Justinas Bacevicius
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Justinas Bacevicius has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Andrius Petrėnas
Kaunas University of Technology
1 shared publication Andrius Zucenka
Hematology, Oncology and Transfusion Medicine Centre, Vilnius University Hospital Santaros Klinikos, Vilnius, Lithuania
1 shared publicationAudrius Aidietis
Department of Cardiac Arrhythmias, Vilnius University Hospital Santaros Klinikos, Santariškių G. 2, Vilnius, 08661, Lithuania
1 shared publication- Austeja Dapkeviciute
Faculty of Medicine, Institute of Clinical Medicine, Vilnius University, Vilnius, Lithuania
1 shared publication Birute Zablockiene
Institute of Clinical Medicine, Faculty of Medicine, Vilnius University, Vilnius, Lithuania
1 shared publication- Christian Jons
Department of Cardiology, The Heart Centre, Copenhagen University Hospital—Rigshospitalet , Copenhagen
1 shared publication
Latest Publications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (1) , 234-244
ECG-Based Detection of Acute Myocardial Infarction Using a Wrist-Worn Device
Background: A wrist-worn wearable device for acquiring limb and chest ECG leads (wECG) may constitute a promising approach to detection of acute myocardial infarction (AMI). However, it remains to be demonstrated whether the information conveyed by the wECG is sufficient for AMI detection. Objective: To explore explainable machine learning models for detecting AMI using the wECG. Methods: Two types of machine learning models are explored: a convolutional neural network (CNN) using the raw ECG as input and a gradient-boosting decision tree (GBDT) using clinically informative features. 123 participants were included, divided into patients with AMI, patients with other cardiovascular diseases, and healthy individuals. A wrist-worn device equipped with three biopotential electrodes was used to acquire two ECG leads with a single touch: limb lead I and another lead involving a specific body site, i.e., either the V3 or V5 electrode positions, or the abdomen. Results: The best performance on the test dataset is obtained using models that incorporate all four leads. The CNN model performs slightly better than the GBDT model, with a sensitivity of 0.77 and specificity of 0.75 compared to 0.77 and 0.72, respectively. When distinguishing between AMI and healthy participants, the specificity increases to 0.94 for the CNN model and 0.90 for the GBDT model. Feature importance analysis shows that the GBDT model primarily relies on the J point, while the CNN model primarily relies on the QRS complex. Conclusions: wECG-based AMI detection shows considerable promise in out-of-hospital settings. However, caution is needed as CNN explanations rarely agree with the ECG intervals typically analyzed in clinical practice.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (1) , 234-244
Open AccessECG-Based Detection of Acute Myocardial Infarction Using a Wrist-Worn Device
Background: A wrist-worn wearable device for acquiring limb and chest ECG leads (wECG) may constitute a promising approach to detection of acute myocardial infarction (AMI). However, it remains to be demonstrated whether the information conveyed by the wECG is sufficient for AMI detection. Objective: To explore explainable machine learning models for detecting AMI using the wECG. Methods: Two types of machine learning models are explored: a convolutional neural network (CNN) using the raw ECG as input and a gradient-boosting decision tree (GBDT) using clinically informative features. 123 participants were included, divided into patients with AMI, patients with other cardiovascular diseases, and healthy individuals. A wrist-worn device equipped with three biopotential electrodes was used to acquire two ECG leads with a single touch: limb lead I and another lead involving a specific body site, i.e., either the V3 or V5 electrode positions, or the abdomen. Results: The best performance on the test dataset is obtained using models that incorporate all four leads. The CNN model performs slightly better than the GBDT model, with a sensitivity of 0.77 and specificity of 0.75 compared to 0.77 and 0.72, respectively. When distinguishing between AMI and healthy participants, the specificity increases to 0.94 for the CNN model and 0.90 for the GBDT model. Feature importance analysis shows that the GBDT model primarily relies on the J point, while the CNN model primarily relies on the QRS complex. Conclusions: wECG-based AMI detection shows considerable promise in out-of-hospital settings. However, caution is needed as CNN explanations rarely agree with the ECG intervals typically analyzed in clinical practice.
