Search

Aims Screening for atrial fibrillation (AF) is recommended in the European Society of Cardiology guidelines. Yields of detection can be low due to the paroxysmal nature of the disease. Prolonged heart rhythm monitoring might be needed to increase yield but can be cumbersome and expensive. The aim of this study was to observe the accuracy of an artificial intelligence (AI)-based network to predict paroxysmal AF from a normal sinus rhythm single-lead ECG. Methods and results A convolutional neural network model was trained and evaluated using data from three AF screening studies. A total of 478 963 single-lead ECGs from 14 831 patients aged ≥65 years were included in the analysis. The training set included ECGs from 80% of participants in SAFER and STROKESTOP II. The remaining ECGs from 20% of participants in SAFER and STROKESTOP II together with all participants in STROKESTOP I were included in the test set. The accuracy was estimated using the area under the receiver operating characteristic curve (AUC). From a single timepoint ECG, the artificial intelligence–based algorithm predicted paroxysmal AF in the SAFER study with an AUC of 0.80 [confidence interval (CI) 0.78–0.83], which had a wide age range of 65–90+ years. Performance was lower in the age-homogenous groups in STROKESTOP I and STROKESTOP II (age range: 75–76 years), with AUCs of 0.62 (CI 0.61–0.64) and 0.62 (CI 0.58–0.65), respectively. Conclusion An artificial intelligence–enabled network has the ability to predict AF from a sinus rhythm single-lead ECG. Performance improves with a wider age distribution.

Aging; Arteriosclerosis; Hemodynamics Envelliment; Arteriosclerosi; Hemodinàmica Envejecimiento; Arteriosclerosis; Hemodinámica Arterial pulse waves (PWs) such as blood pressure and photoplethysmogram (PPG) signals contain a wealth of information on the cardiovascular (CV) system that can be exploited to assess vascular age and identify individuals at elevated CV risk. We review the possibilities, limitations, complementarity, and differences of reduced-order, biophysical models of arterial PW propagation, as well as theoretical and empirical methods for analyzing PW signals and extracting clinically relevant information for vascular age assessment. We provide detailed mathematical derivations of these models and theoretical methods, showing how they are related to each other. Finally, we outline directions for future research to realize the potential of modeling and analysis of PW signals for accurate assessment of vascular age in both the clinic and in daily life. This article is based upon work from COST Action “Network for Research in Vascular Ageing” (VascAgeNet, CA18216), supported by COST (European Cooperation in Science and Technology, www.cost.eu). This work was supported by British Heart Foundation Grants PG/15/104/31913 (to J.A. and P.H.C.), FS/20/20/34626 (to P.H.C.), and AA/18/6/34223, PG/17/90/33415, SPG 2822621, and SP/F/21/150020 (to A.D.H.); Kaunas University of Technology Grant INP2022/16 (to B.P.); European Research Executive Agency, Marie-Sklodowska Curie Actions Individual Fellowship Grant 101038096 (to S.P.); Istinye University, BAP Project Grant 2019B1 (to S.P.); “la Caixa” Foundation Grant LCF/BQ/PR22/11920008 (to A.G.); and National Institute for Health and Care Research Grant AI AWARD02499 and EU Horizon 2020 Grant H2020 848109 (to A.D.H.).

Smart wearables provide an opportunity to monitor health in daily life and are emerging as potential tools for detecting cardiovascular disease (CVD). Wearables such as fitness bands and smartwatches routinely monitor the photoplethysmogram signal, an optical measure of the arterial pulse wave that is strongly influenced by the heart and blood vessels. In this survey, we summarize the fundamentals of wearable photoplethysmography and its analysis, identify its potential clinical applications, and outline pressing directions for future research in order to realize its full potential for tackling CVD., This work was supported by British Heart Foundation grants [PG/15/104/31913] and [FS/20/20/34626], the University of Cambridge EPSRC Impact Acceleration Account, the Wellcome EPSRC Centre for Medical Engineering at King’s College London [WT 203148/Z/16/Z], the European COST ACTION-Network for Research in Vascular Ageing CA18216 supported by COST (European Cooperation in Science and Technology), and the European Regional Development Fund (project No. 01.2.2-LMTK- 718-01-0030) under a grant agreement with the Research Council of Lithuania (LMTLT). The authors acknowledge: financial support from the Department of Health through the National Institute for Health Research Cardiovascular MedTech Co-operative at Guy’s and St Thomas’ NHS Foundation Trust.

