Single-lead Electrocardiography Research Articles

Development of Pediatric Hypokalemia Prediction Deep-Learning System Based on Wearable Single-Lead Electrocardiography in Real Time

Development of Pediatric Hypokalemia Prediction Deep-Learning System Based on Wearable Single-Lead Electrocardiography in Real Time

EfficientNet-based machine learning architecture for sleep apnea identification in clinical single-lead ECG signal data sets

ObjectiveOur objective was to create a machine learning architecture capable of identifying obstructive sleep apnea (OSA) patterns in single-lead electrocardiography (ECG) signals, exhibiting exceptional performance when utilized in clinical data sets.MethodsWe conducted our research using a data set consisting of 1656 patients, representing a diverse demographic, from the sleep center of China Medical University Hospital. To detect apnea ECG segments and extract apnea features, we utilized the EfficientNet and some of its layers, respectively. Furthermore, we compared various training and data preprocessing techniques to enhance the model’s prediction, such as setting class and sample weights or employing overlapping and regular slicing. Finally, we tested our approach against other literature on the Apnea-ECG database.ResultsOur research found that the EfficientNet model achieved the best apnea segment detection using overlapping slicing and sample-weight settings, with an AUC of 0.917 and an accuracy of 0.855. For patient screening with AHI > 30, we combined the trained model with XGBoost, leading to an AUC of 0.975 and an accuracy of 0.928. Additional tests using PhysioNet data showed that our model is comparable in performance to existing models regarding its ability to screen OSA levels.ConclusionsOur suggested architecture, coupled with training and preprocessing techniques, showed admirable performance with a diverse demographic dataset, bringing us closer to practical implementation in OSA diagnosis.Trial registration The data for this study were collected retrospectively from the China Medical University Hospital in Taiwan with approval from the institutional review board CMUH109-REC3-018.

A Comprehensive Study on a Deep-Learning-Based Electrocardiography Analysis for Estimating the Apnea-Hypopnea Index.

This study introduces a deep-learning-based automatic sleep scoring system to detect sleep apnea using a single-lead electrocardiography (ECG) signal, focusing on accurately estimating the apnea-hypopnea index (AHI). Unlike other research, this work emphasizes AHI estimation, crucial for the diagnosis and severity evaluation of sleep apnea. The suggested model, trained on 1465 ECG recordings, combines the deep-shallow fusion network for sleep apnea detection network (DSF-SANet) and gated recurrent units (GRUs) to analyze ECG signals at 1-min intervals, capturing sleep-related respiratory disturbances. Achieving a 0.87 correlation coefficient with actual AHI values, an accuracy of 0.82, an F1 score of 0.71, and an area under the receiver operating characteristic curve of 0.88 for per-segment classification, our model was effective in identifying sleep-breathing events and estimating the AHI, offering a promising tool for medical professionals.

Artificial Intelligence Interpretation of the Electrocardiogram: A State-of-the-Art Review.

Artificial intelligence (AI) is transforming electrocardiography (ECG) interpretation. AI diagnostics can reach beyond human capabilities, facilitate automated access to nuanced ECG interpretation, and expand the scope of cardiovascular screening in the population. AI can be applied to the standard 12-lead resting ECG and single-lead ECGs in external monitors, implantable devices, and direct-to-consumer smart devices. We summarize the current state of the literature on AI-ECG. Rhythm classification was the first application of AI-ECG. Subsequently, AI-ECG models have been developed for screening structural heart disease including hypertrophic cardiomyopathy, cardiac amyloidosis, aortic stenosis, pulmonary hypertension, and left ventricular systolic dysfunction. Further, AI models can predict future events like development of systolic heart failure and atrial fibrillation. AI-ECG exhibits potential in acute cardiac events and non-cardiac applications, including acute pulmonary embolism, electrolyte abnormalities, monitoring drugs therapy, sleep apnea, and predicting all-cause mortality. Many AI models in the domain of cardiac monitors and smart watches have received Food and Drug Administration (FDA) clearance for rhythm classification, while others for identification of cardiac amyloidosis, pulmonary hypertension and left ventricular dysfunction have received breakthrough device designation. As AI-ECG models continue to be developed, in addition to regulatory oversight and monetization challenges, thoughtful clinical implementation to streamline workflows, avoiding information overload and overwhelming of healthcare systems with false positive results is necessary. Research to demonstrate and validate improvement in healthcare efficiency and improved patient outcomes would be required before widespread adoption of any AI-ECG model.

