Heart failure & cardiomyopathies
Detection of Titin-Associated Electrocardiography Features in Dilated Cardiomyopathy Using Conventional and Deep Neural Network Analysis
Authors' conclusion
Conventional ECG and DNN analyses demonstrated similar good predictive performance in distinguishing TTNtv from gene-elusive DCM patients, emphasizing their potential as clinical tools to guide targeted genetic testing.
Study context
- Population
- Patients with dilated cardiomyopathy (DCM)
- Participants
- 99 vs 318
- Exposure
- Conventional electrocardiography (ECG) analysis vs ECG-based deep neural network (DNN) for predicting TTNtv
- TTNtvn = 99
- Gene-elusiven = 318reference
- Outcome
- Discriminative performance of conventional ECG and DNN models for TTNtv (C-statistics)
Methodological detailsmultinational
- Multinational
Main finding
As reported in the abstract
Prediction of TTNtv (C-statistic)
C-statistic, conventional ECG model
0.83
C-statistic, DNN model
0.86
Observational data: associations, not effects.
Further findings
Baseline characteristics
Age TTNtv 50.5 years · Gene-elusive 56.9 years
Male
LVEF
- Baseline characteristics: Age P < 0.001
- Baseline characteristics: Male P = 0.008
- Baseline characteristics: LVEF P < 0.001
Conventional ECG features of TTNtv
- Shorter QRS duration
- P < 0.001
- Prolonged PR interval
- P < 0.001
- Trend toward reduced QRS voltage
- P = 0.098
DNN factors associated with TTNtv
- F1 (inferolateral T wave inversion) and F9 (anterior T-wave inversion), among others, associated with TTNtv
Original publication
Detection of Titin-Associated Electrocardiography Features in Dilated Cardiomyopathy Using Conventional and Deep Neural Network Analysis. JACC Clin Electrophysiol. Published 24 November 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →