Related Experiment Video
Updated: Jan 9, 2026

Calculating Heart Rate Variability from ECG Data from Youth with Cerebral Palsy During Active Video Game Sessions
Published on: June 5, 2019
Classification of Valvular Heart Diseases based on Heart Rate Variability and Hjorth Parameters in
Insights
This study classifies valvular heart disease using heart rate variability (HRV) and Hjorth parameters from ECG, SCG, and GCG signals. Efficient Logistic Regression achieved high accuracy in detecting mitral regurgitation and stenosis.
Area of Science:
- Biomedical Engineering
- Cardiovascular Research
- Signal Processing
Background:
- Valvular heart disease (VHD) is a growing public health concern due to increasing prevalence, reduced quality of life, and high healthcare costs.
- Accurate and early detection of VHD is crucial for effective patient management and treatment.
- Non-invasive methods for VHD assessment are highly desirable.
Purpose of the Study:
- To classify valvular heart diseases using heart rate variability (HRV) indices and Hjorth parameters.
- To evaluate the efficacy of electrocardiograms (ECG), seismocardiography (SCG), and gyrocardiogram (GCG) signals for VHD classification.
- To identify the most effective classification algorithms and features for different types of VHD.
Main Methods:
- Utilized a publicly available dataset of 30 concurrent ECG, SCG, and GCG signals with annotated heartbeats.
- Employed the Classification Learner App in MATLAB R2024a for signal analysis and classification.
- Applied Efficient Logistic Regression, a binary linear classifier, and analyzed features from time and frequency domains, including ellipse area.
Main Results:
- Achieved the highest classification accuracy for mitral regurgitation (86.7%) across all signal types.
- Demonstrated high accuracy for mitral stenosis (83.3%-86.7%) and moderate accuracy for tricuspid regurgitation (70.0%-76.7%).
- Identified frequency domain and ellipse area features as most relevant for mitral regurgitation and stenosis, while time domain features were key for tricuspid regurgitation using SCG and GCG.
Conclusions:
- Heart rate variability and Hjorth parameters derived from ECG, SCG, and GCG signals show promise for classifying valvular heart diseases.
- Efficient Logistic Regression provides a viable classification method for VHD detection.
- The study highlights the potential of multi-modal sensor data for improving the accuracy of VHD diagnosis.
Abstract:
Valvular heart disease (VHD) is defined as a cardiovascular disease that affects any heart valve and is becoming a major concern for public health due to the growing prevalence, impact on patient quality of life and healthcare costs. In this study, we carried out the classification of valvular heart diseases based on heart rate variability (HRV) indices and Hjorth parameters in electrocardiograms (ECG), seismocardiography (SCG), and gyrocardiogram (GCG) with the Classification Learner App in MATLAB R2024a. The study was carried out on 30 concurrent ECG, SCG, and GCG signals with annotated heartbeats taken from a publicly available dataset. The most frequently used classifier was Efficient Logistic Regression (binary linear classifier). The highest classification accuracy was observed for the detection of mitral regurgitation (86.7% for all signals), followed by mitral stenosis (83.3%-86.7%) and tricupsid regurgitation (70.0%-76.7%). The most relevant features for mitral regurgitation and mitral stenosis were based on frequency domain and ellipse area, except for SCG, and for tricupsid regurgitation were based on time domain for SCG and GCG.
More Related Videos
Related Concept Videos
Heart Failure IV: Classification and Diagnostic Evaluation
Dysrhythmias II: Classification of Tachyarrhythmias
Cardiomyopathy I: Introduction and Classification
Rheumatic Heart Disease II: Clinical Manifestations and Diagnostic Studies
Mechanism of Cardiac Arrhythmias
Heart Valves
The AV valves prevent the backflow of blood from the ventricles to the atria during ventricular contraction. These valves function with the assistance of the chordae tendineae and papillary muscles. When the ventricles are relaxed, the chordae tendineae are slack, allowing blood to flow from the atria into the...