Facilitating ambulatory heart rate variability analysis using accelerometry-based classifications of body position and self-reported sleep

Objective. This study aimed to examine differences in heart rate variability (HRV) across accelerometer-derived position, self-reported sleep, and different summary measures (sleep, 24 h HRV) in free-living settings using open-source methodology. Approach. HRV is a biomarker of autonomic activity. As it is strongly affected by factors such as physical behaviour, stress, and sleep, ambulatory HRV analysis is challenging. Beat-to-beat heart rate (HR) and accelerometry data were collected using single-lead electrocardiography and trunk- and thigh-worn accelerometers among 160 adults participating in the SCREENS trial. HR files were processed and analysed in the RHRV R package. Start time and duration spent in physical behaviours were extracted, and time and frequency analysis for each episode was performed. Differences in HRV estimates across activities were compared using linear mixed models adjusted for age and sex with subject ID as random effect. Next, repeated-measures Bland–Altman analysis was used to compare 24 h RMSSD estimates to HRV during self-reported sleep. Sensitivity analyses evaluated the accuracy of the methodology, and the approach of employing accelerometer-determined episodes to examine activity-independent HRV was described. Main results. HRV was estimated for 31 289 episodes in 160 individuals (53.1% female) at a mean age of 41.4 years. Significant differences in HR and most markers of HRV were found across positions [Mean differences RMSSD: Sitting (Reference) − Standing (−2.63 ms) or Lying (4.53 ms)]. Moreover, ambulatory HRV differed significantly across sleep status, and poor agreement between 24 h estimates compared to sleep HRV was detected. Sensitivity analyses confirmed that removing the first and last 30 s of accelerometry-determined HR episodes was an accurate strategy to account for orthostatic effects. Significance. Ambulatory HRV differed significantly across accelerometry-assigned positions and sleep. The proposed approach for free-living HRV analysis may be an effective strategy to remove confounding by physical activity when the aim is to monitor general autonomic stress.

Automated identification of atrial fibrillation from single-lead ECGs using multi-branching ResNet.

Introduction: Atrial fibrillation (AF) is the most common cardiac arrhythmia, which is clinically identified with irregular and rapid heartbeat rhythm. AF puts a patient at risk of forming blood clots, which can eventually lead to heart failure, stroke, or even sudden death. Electrocardiography (ECG), which involves acquiring bioelectrical signals from the body surface to reflect heart activity, is a standard procedure for detecting AF. However, the occurrence of AF is often intermittent, costing a significant amount of time and effort from medical doctors to identify AF episodes. Moreover, human error is inevitable, as even experienced medical professionals can overlook or misinterpret subtle signs of AF. As such, it is of critical importance to develop an advanced analytical model that can automatically interpret ECG signals and provide decision support for AF diagnostics. Methods: In this paper, we propose an innovative deep-learning method for automated AF identification using single-lead ECGs. We first extract time-frequency features from ECG signals using continuous wavelet transform (CWT). Second, the convolutional neural networks enhanced with residual learning (ReNet) are employed as the functional approximator to interpret the time-frequency features extracted by CWT. Third, we propose to incorporate a multi-branching structure into the ResNet to address the issue of class imbalance, where normal ECGs significantly outnumber instances of AF in ECG datasets. Results and Discussion: We evaluate the proposed Multi-branching Resnet with CWT (CWT-MB-Resnet) with two ECG datasets, i.e., PhysioNet/CinC challenge 2017 and ECGs obtained from the University of Oklahoma Health Sciences Center (OUHSC). The proposed CWT-MB-Resnet demonstrates robust prediction performance, achieving an F1 score of 0.8865 for the PhysioNet dataset and 0.7369 for the OUHSC dataset. The experimental results signify the model's superior capability in balancing precision and recall, which is a desired attribute for ensuring reliable medical diagnoses.

