Mauro Luis Buelga Suárez
Research Subjects
Mauro Luis Buelga Suárez has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Gonzalo Luis Alonso Salinas
Department of Cardiology, Hospital Universitario de Navarra, 31008 Pamplona, Spain
3 shared publications - Joaquín Recas
Universidad Complutense de Madrid
2 shared publications - Luis Piñuel
Computer Architecture and Automation Department, Complutense University of Madrid, Madrid, Spain
2 shared publications - Marian Diaz-Vicente
Complutense University of Madrid, Madrid, Spain and Vision2.ai, Madrid, Spain
2 shared publications - Mario Sanz-Guerrero
Johannes Gutenberg University Mainz, Mainz, Germany
2 shared publications - Sergio González-Cabeza
Department of Computer Architecture and Automation, Complutense University of Madrid, Madrid, Spain
2 shared publications
Latest Publications
- Open Access
- 5 November 2026
- Published by JMIR Publications Inc. in JMIR Cardio
- Vol. 10, e86621
Generation of 12-Lead Electrocardiogram Using Smartwatches in Patients With Cardiac Conditions: Clinical Validation Study
Background: Smartwatches have significantly expanded personal health monitoring capabilities; however, their application in comprehensive cardiac assessment remains limited by single-lead electrocardiogram (ECG) acquisition. The inability to directly obtain augmented limb leads represents a major limitation for the evaluation of ischemic and arrhythmogenic conditions. Objective: This study aimed to present and preliminarily evaluate a methodology for generating augmented limb leads (augmented voltage right [aVR], augmented voltage left [aVL], and augmented voltage foot [aVF]) from sequential smartwatch recordings through signal synchronization and RR interval alignment, and to combine this approach with precordial smartwatch recordings to reconstruct a full 12-lead ECG in a proof-of-concept setting. Methods: A signal-processing framework was developed to preserve ECG morphology across sequential smartwatch lead recordings. The method is based on RR interval–guided temporal resampling, enabling interlead synchronization and analytical reconstruction of augmented limb leads. A prospective proof-of-concept clinical validation was conducted in 20 cases with diverse cardiac pathologies, including 1 healthy control. Smartwatch-derived ECGs were compared with standard 12-lead ECGs. Evaluation included expert-based clinical interpretation by 85 health care professionals and objective quantitative analysis of key electrocardiographic parameters, including heart rate, PR interval, QRS duration, QT interval, QTc, RR interval, P-wave duration, and PP interval. Mean values, SDs, and intermethod differences were calculated to assess agreement and variability. Results: Reconstruction of a 12-lead ECG from smartwatch-acquired signals was successfully achieved in all cases. Visual correlation scores between smartwatch-derived and conventional ECGs ranged from 78.1% to 91.3% across specialty-level means (mean 81.1, SD 22.7), indicating high perceived concordance; individual case-level scores ranged more widely, from 47.0% to 96.3%. Evaluator-perceived axis agreement reached 95.4% across all cases, while the investigators’ direct axis measurements showed complete concordance in all cases. Quantitative analysis demonstrated small mean differences between modalities, with particularly high agreement observed in structurally stable parameters such as heart rate (mean 77.2, SD 22.3 vs mean 75.9, SD 23.1 bpm; Δ=1.3 bpm) and PR interval (mean 176.2, SD 29.1 vs mean 180.8, SD 19.8 ms; Δ=−4.6 ms). Greater variability was observed in atrial activation parameters such as P-wave duration (Δ=−13.3 ms) and time-dependent parameters such as QT (Δ=−19.2 ms) and QTc (Δ=−12.7 ms). Conclusions: This proof-of-concept study demonstrates the feasibility of reconstructing a full 12-lead ECG from smartwatch-derived signals using a synchronization-based approach. The results demonstrated generally small mean differences between conventional and smartwatch-derived ECG measurements, although larger interval differences were observed in some individual cases. Importantly, due to the sequential nature of signal acquisition, the proposed methodology does not aim to achieve direct waveform equivalence but rather clinically meaningful agreement in electrocardiographic parameters. These findings support the potential of smartwatches as accessible tools for advanced cardiac monitoring and broaden their applicability beyond single-lead screening.
