Related Experiment Video
Updated: Jul 9, 2025
Lumped-Parameter and Finite Element Modeling of Heart Failure with Preserved Ejection Fraction
Published on: February 13, 2021
Model for classification of heart failure severity in patients with hypertrophic cardiomyopathy using a deep neural
Sanshiro Togo1, Yuki Sugiura1, Sayumi Suzuki2
1Hamamatsu University School of Medicine, Hamamatsu, Japan.
Insights
Deep learning models can now classify heart failure severity in hypertrophic cardiomyopathy patients using ECG data. This approach shows promise for non-invasively assessing disease progression and guiding treatment strategies.
Area of Science:
- Cardiology
- Medical Imaging
- Artificial Intelligence
Background:
- Electrocardiogram (ECG) abnormalities are characteristic of hypertrophic cardiomyopathy (HCM).
- While ECG aids in risk stratification for arrhythmias, its utility in determining heart failure (HF) severity using deep learning (DL) remains underexplored.
- Identifying HF severity is crucial for managing HCM patients.
Purpose of the Study:
- To develop and evaluate a DL model for classifying HF severity in HCM patients using 12-lead ECG data.
- To assess the model's performance in distinguishing between different levels of HF severity.
- To explore the potential of ECG-based DL for non-invasive HF assessment in HCM.
Main Methods:
- A residual neural network was developed using 12-lead ECG data from HCM and non-HCM patients.
- HF severity was categorized using New York Heart Association functional class, N-terminal prohormone of brain natriuretic peptide levels, and Kansas City Cardiomyopathy Questionnaire (KCCQ)-12 scores.
- Transfer learning was employed, pre-training the model on the PTB-XL ECG dataset to address limited sample sizes.
Main Results:
- The DL model achieved a weighted average F1 score of 0.745 and precision of 0.750 for mild-to-moderate HF classification.
- Similar performance was observed when grouping patients based on KCCQ-12 scores.
- Analysis revealed that QRS waves were key indicators for mild-to-moderate HF, while patterns were more variable for severe HF.
Conclusions:
- A deep neural network model effectively classifies HF severity in HCM patients using 12-lead ECG data.
- The developed DL algorithm shows potential as a valuable tool for assessing HF status in HCM.
- This approach may facilitate non-invasive monitoring and management of heart failure in HCM.
Objectives:
In hypertrophic cardiomyopathy (HCM), specific ECG abnormalities are observed. Therefore, ECG is a valuable screening tool. Although several studies have reported on estimating the risk of developing fatal arrhythmias from ECG findings, the use of ECG to identify the severity of heart failure (HF) by applying deep learning (DL) methods has not been established.
Methods:
We assessed whether data-driven machine-learning methods could effectively identify the severity of HF in patients with HCM. A residual neural network-based model was developed using 12-lead ECG data from 218 patients with HCM and 245 patients with non-HCM, categorised them into two (mild-to-moderate and severe) or three (mild, moderate and severe) severities of HF. These severities were defined according to the New York Heart Association functional class and levels of the N-terminal prohormone of brain natriuretic peptide. In addition, the patients were divided into groups according to Kansas City Cardiomyopathy Questionnaire (KCCQ)-12. A transfer learning method was applied to resolve the issue of the low number of target samples. The model was trained in advance using PTB-XL, which is an open ECG dataset.
Results:
The model trained with our dataset achieved a weighted average F1 score of 0.745 and precision of 0.750 for the mild-to-moderate class samples. Similar results were obtained for grouping based on KCCQ-12. Through data analyses using the Guided Gradient Weighted-Class Activation Map and Integrated Gradients, QRS waves were intensively highlighted among true-positive mild-to-moderate class cases, while the highlighted part was highly variable among true-positive severe class cases.
Conclusions:
We developed a model for classifying HF severity in patients with HCM using a deep neural network algorithm with 12-lead ECG data. Our findings suggest that applications of this DL algorithm for using 12-lead ECG data may be useful to classify the HF status in patients with HCM.
Related Concept Videos
01:17Pathophysiology of Heart Failure
01:22Heart Failure Drugs: β-Blockers
01:26Heart Failure Drugs: Inhibitors of Renin-Angiotensin System
01:26Heart Failure Drugs: Inotropic Agents