{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T15:13:44Z","timestamp":1786115624227,"version":"build-2736575974"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T00:00:00Z","timestamp":1785974400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Psychol."],"abstract":"<jats:p>Reliable estimation of heart rate variability (HRV) from electrocardiography (ECG) depends on accurate detection of R-peaks, a task that becomes challenging in operational environments characterized by noise, motion artifacts, and monitoring-grade sensor configurations. While classical detection algorithms perform well under controlled conditions, their robustness is often limited in realistic settings. This study investigates whether artificial intelligence (AI)-based approaches can achieve robust R-peak detection in noisy operational ECG recordings, providing a reliable foundation for downstream HRV analysis. A physiologically constrained annotation framework was developed to generate temporally consistent reference annotations for evaluation of operational ECG recordings, while model training was performed exclusively using the MIT-BIH Arrhythmia Database with noise augmentation from the MIT-BIH Noise Stress Test Database. Two AI-based approaches were evaluated: a bidirectional Long Short-Term Memory (LSTM) network and a Transformer-based time-series foundation model (Mantis-8M) with task-specific output layers. Model performance was evaluated using both the MIT-BIH Arrhythmia Database and a real-world dataset comprising monitoring-grade ECG recordings from 30 participants acquired under operational conditions. The strongest-performing AI-based models achieved near-perfect benchmark performance (F1\u202f\u2248\u202f0.99) and maintained high accuracy under noisy conditions. On operational data, the LSTM model achieved the strongest overall performance (F1\u202f=\u202f0.96), substantially outperforming classical Pan\u2013Tompkins implementations and alternative AI architectures. Additional validation analyses demonstrated consistent performance across participants, low RR interval error, and minimal variability across repeated training runs, supporting the robustness and reproducibility of the proposed approach. The results demonstrate that AI-based R-peak detection preserves physiologically consistent beat-to-beat timing in noisy, monitoring-grade ECG recordings, providing a robust foundation for downstream HRV analysis. The study focuses on robustness in operational, non-clinical environments rather than diagnostic ECG interpretation. These findings support AI-based ECG analysis, trained on physiologically valid benchmark data, as a robust and reproducible foundation for real-time physiological monitoring in complex operational environments.<\/jats:p>","DOI":"10.3389\/fpsyg.2026.1892662","type":"journal-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T04:24:23Z","timestamp":1785990263000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Toward robust AI-based ECG R-peak detection for real-time physiological monitoring in operational environments"],"prefix":"10.3389","volume":"17","author":[{"given":"Maja","family":"Bostr\u00f6m","sequence":"first","affiliation":[{"name":"Division for Defence Technology, Department for Aeronautical Engineering, Swedish Defence Research Agency","place":["Stockholm, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik","family":"Jons\u00e4ll","sequence":"additional","affiliation":[{"name":"Division for Defence Technology, Department for Aeronautical Engineering, Swedish Defence Research Agency","place":["Stockholm, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fredrik","family":"Allenmark","sequence":"additional","affiliation":[{"name":"Division for Defence Technology, Department for Military Air Systems, Swedish Defence Research Agency","place":["Stockholm, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivier","family":"Amoignon","sequence":"additional","affiliation":[{"name":"Division for Defence Technology, Department for Aeronautical Engineering, Swedish Defence Research Agency","place":["Stockholm, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik","family":"Persson","sequence":"additional","affiliation":[{"name":"Division for Cyber Defence and C2 Technology, Department for Cognitive AI-systems, Swedish Defence Research Agency","place":["Stockholm, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guilherme H.","family":"Elcadi","sequence":"additional","affiliation":[{"name":"Division for Defence Technology, Department for Military Air Systems, Swedish Defence Research Agency","place":["Stockholm, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,6]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1111\/j.1469-8986.1997.tb02140.x","article-title":"Heart rate variability: origins, methods, and interpretive caveats","volume":"34","author":"Berntson","year":"1997","journal-title":"Psychophysiology"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1016\/0301-0511(95)05167-8","article-title":"Psychophysiological responses to changes in workload during simulated air traffic control","volume":"42","author":"Brookings","year":"1996","journal-title":"Biol. Psychol."