Detection of myocardial infarction using Shannon energy envelope, FA-MVEMD and deterministic learning

Myocardial infarction (MI) poses a significant clinical challenge, necessitating expeditious and precise detection to mitigate potentially fatal outcomes. Current MI diagnosis predominantly relies on electrocardiography (ECG); however, it is fraught with limitations, including inter-observer variability and a reliance on expert interpretation. This study introduces an automated MI detection framework that capitalizes on hybrid signal processing methodologies and deterministic learning theory. The initial step involves the extraction of the Shannon energy envelope (SEE) and its derivative from a single-lead ECG. Integration of the SEE into the ECG’s phase portrait provides a means to capture the underlying nonlinear system dynamics. Subsequently, the application of fast and adaptive multivariate empirical mode decomposition (FA-MVEMD) yields discriminative features originating from the most energetically dominant intrinsic mode components (IMFs) within the SEE. Profound dissimilarities are discernible between ECG signals recorded from healthy subjects and those afflicted with MI. In the subsequent phase, deterministic learning theory, implemented through neural networks, is employed to facilitate the classification of ECG signals into two distinct groups. The method’s efficacy is meticulously evaluated using the PTB diagnostic ECG database, resulting in a noteworthy average classification accuracy of 99.21%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} within a tenfold cross-validation framework. In summation, the findings affirm that the proposed features not only complement conventional ECG attributes but also align closely with the underlying dynamics of the ECG system, ultimately fortifying the automatic detection of MI. The imperative requirement for early and accurate MI diagnosis is addressed through our approach, offering a robust and dependable means to fulfill this pivotal clinical need.

Real-world validation of smartphone-based photoplethysmography for rate and rhythm monitoring in atrial fibrillation.

Photoplethysmography- (PPG) based smartphone applications facilitate heart rate and rhythm monitoring in patients with paroxysmal and persistent atrial fibrillation (AF). Despite an endorsement from the European Heart Rhythm Association, validation studies in this setting are lacking. Therefore, we evaluated the accuracy of PPG-derived heart rate and rhythm classification in subjects with an established diagnosis of AF in unsupervised real-world conditions. Fifty consecutive patients were enrolled, 4 weeks before undergoing AF ablation. Patients used a handheld single-lead electrocardiography (ECG) device and a fingertip PPG smartphone application to record 3907 heart rhythm measurements twice daily during 8 weeks. The ECG was performed immediately before and after each PPG recording and was given a diagnosis by the majority of three blinded cardiologists. A consistent ECG diagnosis was exhibited along with PPG data of sufficient quality in 3407 measurements. A single measurement exhibited good quality more often with ECG (93.2%) compared to PPG (89.5%; P < 0.001). However, PPG signal quality improved to 96.6% with repeated measurements. Photoplethysmography-based detection of AF demonstrated excellent sensitivity [98.3%; confidence interval (CI): 96.7-99.9%], specificity (99.9%; CI: 99.8-100.0%), positive predictive value (99.6%; CI: 99.1-100.0%), and negative predictive value (99.6%; CI: 99.0-100.0%). Photoplethysmography underestimated the heart rate in AF with 6.6 b.p.m. (95% CI: 5.8 b.p.m. to 7.4 b.p.m.). Bland-Altman analysis revealed increased underestimation in high heart rates. The root mean square error was 11.8 b.p.m. Smartphone applications using PPG can be used to monitor patients with AF in unsupervised real-world conditions. The accuracy of AF detection algorithms in this setting is excellent, but PPG-derived heart rate may tend to underestimate higher heart rates.

