Related Experiment Video

Updated: May 5, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.6K

DTF-STCANet: A Dual Time-Frequency Swin Transformer and ConvNeXt Attention Network for Heart Sound Classification

Mehmet Nail Bilen1, Fatih Mehmet Çelik2, Mehmet Ali Kobat3

  • 1Department of Cardiology, Basaksehir Cam and Sakura City Hospital, Istanbul 34480, Turkey.

Diagnostics (Basel, Switzerland)
|May 4, 2026
PubMed

Insights

This study introduces an AI model for early heart disease detection using phonocardiogram (PCG) signals, achieving 99.29% accuracy. The approach enhances cardiovascular disease diagnosis through advanced signal processing and machine learning.

Area of Science:

  • Cardiology
  • Biomedical Engineering
  • Artificial Intelligence in Healthcare

Background:

  • Cardiovascular diseases represent a significant global health burden, necessitating early and accurate diagnostic methods.
  • Traditional stethoscope-based diagnosis of heart conditions requires specialized expertise, limiting accessibility.
  • Artificial intelligence (AI) is increasingly utilized for clinical decision support, offering potential for improved diagnostic capabilities.

Purpose of the Study:

  • To develop and evaluate an AI-driven system for the early detection of cardiovascular diseases.
  • To enhance the diagnostic accuracy of phonocardiogram (PCG) signals through advanced signal processing and machine learning techniques.
  • To investigate the efficacy of a novel Dual Time-Frequency Swin Transformer-ConvNeXt Attention Network (DTF-STCANet) for heart sound classification.

Main Methods:

  • Utilized the 2016 PhysioNet/CinC Challenge dataset comprising phonocardiogram (PCG) signals.
  • Generated time-frequency representations including spectrograms and continuous wavelet transform (CWT) images from PCG signals.
  • Implemented a Dual Time-Frequency Swin Transformer-ConvNeXt Attention Network (DTF-STCANet) model incorporating Weighted KNN for classification.

Main Results:

  • Achieved a high classification accuracy of 99.29% for detecting cardiovascular diseases.
  • Demonstrated superior performance compared to existing state-of-the-art models in heart sound analysis.
  • The integration of time and frequency domain features significantly improved diagnostic precision.

Conclusions:

  • The proposed AI-integrated approach significantly enhances the early diagnosis of heart disease.
  • The DTF-STCANet model shows promise for reliable and accurate cardiovascular disease screening.
  • This study underscores the potential of AI in revolutionizing cardiac diagnostics and improving patient outcomes.

Keywords:
cardiovascular diseasesconvnextdeep learningdual time–frequency fusionphonocardiogram (PCG)swin transformer

More Related Videos

Echocardiographic Evaluation of Atrial Communications before Transcatheter Closure07:41

Echocardiographic Evaluation of Atrial Communications before Transcatheter Closure

Published on: February 8, 2022

3.7K
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation08:10

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation

Published on: July 20, 2022

2.8K

Related Concept Videos

Heart Sounds01:15

Heart Sounds

Heart sounds are generated by the turbulence in blood flow due to the closing of heart valves. These sounds are best perceived slightly away from the valves, where the blood flow disseminates the sound.
Auscultation is the process of listening to these internal body sounds using a stethoscope. The heart produces four types of sounds, but only two—S1 and S2—can usually be heard with a stethoscope.
S1, also known as the "lub" sound, is caused by the closure of atrioventricular (A-V)...
3.7K
Assessing Blood pressure using a doppler ultrasound01:19

Assessing Blood pressure using a doppler ultrasound

To obtain accurate blood pressure measurements in clinical settings, especially when traditional methods are insufficient, healthcare professionals utilize the Doppler ultrasound technique. This method uses high-frequency sound waves to detect blood flow within the arteries, which is crucial for patients with conditions that complicate circulatory system assessment.
Pre-Procedural Guidelines for Doppler Ultrasound Blood Pressure Assessment:
Preparation of Equipment:
3.0K
Classification of Signals01:30

Classification of Signals

In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.6K
Discrete Fourier Transform01:15

Discrete Fourier Transform

The Discrete Fourier Transform (DFT) is a fundamental tool in signal processing, extending the discrete-time Fourier transform by evaluating discrete signals at uniformly spaced frequency intervals. This transformation converts a finite sequence of time-domain samples into frequency components, each representing complex sinusoids ordered by frequency. The DFT translates these sequences into the frequency domain, effectively indicating the magnitude and phase of each frequency component present...
1.3K