},{"key":"ref3","first-page":"55","volume-title":"Advanced Methods and Tools for ECG Data Analysis","author":"Clifford","year":"2006"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1088\/0967-3334\/33\/9\/1419","article-title":"Signal quality indices and data fusion for determining clinical acceptability of electrocardiograms","volume":"33","author":"Clifford","year":"2012","journal-title":"Physiol. Meas."},{"key":"ref5","first-page":"1","volume-title":"2017 Computing in Cardiology (CinC)","author":"Clifford","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e73557","DOI":"10.1371\/journal.pone.0073557","article-title":"Fast QRS detection with an optimized knowledge-based method: evaluation on 11 standard ECG databases","volume":"8","author":"Elgendi","year":"2013","journal-title":"PLoS One"},{"key":"ref9001","first-page":"112","article-title":"Using heart rate variability and eye-tracking to differentiate simulator sickness severity rated by visual analogue scale","volume-title":"Virtual Reality","author":"Elcadi","year":"2026"},{"key":"ref7","first-page":"2502.15637","volume-title":"Mantis: Lightweight Calibrated Foundation model for user-Friendly time series Classifications","author":"Feofanov","year":"2025"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"e215","DOI":"10.1161\/01.cir.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"150611","DOI":"10.1109\/ACCESS.2020.3016705","article-title":"ETSI SmartBAN architecture: the global vision for smart body area networks","volume":"8","author":"H\u00e4m\u00e4l\u00e4inen","year":"2020","journal-title":"IEEE Access"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/s41591-018-0268-3","article-title":"Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network","volume":"25","author":"Hannun","year":"2019","journal-title":"Nat. Med."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"5979","DOI":"10.1038\/s41598-022-09954-8","article-title":"On evaluation metrics for medical applications of artificial intelligence","volume":"12","author":"Hicks","year":"2022","journal-title":"Sci. Rep."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1104","DOI":"10.1145\/3341105.3373945","volume-title":"Proceedings of the 35th Annual ACM Symposium on Applied Computing","author":"Laitala","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/10.362922","article-title":"Detection of ECG characteristic points using wavelet transforms","volume":"42","author":"Li","year":"1995","journal-title":"I.E.E.E. Trans. Biomed. Eng."},{"key":"ref15","first-page":"381","article-title":"A noise stress test for arrhythmia detectors","volume":"11","author":"Moody","year":"1984","journal-title":"Comput. Cardiol."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/TBME.1985.325532","article-title":"A real-time QRS detection algorithm","volume":"32","author":"Pan","year":"1985","journal-title":"I.E.E.E. Trans. Biomed. Eng."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1518\/001872008X288349","article-title":"Putting the brain to work: Neuroergonomics past, present, and future","volume":"50","author":"Parasuraman","year":"2008","journal-title":"Hum. Factors"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"258","DOI":"10.3389\/fpubh.2017.00258","article-title":"An overview of heart rate variability metrics and norms","volume":"5","author":"Shaffer","year":"2017","journal-title":"Front. Public Health"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1093\/oxfordjournals.eurheartj.a014868","article-title":"Heart rate variability. Standards of measurement, physiological interpretation, and clinical use","volume":"17","year":"1996","journal-title":"Eur. Heart J."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"6590","DOI":"10.3390\/s25216590","article-title":"Generalizable hybrid wavelet\u2013deep learning architecture for robust arrhythmia detection in wearable ECG monitoring","volume":"25","author":"Thapa","year":"2025","journal-title":"Sensors"},{"key":"ref21","volume-title":"Attention is All you Need. Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1207\/S15327108IJAP1201_2","article-title":"An analysis of mental workload in pilots during flight using multiple psychophysiological measures","volume":"12","author":"Wilson","year":"2002","journal-title":"Int. J. Aviat. Psychol."},{"key":"ref23","first-page":"2114","volume-title":"A Transformer-based Framework for Multivariate Time Series Representation Learning Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","author":"Zerveas","year":"2021"}],"container-title":["Frontiers in Psychology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyg.2026.1892662\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T04:24:25Z","timestamp":1785990265000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyg.2026.1892662\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,6]]},"references-count":24,"alternative-id":["10.3389\/fpsyg.2026.1892662"],"URL":"https:\/\/doi.org\/10.3389\/fpsyg.2026.1892662","relation":{},"ISSN":["1664-1078"],"issn-type":[{"value":"1664-1078","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,6]]},"article-number":"1892662"}}