Identifying patients with acute aortic dissection using an electrocardiogram with convolutional neural network

BackgroundThe potential of utilizing artificial intelligence with electrocardiography (ECG) for initial screening of aortic dissection (AD) is promising. However, achieving a high positive predictive rate (PPR) remains challenging. Methods and resultsThis retrospective analysis of a single-center, prospective cohort study (Shinken Database 2010–2017, N = 19,170) used digital 12-lead ECGs from initial patient visits. We assessed a convolutional neural network (CNN) model's performance for AD detection with eight-lead (I, II, and V1-6), single-lead, and double-lead (I, II) ECGs via five-fold cross-validation. The mean age was 63.5 ± 12.5 years for the AD group (n = 147) and 58.1 ± 15.7 years for the non-AD group (n = 19,023). The CNN model achieved an area under the curve (AUC) of 0.936 (standard deviation [SD]: 0.023) for AD detection with eight-lead ECGs. In the entire cohort, the PPR was 7 %, with 126 out of 147 AD cases correctly diagnosed (sensitivity 86 %). When applied to patients with D-dimer levels ≥1 μg/dL and a history of hypertension, the PPR increased to 35 %, with 113 AD cases correctly identified (sensitivity 86 %). The single V1 lead displayed the highest diagnostic performance (AUC: 0.933, SD: 0.03), with PPR improvement from 8 % to 38 % within the same population. ConclusionsOur CNN model using ECG data for AD detection achieved an over 30% PPR when applied to patients with elevated D-dimer levels and hypertension history while maintaining sensitivity. A similar level of performance was observed with a single-lead V1 ECG in the CNN model.

New-onset hypertension as a contributing factor to the incidence of atrial fibrillation in the elderly.

Hypertension and atrial fibrillation are closely related. However, hypertension is already prevalent in young adults, but atrial fibrillation usually occurs in the elderly. In the present analysis, we investigated incident atrial fibrillation in relation to new-onset hypertension in an elderly Chinese population. Our study participants were elderly (≥65 years) hypertensive residents, recruited from community health centers in the urban Shanghai (n = 4161). Previous and new-onset hypertension were defined as the use of antihypertensive medication or elevated systolic/diastolic blood pressure (≥140/90 mmHg), respectively, at entry and during follow-up on ≥ 2 consecutive clinic visits. Atrial fibrillation was detected by a 30-s single-lead electrocardiography (ECG, AliveCor® Heart Monitor) and further evaluated with a regular 12-lead ECG. During a median of 2.1 years follow-up, the incidence rate of atrial fibrillation was 7.60 per 1000 person-years in all study participants; it was significantly higher in patients with new-onset hypertension (n = 368) than those with previous hypertension (n = 3793, 15.76 vs. 6.77 per 1000 person-years, P = 0.02). After adjustment for confounding factors, the hazard ratio for the incidence of atrial fibrillation was 2.21 (95% confidence interval 1.15-4.23, P = 0.02) in patients with new-onset hypertension versus those with previous hypertension. The association was even stronger in those aged ≥ 75 years (hazard ratio 2.70, 95% confidence interval 1.11-6.56, P = 0.03). In patients with previous hypertension, curvilinear association (P for non-linear trend = 0.04) was observed between duration of hypertension and the risk of incident atrial fibrillation, with a higher risk in short- and long-term than mid-term duration of hypertension. Our study showed a significant association between new-onset hypertension and the incidence of atrial fibrillation in elderly Chinese. In an elderly Chinese population with previous and new-onset hypertension, we found that the new-onset hypertension during follow-up, compared with previous hypertension, was associated with a significantly higher risk of incident atrial fibrillation. In patients with previous hypertension, curvilinear association was observed between duration of hypertension and the risk of incident atrial fibrillation, with a higher risk in short- and long-term than mid-term duration of hypertension.

Multi-Feature Automatic Extraction for Detecting Obstructive Sleep Apnea Based on Single-Lead Electrocardiography Signals.

Obstructive sleep apnea (OSA), a prevalent sleep disorder, is intimately associated with various other diseases, particularly cardiovascular conditions. The conventional diagnostic method, nocturnal polysomnography (PSG), despite its widespread use, faces challenges due to its high cost and prolonged duration. Recent developments in electrocardiogram-based diagnostic techniques have opened new avenues for addressing these challenges, although they often require a deep understanding of feature engineering. In this study, we introduce an innovative method for OSA classification that combines a composite deep convolutional neural network model with a multimodal strategy for automatic feature extraction. This approach involves transforming the original dataset into scalogram images that reflect heart rate variability attributes and Gramian angular field matrix images that reveal temporal characteristics, aiming to enhance the diversity and richness of data features. The model comprises automatic feature extraction and feature enhancement components and has been trained and validated on the PhysioNet Apnea-ECG database. The experimental results demonstrate the model's exceptional performance in diagnosing OSA, achieving an accuracy of 96.37%, a sensitivity of 94.67%, a specificity of 97.44%, and an AUC of 0.96. These outcomes underscore the potential of our proposed model as an efficient, accurate, and convenient tool for OSA diagnosis.

