using the SHAP (SHapley Additive exPlanations) method. Unwanted cardiac events were defined as sustained ventricular tachycardia occurrence (VT), heart failure (HF), ICD activation, sudden cardiac death (SCD), cardiac death, and all-cause death. Results: The proposed machine learning approach outperformed the similar existing risk-stratification models for SCD, cardiac death, and all-cause death risk-stratification: it achieved higher AUC by 17%, 9%, and 1%, respectively. The boosted trees achieved the best performing AUC of 0.82. The resulting model most accurately predicts VT, HF, and ICD with AUCs of 0.90, 0.88, and 0.87, respectively. Conclusions: The proposed risk-stratification model demonstrates high accuracy in predicting events in patients with hypertrophic cardiomyopathy. The use of a machine-learning risk stratification model may improve patient management, clinical practice, and outcomes in general.",
publisher = "Elsevier Ltd",
journal = "Computers in Biology and Medicine",
title = "A machine learning-based risk stratification model for ventricular tachycardia and heart failure in hypertrophic cardiomyopathy",
volume = "135",
doi = "10.1016/j.compbiomed.2021.104648"
}

Smole, T., Žunkovič, B., Pičulin, M., Kokalj, E., Robnik-Šikonja, M., Kukar, M., Fotiadis, D. I., Pezoulas, V. C., Tachos, N. S., Barlocco, F., Mazzarotto, F., Popović, D., Maier, L., Velicki, L., MacGowan, G. A., Olivotto, I., Filipović, N., Jakovljević, Đ. G.,& Bosnić, Z.. (2021). A machine learning-based risk stratification model for ventricular tachycardia and heart failure in hypertrophic cardiomyopathy. in Computers in Biology and Medicine
Elsevier Ltd., 135.
https://doi.org/10.1016/j.compbiomed.2021.104648

Smole T, Žunkovič B, Pičulin M, Kokalj E, Robnik-Šikonja M, Kukar M, Fotiadis DI, Pezoulas VC, Tachos NS, Barlocco F, Mazzarotto F, Popović D, Maier L, Velicki L, MacGowan GA, Olivotto I, Filipović N, Jakovljević ĐG, Bosnić Z. A machine learning-based risk stratification model for ventricular tachycardia and heart failure in hypertrophic cardiomyopathy. in Computers in Biology and Medicine. 2021;135.
doi:10.1016/j.compbiomed.2021.104648 .

Smole, Tim, Žunkovič, Bojan, Pičulin, Matej, Kokalj, Enja, Robnik-Šikonja, Marko, Kukar, Matjaž, Fotiadis, Dimitrios I., Pezoulas, Vasileios C., Tachos, Nikolaos S., Barlocco, Fausto, Mazzarotto, Francesco, Popović, Dejana, Maier, Lars, Velicki, Lazar, MacGowan, Guy A., Olivotto, Iacopo, Filipović, Nenad, Jakovljević, Đorđe G., Bosnić, Zoran, "A machine learning-based risk stratification model for ventricular tachycardia and heart failure in hypertrophic cardiomyopathy" in Computers in Biology and Medicine, 135 (2021),
https://doi.org/10.1016/j.compbiomed.2021.104648 . .