Peer reviewed: True, Intervals of low-quality photoplethysmogram (PPG) signals might lead to significant inaccuracies in estimation of pulse arrival time (PAT) during polysomnography (PSG) studies. While PSG is considered to be a "gold standard" test for diagnosing obstructive sleep apnea (OSA), it also enables tracking apnea-related nocturnal blood pressure fluctuations correlated with PAT. Since the electrocardiogram (ECG) is recorded synchronously with the PPG during PSG, it makes sense to use the ECG signal for PPG signal-quality assessment. (1) Objective: to develop a PPG signal-quality assessment algorithm for robust PAT estimation, and investigate the influence of signal quality on PAT during various sleep stages and events such as OSA. (2) Approach: the proposed algorithm uses R and T waves from the ECG to determine approximate locations of PPG pulse onsets. The MESA database of 2055 PSG recordings was used for this study. (3) Results: the proportions of high-quality PPG were significantly lower in apnea-related oxygen desaturation (matched-pairs rc = 0.88 and rc = 0.97, compared to OSA and hypopnea, respectively, when p < 0.001) and arousal (rc = 0.93 and rc = 0.98, when p < 0.001) than in apnea events. The significantly large effect size of interquartile ranges of PAT distributions was between low- and high-quality PPG (p < 0.001, rc = 0.98), and regular and irregular pulse waves (p < 0.001, rc = 0.74), whereas a lower quality of the PPG signal was found to be associated with a higher interquartile range of PAT across all subjects. Suggested PPG signal quality-based PAT evaluation reduced deviations (e.g., rc = 0.97, rc = 0.97, rc = 0.99 in hypopnea, oxygen desaturation, and arousal stages, respectively, when p < 0.001) and allowed obtaining statistically larger differences between different sleep stages and events. (4) Significance: the implemented algorithm has the potential to increase the robustness of PAT estimation in PSG studies related to nocturnal blood pressure monitoring.

This editorial is driven by recent reports highlighting potential inaccuracies of pulse oximeters in patients with different skin pigmentations. The authors summarise the pertinent literature and provide an overview of the potential clinical implications. The editorial closes by providing insights into how pulse oximetry could be improved to mitigate against such potential shortcomings.

An introduction to wearables, the signals they acquire, and the underlying physiology on which wearable vascular ageing assessments are based., Presented on 9th May 2023 at the VascAgeNet Training School in Limassol, Cyprus.

Physiological measurement devices are widely integrated into clinical practice, ranging from blood pressure measurement in primary care, to continuous oxygen saturation monitoring in intensive care. Consumer wearables such as smartwatches potentially provide opportunity to monitor health and detect diseases unobtrusively outside of the clinical setting, in daily life. However, much work is required to establish pathways to use consumer wearables for clinical decision making. In this talk, Peter Charlton will present an introduction to consumer wearables, focusing on the capabilities provided by photoplethysmography and electrocardiography sensors. He will then summarise potential clinical applications, highlighting contributions from his research towards making these applications a reality. Finally, he will share some areas for consideration to ensure consumer wearables can be used robustly for clinical decision making.

Slides accompanying the 'Multimodal signal processing and learning for wearables' held on March 15th. Further details of the workshop are available at: -https://peterhcharlton.github.io/talk/multimodal-signal-processing-and-learning-for-wearables/ -https://peterhcharlton.github.io/bsp-book