SleepMI: An AI-based screening algorithm for myocardial infarction using nocturnal electrocardiography

Myocardial infarction (MI) is a common cardiovascular disease, the early diagnosis of which is essential for effective treatment and reduced mortality. Therefore, novel methods are required for automatic screening or early diagnosis of MI, and many studies have proposed diverse conventional methods for its detection. In this study, we aimed to develop a sleep-myocardial infarction (sleepMI) algorithm for automatic screening of MI based on nocturnal electrocardiography (ECG) findings from diagnostic polysomnography (PSG) data using artificial intelligence (AI) models. The proposed sleepMI algorithm was designed using representation and ensemble learning methods and optimized via dropout and batch normalization. In the sleepMI algorithm, a deep convolutional neural network and light gradient boost machine (LightGBM) models were mixed to obtain robust and stable performance for screening MI from nocturnal ECG findings. The nocturnal ECG signal was extracted from 2,691 participants (2,331 healthy individuals and 360 patients with MI) from the PSG data of the second follow-up stage of the Sleep Heart Health Study. The nocturnal ECG signal was extracted 3 h after sleep onset and segmented at 30-s intervals for each participant. All ECG datasets were divided into training, validation, and test sets consisting of 574,729, 143,683, and 718,412 segments, respectively. The proposed sleepMI model exhibited very high performance with precision, recall, and F1-score of 99.38%, 99.38%, and 99.38%, respectively. The total mean accuracy for automatic screening of MI using a nocturnal single-lead ECG was 99.387%. MI events can be detected using conventional 12-lead ECG signals and polysomnographic ECG recordings using our model.

Classification feasibility test on multi-lead electrocardiography signals generated from single-lead electrocardiography signals.

Nowadays, Electrocardiogram (ECG) signals can be measured using wearable devices, such as smart watches. Most wearable devices provide only a few details; however, they have the advantage of recording data in real time. In this study, 12-lead ECG signals were generated from lead I and their feasibility was tested to obtain more details. The 12-lead ECG signals were generated using a U-net-based generative adversarial network (GAN) that was trained on ECG data obtained from the Asan Medical Center. Subsequently, unseen PTB-XL PhysioNet data were used to produce real 12-lead ECG signals for classification. The generated and real 12-lead ECG signals were then compared using a ResNet classification model; and the normal, atrial fibrillation (A-fib), left bundle branch block (LBBB), right bundle branch block (RBBB), left ventricular hypertrophy (LVH), and right ventricular hypertrophy (RVH) were classified. The mean precision, recall, and f1-score for the real 12-lead ECG signals are 0.70, 0.72, and 0.70, and that for the generated 12-lead ECG signals are 0.82, 0.80, and 0.81, respectively. In our study, according to the result generated 12-lead ECG signals performed better than real 12-lead ECG.

Consumer-grade wearable cardiac monitors: What they do well, and what needs work.

Consumer-grade smart devices, including smartwatches and smartphones, are potentially valuable tools in detecting cardiac arrhythmias, particularly atrial fibrillation, and their use is increasing. These devices, which use photoplethys mography, show remarkably high sensitivity and specificity for detection of atrial fibrillation, with implications for stroke prevention and management in at-risk patients. The ability of the devices to detect atrial fibrillation is being compared with single-lead electrocardiography. Physicians will increasingly be asked to interpret data from these nonmedical-grade devices as they become more common. Limitations include high false-positive rates in certain populations and disparities in access.