- 23 July 2025
- Published by Vilnius University Press
Cardiac Monitoring in Patients with Atrial Arrhythmias: Invention and Validation of a User-Friendly Wearable Device, Diagnostic Capability of an Artificial Intelligence Algorithm, and Detection of Pro-Arrhythmic Risk Markers in Long-Term Electrocardiograms
- 23 July 2025
- Published by Vilnius University Press
Cardiac Monitoring in Patients with Atrial Arrhythmias: Invention and Validation of a User-Friendly Wearable Device, Diagnostic Capability of an Artificial Intelligence Algorithm, and Detection of Pro-Arrhythmic Risk Markers in Long-Term Electrocardiograms
- Open Access
- 25 June 2025
- Published by Springer Nature in Journal of Interventional Cardiac Electrophysiology
- Vol. 69 (7) , 1687-1693
First in-human results of the MAGiC robotic magnetic navigation radiofrequency ablation catheter
Robotic magnetic navigation (RMN) has demonstrated clinical utility in treating arrhythmia patients by providing direct distal-tip control of an ablation catheter, enhancing catheter precision, safety, and stability with an atraumatic catheter design. We aimed to assess the first in-human efficacy and safety of the new RMN-guided MAGiCTM radiofrequency ablation catheter. This prospective, multicenter single-arm, unblinded study enrolled 67 patients with arrhythmias that met EHRA guidelines for catheter ablation. All patients were treated for their index arrhythmia with the MAGiC RMN catheter. All other devices used in the procedures were approved for treatment including a RMN System (Genesis/Niobe®) used to navigate the MAGiC catheter. Acute procedural success and adverse events were assessed for all patients through discharge from the hospital in the days following the procedure. Sixty-seven patients were treated as follows: 25 cases of atrioventricular nodal reentrant tachycardia, 19 of premature ventricular contractions, 8 of Wolf-Parkinson-White (WPW) syndrome, 8 of atrial fibrillation, 3 of atrial flutter, and 4 of ventricular tachycardia. Acute procedural success was 94%. There was one cardiac tamponade due to perforation of the right ventricular outflow tract during ablation. Otherwise, no adverse events were observed. The results of this study demonstrate good acute efficacy and safety of the MAGiC RMN ablation catheter independent of underlying arrhythmias. Contact force and stability with MAGiC seem improved compared to previous catheters available with RMN, and therefore radiofrequency energy delivery needs careful attention, especially in thin areas of the myocardium. Additional long-term data are needed.
- 25 June 2025
- Published by Springer Nature in Journal of Interventional Cardiac Electrophysiology
- Vol. 69 (7) , 1687-1693
Open AccessFirst in-human results of the MAGiC robotic magnetic navigation radiofrequency ablation catheter
Robotic magnetic navigation (RMN) has demonstrated clinical utility in treating arrhythmia patients by providing direct distal-tip control of an ablation catheter, enhancing catheter precision, safety, and stability with an atraumatic catheter design. We aimed to assess the first in-human efficacy and safety of the new RMN-guided MAGiCTM radiofrequency ablation catheter. This prospective, multicenter single-arm, unblinded study enrolled 67 patients with arrhythmias that met EHRA guidelines for catheter ablation. All patients were treated for their index arrhythmia with the MAGiC RMN catheter. All other devices used in the procedures were approved for treatment including a RMN System (Genesis/Niobe®) used to navigate the MAGiC catheter. Acute procedural success and adverse events were assessed for all patients through discharge from the hospital in the days following the procedure. Sixty-seven patients were treated as follows: 25 cases of atrioventricular nodal reentrant tachycardia, 19 of premature ventricular contractions, 8 of Wolf-Parkinson-White (WPW) syndrome, 8 of atrial fibrillation, 3 of atrial flutter, and 4 of ventricular tachycardia. Acute procedural success was 94%. There was one cardiac tamponade due to perforation of the right ventricular outflow tract during ablation. Otherwise, no adverse events were observed. The results of this study demonstrate good acute efficacy and safety of the MAGiC RMN ablation catheter independent of underlying arrhythmias. Contact force and stability with MAGiC seem improved compared to previous catheters available with RMN, and therefore radiofrequency energy delivery needs careful attention, especially in thin areas of the myocardium. Additional long-term data are needed.
- Open Access
- 1 February 2021
- Published by Elsevier in IJC Heart & Vasculature
- Vol. 32, 100685
Mitigating arrhythmia risk in Hydroxychloroquine and Azithromycin treated COVID-19 patients using arrhythmia risk management plan
- 1 February 2021
- Published by Elsevier in IJC Heart & Vasculature
- Vol. 32, 100685
Open AccessMitigating arrhythmia risk in Hydroxychloroquine and Azithromycin treated COVID-19 patients using arrhythmia risk management plan