Machine learning and physical based modeling for cardiac hypertrophy

Bogdan Milićević; Miljan Milošević; Vladimir Simić; Andrej Preveden; Lazar Velicki; Đorđe Jakovljević; Zoran Bosnić; Matej Pičulin; Bojan Žunkovič; Miloš Kojić; Nenad Filipović

doi:10.1016/j.heliyon.2023.e16724

Machine learning and physical based modeling for cardiac hypertrophy

Heliyon. 2023 May 27;9(6):e16724. doi: 10.1016/j.heliyon.2023.e16724. eCollection 2023 Jun.

Authors

Bogdan Milićević^{1

2}, Miljan Milošević^{2

3

4}, Vladimir Simić^{2

3}, Andrej Preveden⁵, Lazar Velicki⁵, Đorđe Jakovljević^{6

7}, Zoran Bosnić⁸, Matej Pičulin⁸, Bojan Žunkovič⁸, Miloš Kojić^{2

9

10}, Nenad Filipović^{1

2}

Affiliations

¹ Faculty of Engineering, University of Kragujevac, Kragujevac 34000, Serbia.
² Bioengineering Research and Development Center (BioIRC), Kragujevac 34000, Serbia.
³ Institute for Information Technologies, University of Kragujevac, Kragujevac 34000, Serbia.
⁴ Belgrade Metropolitan University, Belgrade 11000, Serbia.
⁵ Faculty of Medicine, University of Novi Sad, Serbia and Institute of Cardiovascular Diseases Vojvodina, Sremska Kamenica, Serbia.
⁶ Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle Upon Tyne, UK.
⁷ Faculty of Health and Life Sciences, Coventry University, Coventry, UK.
⁸ University of Ljubljana, Faculty of Computer and Information Science, Večna Pot 113, Ljubljana, Slovenia.
⁹ Serbian Academy of Sciences and Arts, Belgrade 11000, Serbia.
¹⁰ Houston Methodist Research Institute, Houston TX 77030, USA.

Abstract

Background and objective: Predicting the long-term expansion and remodeling of the left ventricle in patients is challenging task but it has the potential to be clinically very useful.

Methods: In our study, we present machine learning models based on random forests, gradient boosting, and neural networks, used to track cardiac hypertrophy. We collected data from multiple patients, and then the model was trained using the patient's medical history and present level of cardiac health. We also demonstrate a physical-based model, using the finite element procedure to simulate the development of cardiac hypertrophy.

Results: Our models were used to forecast the evolution of hypertrophy over six years. The machine learning model and finite element model provided similar results.

Conclusions: The finite element model is much slower, but it's more accurate compared to the machine learning model since it's based on physical laws guiding the hypertrophy process. On the other hand, the machine learning model is fast but the results can be less trustworthy in some cases. Both of our models, enable us to monitor the development of the disease. Because of its speed machine learning model is more likely to be used in clinical practice. Further improvements to our machine learning model could be achieved by collecting data from finite element simulations, adding them to the dataset, and retraining the model. This can result in a fast and more accurate model combining the advantages of physical-based and machine learning modeling.

Keywords: Cardiac hypertrophy; Disease progress tracking; Finite element analysis; Left ventricle mode; Machine learning.