Combining radiomics and machine learning for enhanced localization of premature ventricular contractions
-
By
-
Jingjie Liu
-
Shiyu Dai
-
Lingxuan Hou
-
Boyang Zang
-
Yang Liu
-
Chongfu Jia
-
Xiaomeng Yin
-
May 15, 2026
-
Clinical Scorecard: Integrating Radiomics with Machine Learning to Improve Detection of Premature Ventricular Contractions
At a Glance
| Category | Detail |
|---|
| Condition | Premature Ventricular Contractions (PVC) |
| Key Mechanisms | Abnormal excitability of ventricular myocardial cells leading to premature depolarization. |
| Target Population | Patients diagnosed with PVC undergoing first-time radiofrequency catheter ablation. |
| Care Setting | Single-center, retrospective diagnostic accuracy study. |
Key Highlights
- PVC can lead to symptoms like palpitations and chest tightness.
- Catheter ablation is highly effective for managing PVC.
- CCTA-based radiomics can identify microstructural changes associated with PVC.
- Machine learning models have shown improved localization accuracy for PVC origins.
- The study included 304 patients with documented PVC origins.
Guideline-Based Recommendations
Diagnosis
- PVC diagnosed by ECG and Holter monitoring.
- CCTA used for localization of PVC origin.
Management
- Radiofrequency catheter ablation (RFCA) is recommended for treatment.
Monitoring & Follow-up
- Documented PVC origin confirmed by intracardiac electrophysiological mapping.
Risks
- Persistent PVC increases the risk of lethal arrhythmias.
Patient & Prescribing Data
Patients undergoing RFCA for PVC.
Limited benefit from anti-arrhythmic medications; RFCA is preferred.
Clinical Best Practices
- Utilize CCTA and radiomics for improved PVC localization.
- Ensure accurate ECG interpretation by experienced operators.
- Standardize diagnostic processes for PVC localization.
Related Resources & Content
