Dataset Information

Explainable localization of premature ventricular contraction using deep learning-based semantic segmentation of 12-lead electrocardiogram.

ABSTRACT:

Background

Predicting the origin of premature ventricular contraction (PVC) from the preoperative electrocardiogram (ECG) is important for catheter ablation therapies. We propose an explainable method that localizes PVC origin based on the semantic segmentation result of a 12-lead ECG using a deep neural network, considering suitable diagnosis support for clinical application.

Methods

The deep learning-based semantic segmentation model was trained using 265 12-lead ECG recordings from 84 patients with frequent PVCs. The model classified each ECG sampling time into four categories: background (BG), sinus rhythm (SR), PVC originating from the left ventricular outflow tract (PVC-L), and PVC originating from the right ventricular outflow tract (PVC-R). Based on the ECG segmentation results, a rule-based algorithm classified ECG recordings into three categories: PVC-L, PVC-R, as well as Neutral, which is a group for the recordings requiring the physician's careful assessment before separating them into PVC-L and PVC-R. The proposed method was evaluated with a public dataset which was used in previous research.

Results

The evaluation of the proposed method achieved neutral rate, accuracy, sensitivity, specificity, F1-score, and area under the curve of 0.098, 0.932, 0.963, 0.882, 0.945, and 0.852 on a private dataset, and 0.284, 0.916, 0.912, 0.930, 0.943, and 0.848 on a public dataset, respectively. These quantitative results indicated that the proposed method outperformed almost all previous studies, although a significant number of recordings resulted in requiring the physician's assessment.

Conclusions

The feasibility of explainable localization of premature ventricular contraction was demonstrated using deep learning-based semantic segmentation of 12-lead ECG.Clinical trial registration: M26-148-8.

SUBMITTER: Kujime K

PROVIDER: S-EPMC11317653 | biostudies-literature | 2024 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Explainable localization of premature ventricular contraction using deep learning-based semantic segmentation of 12-lead electrocardiogram.

Kujime Kota K Seno Hiroshi H Nakajima Kenzaburo K Yamazaki Masatoshi M Sakuma Ichiro I Yamagata Kenichiro K Kusano Kengo K Tomii Naoki N

Journal of arrhythmia 20240621 4

<h4>Background</h4>Predicting the origin of premature ventricular contraction (PVC) from the preoperative electrocardiogram (ECG) is important for catheter ablation therapies. We propose an explainable method that localizes PVC origin based on the semantic segmentation result of a 12-lead ECG using a deep neural network, considering suitable diagnosis support for clinical application.<h4>Methods</h4>The deep learning-based semantic segmentation model was trained using 265 12-lead ECG recordings ...[more]

PMID: 39139876

Similar Datasets

Project description:Mechanisms behind development of premature ventricular contraction (PVC)-induced cardiomyopathy remain unclear. PVCs may adversely modulate the autonomic nervous system to promote development of heart failure. Afferent neurons in the inferior vagal (nodose) ganglia transduce cardiac activity and modulate parasympathetic output. Effects of PVCs on cardiac parasympathetic efferent and vagal afferent neurotransmission are unknown. The purpose of this study was to evaluate effects of PVCs on vagal afferent neurotransmission and compare these effects with a known powerful autonomic modulator, myocardial ischemia. In 16 pigs, effects of variably coupled PVCs on heart rate variability (HRV) and vagal afferent neurotransmission were evaluated. Direct nodose neuronal recordings were obtained in vivo, and cardiac-related afferent neurons were identified based on their response to cardiovascular interventions, including ventricular chemical and mechanical stimuli, left anterior descending (LAD) coronary artery occlusion, and variably coupled PVCs. On HRV analysis before versus after PVCs, parasympathetic tone decreased (normalized high frequency: 83.6?±?2.8 to 72.5?±?5.3; P < 0.05). PVCs had a powerful impact on activity of cardiac-related afferent neurons, altering activity of 51% of neurons versus 31% for LAD occlusion (P < 0.05 vs. LAD occlusion and all other cardiac interventions). Both chemosensitive and mechanosensitive neurons were activated by PVCs, and their activity remained elevated even after cessation of PVCs. Cardiac afferent neural responses to PVCs were greater than any other intervention, including ischemia of similar duration. These data suggest that even brief periods of PVCs powerfully modulate vagal afferent neurotransmission, reflexly decreasing parasympathetic efferent tone.NEW & NOTEWORTHY Premature ventricular contractions (PVCs) are common in many patients and, at an increased burden, are known to cause heart failure. This study determined that PVCs powerfully modulate cardiac vagal afferent neurotransmission (exerting even greater effects than ventricular ischemia) and reduce parasympathetic efferent outflow to the heart. PVCs activated both mechano- and chemosensory neurons in the nodose ganglia. These peripheral neurons demonstrated adaptation in response to PVCs. This study provides additional data on the potential role of the autonomic nervous system in PVC-induced cardiomyopathy.

Project description:Abstract Background We have demonstrated that a neural network is able to predict a person’s age from the electrocardiogram (ECG) [artificial intelligence (AI) ECG age]. However, some discrepancies were observed between ECG-derived and chronological ages. We assessed whether the difference between AI ECG and chronological age (Age-Gap) represents biological ageing and predicts long-term outcomes. Methods and results We previously developed a convolutional neural network to predict chronological age from ECGs. In this study, we used the network to analyse standard digital 12-lead ECGs in a cohort of 25 144 subjects ≥30 years who had primary care outpatient visits from 1997 to 2003. Subjects with coronary artery disease, stroke, and atrial fibrillation were excluded. We tested whether Age-Gap was correlated with total and cardiovascular mortality. Of 25 144 subjects tested (54% females, 95% Caucasian) followed for 12.4 ± 5.3 years, the mean chronological age was 53.7 ± 11.6 years and ECG-derived age was 54.6 ± 11 years (R2 = 0.79, P < 0.0001). The mean Age-Gap was small at 0.88 ± 7.4 years. Compared to those whose ECG-derived age was within 1 standard deviation (SD) of their chronological age, patients with Age-Gap ≥1 SD had higher all-cause and cardiovascular disease (CVD) mortality. Conversely, subjects whose Age-Gap was ≤1 SD had lower all-cause and CVD mortality. Results were unchanged after adjusting for CVD risk factors and other survival influencing factors. Conclusion The difference between AI ECG and chronological age is an independent predictor of all-cause and cardiovascular mortality. Discrepancies between these possibly reflect disease independent biological ageing. Graphical Abstract In subjects without baseline cardiovascular disease, an older artificial intelligence (AI)-derived electrocardiogram (ECG) Age (AI-ECG age) compared to chronological age was associated with increased all-cause and cardiovascular mortality. Subjects, where the reverse was true, had lower mortality. Discrepancies between chronological age and ECG-derived age possibly reflect disease independent biological ageing.

Dataset Information

Explainable localization of premature ventricular contraction using deep learning-based semantic segmentation of 12-lead electrocardiogram.

Background

Methods

Results

Conclusions

Publications

Explainable localization of premature ventricular contraction using deep learning-based semantic segmentation of 12-lead electrocardiogram.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets