Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
January 1, 2011Journal of Biomedical Science and EngineeringOpen Access

Diagnosis of long QT syndrome via support vector machines classification

View Full Paper
Ask AI
Bookmark
Share

Key result

Support vector machine classification using discrete wavelet transform features from ECG data achieved an 80% accuracy in diagnosing long QT syndrome, outperforming the 71% accuracy of clinical inspection.

Why the study?

Does a machine learning approach using Discrete Wavelet Transform and Support Vector Machine classification improve the diagnostic accuracy of congenital Long QT Syndrome compared to standard clinical QTc criteria in children?

Population

45 children, including 26 genetically identified patients with congenital Long QT Syndrome and 19 healthy…

Comparison

Discrete Wavelet Transform for feature… vs Clinical inspection based on QTc criteria.

Design

Case-control

Authors

HBHalil BişğinOKOrhan U. KilincAUAhmet Ugur

Discussion

Loading...

Member takes

Overview

May support ML-assisted LQTS diagnosis in children; hypothesis-generating and requires prospective validation before practice change.

Study Design

Type

Case-Control (n=45)

Multicenter

No

Structured PICO

Does a machine learning approach using Discrete Wavelet Transform and Support Vector Machine classification improve the diagnostic accuracy of congenital Long QT Syndrome compared to standard clinical QTc criteria in children?

P
Population
45 children, including 26 genetically identified patients with congenital Long QT Syndrome (LQTS) and 19 healthy controls.
I
Intervention
Discrete Wavelet Transform (DWT) for feature extraction from beat-to-beat QT intervals (first 16,384 data points from 24-hour Holter monitoring) followed by Support Vector Machine (SVM) classification.
C
Comparator
Clinical inspection based on QTc criteria (QTc ≤ 440 msec or QTc ≥ 450 msec).
O
Outcome
Diagnostic accuracy for Long QT Syndrome.surrogate

Main Result

Absolute Event Rate: 80% vs 71%

Combining Discrete Wavelet Transform and Support Vector Machine classification on Holter ECG data achieved 80% accuracy in diagnosing congenital Long QT Syndrome, outperforming standard clinical QTc criteria.

Limitations

  • Limited number of samples (45 subjects)
  • Requires a minimum signal length of 16,384 data points for analysis
  • Limited number of samples
  • Small data set requiring leave-one-out cross-validation

Cite This Study

Bişğin et al. (2011) conducted a case-control in Congenital Long QT Syndrome (LQTS) (n=45). Support Vector Machine (SVM) classification using Discrete Wavelet Transform (DWT) vs. Clinical inspection based on QTc measure was evaluated on Classification accuracy for LQTS diagnosis. Support vector machine classification using discrete wavelet transform features from ECG data achieved an 80% accuracy in diagnosing long QT syndrome, outperforming the 71% accuracy of clinical inspection.

synapsesocial.com/papers/6a0f33ee2d7a240a01425de4https://doi.org/10.4236/jbise.2011.44036
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Differentiating long QT syndrome genotypes using electrocardiographic geometric parameterization and machine learning approaches2026
  2. 2Support vector machine-based assessment of the T-wave morphology improves long QT syndrome diagnosis2018 · 30 citations
  3. 3A deep learning approach identifies new ECG features in congenital long QT syndrome2022 · 44 citations
  4. 4The diagnostic value of electrocardiogram-based machine learning in long QT syndrome: a systematic review and meta-analysis2023 · 7 citations
  5. 5A MATLAB Algorithm to Automatically Estimate the QT Interval and Other ECG Parameters and Validation Using a Machine Learning Approach in Congenital Long-QT Syndrome2025 · 3 citations