- 5 November 2026
- Published by JMIR Publications Inc. in JMIR Cardio
- Vol. 10, e86621
Open AccessGeneration of 12-Lead Electrocardiogram Using Smartwatches in Patients With Cardiac Conditions: Clinical Validation Study
Background: Smartwatches have significantly expanded personal health monitoring capabilities; however, their application in comprehensive cardiac assessment remains limited by single-lead electrocardiogram (ECG) acquisition. The inability to directly obtain augmented limb leads represents a major limitation for the evaluation of ischemic and arrhythmogenic conditions. Objective: This study aimed to present and preliminarily evaluate a methodology for generating augmented limb leads (augmented voltage right [aVR], augmented voltage left [aVL], and augmented voltage foot [aVF]) from sequential smartwatch recordings through signal synchronization and RR interval alignment, and to combine this approach with precordial smartwatch recordings to reconstruct a full 12-lead ECG in a proof-of-concept setting. Methods: A signal-processing framework was developed to preserve ECG morphology across sequential smartwatch lead recordings. The method is based on RR interval–guided temporal resampling, enabling interlead synchronization and analytical reconstruction of augmented limb leads. A prospective proof-of-concept clinical validation was conducted in 20 cases with diverse cardiac pathologies, including 1 healthy control. Smartwatch-derived ECGs were compared with standard 12-lead ECGs. Evaluation included expert-based clinical interpretation by 85 health care professionals and objective quantitative analysis of key electrocardiographic parameters, including heart rate, PR interval, QRS duration, QT interval, QTc, RR interval, P-wave duration, and PP interval. Mean values, SDs, and intermethod differences were calculated to assess agreement and variability. Results: Reconstruction of a 12-lead ECG from smartwatch-acquired signals was successfully achieved in all cases. Visual correlation scores between smartwatch-derived and conventional ECGs ranged from 78.1% to 91.3% across specialty-level means (mean 81.1, SD 22.7), indicating high perceived concordance; individual case-level scores ranged more widely, from 47.0% to 96.3%. Evaluator-perceived axis agreement reached 95.4% across all cases, while the investigators’ direct axis measurements showed complete concordance in all cases. Quantitative analysis demonstrated small mean differences between modalities, with particularly high agreement observed in structurally stable parameters such as heart rate (mean 77.2, SD 22.3 vs mean 75.9, SD 23.1 bpm; Δ=1.3 bpm) and PR interval (mean 176.2, SD 29.1 vs mean 180.8, SD 19.8 ms; Δ=−4.6 ms). Greater variability was observed in atrial activation parameters such as P-wave duration (Δ=−13.3 ms) and time-dependent parameters such as QT (Δ=−19.2 ms) and QTc (Δ=−12.7 ms). Conclusions: This proof-of-concept study demonstrates the feasibility of reconstructing a full 12-lead ECG from smartwatch-derived signals using a synchronization-based approach. The results demonstrated generally small mean differences between conventional and smartwatch-derived ECG measurements, although larger interval differences were observed in some individual cases. Importantly, due to the sequential nature of signal acquisition, the proposed methodology does not aim to achieve direct waveform equivalence but rather clinically meaningful agreement in electrocardiographic parameters. These findings support the potential of smartwatches as accessible tools for advanced cardiac monitoring and broaden their applicability beyond single-lead screening.
- Open Access
- 19 February 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 119
Peak Attention U-Net: Enhancing ECG delineation with attention
- 19 February 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 119
Open AccessPeak Attention U-Net: Enhancing ECG delineation with attention
- Open Access
- 16 December 2025
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 115
Performance evaluation of smartwatches: Can they match clinical standards for ECG analysis?
- 16 December 2025
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 115
Open AccessPerformance evaluation of smartwatches: Can they match clinical standards for ECG analysis?