Comparison of Digital Filter Orders in Single Lead Electrocardiographic Design for Reducing Interference Motion Artifact

Developed a new method to overcome motion artifacts in Electrocardiogram (ECG) signals, which often interfere with accurate clinical analysis. Motion artifacts, such as body movements, can cause significant distortions in the ECG signal, resulting in incorrect interpretation and affecting medical diagnosis. The main objective of this research is to design and implement an infinite impulse response (IIR) filter with a predetermined sequence, namely orders 2, 4, 6, and 8 to reduce motion artifacts in the ECG signal. We aim to improve ECG signal quality by preserving important ECG signal information and reducing noise caused by motion artifacts. This research contributes to developing more precise and reliable ECG signal processing techniques. The proposed method provides an effective approach to handling motion artifacts, enabling more accurate and reliable ECG interpretation by medical professionals. We used an ECG simulator that provides body movement simulation as a basis for experiments. The detected ECG signal is processed with a predetermined order IIR filter. We compare the filtered signal to the original signal to measure the effectiveness of reducing motion artifacts. Experimental results show that the applied IIR filter efficiently reduces motion artifacts in the ECG signal. The SNR assessment showed a significant improvement, proving the success of this method in maintaining ECG signal quality. The result is that in the 2nd order, the SNR value is 22.25 dB, in the 4th order the SNR value is 22.75 dB, in the 6th order the SNR value is 22.99 dB, in the 6th order the SNR value is 22.99 dB. 8 obtained an SNR value of 23dB. This study successfully demonstrated that using IIR filters in a specified order effectively reduces motion artifacts in the ECG signal, increases SNR, and maintains the integrity of clinical information in the ECG signal. The implications of this research extend to medical technology development and clinical applications, providing a strong foundation for continued research in more efficient and reliable ECG signal processing.

Evaluation of a smartphone electrocardiograph in healthy foals and comparison to standard base-apex electrocardiography

Smartphone-based technology for ECG recording has recently spread as a complementary tool for electrocardiographic screening and monitoring in adult horses and in other animal species. The present study aimed to assess the feasibility and accuracy of a smartphone-based ECG in healthy foals. This was a prospective observational study (authorization n. 45,865/2016) including 22 foals aged less than 21 days. A reference standard base-apex ECG (rECG) was acquired, and a smartphone ECG (sECG) was recorded immediately after by using a smartphone-based single lead electrocardiograph. All ECG tracings were evaluated in a blind fashion by a single board-certified cardiologist, who judged whether the tracings were acceptable for interpretation and performed ECG measurements and diagnosis. The Spearman correlation coefficient, the Cohen’s k test and the Bland-Altman test were used to assess the agreement between sECG and rECG. All sECG tracings were acceptable for interpretation. All foals showed sinus rhythm on both rRCG and sECG tracings, with perfect agreement in heart rate classification (κ = 0.87; p < 0.001). No clinically relevant differences were found in the assessment of waves and intervals duration. Concerning P wave and QRS complex polarity, the percentage of agreement between rECG and sECG was 78% and 83%, respectively. About ECG tracing quality, rECG and sECG showed a substantial agreement (κ = 0.624; p < 0.001). In conclusion, the smartphone-based ECG device tested in the present study recorded good quality single-lead ECG tracings in foals, reliable for heart rate and ECG measurements, but different polarity of P waves and QRS complexes was found in some foals in comparison to rECG.

Screening for atrial fibrillation by village doctors in rural areas of china: the jiangsu province rural community atrial fibrillation project

Abstract Background No study has systematically investigated the quality of long-term care delivered to the rural elderly with chronic diseases in China. Since atrial fibrillation (AF) is becoming an increasing burden on healthcare systems worldwide. Purpose We conducted an AF screening programme in rural elderly and evaluated healthcare efficiency led by the village doctors in China. Methods This cross-sectional study of the rural population aged ≥65 years was conducted from April to June 2019 in our towns of Jiangsu Province. AF was identified using 12-lead electrocardiography in the first-step (government-led health examination) and single-lead electrocardiography in the second-step (in-house AF screening). Questionnaire surveys were designed for the AF patients and their village doctors, respectively. Results Among the 31,342 registered subjects, 12,630 (40·3%) declined, 7,956 (25·3%) participated in the first-step and 10,756 (34·3%) in the second-step (Figure 1). The overall AF detection rate was 4·3% (810/18,712). Of the 810 patients with AF (mean age 76·1±5·9 years; 51·4% female), 51·5% had education level below primary school, 2·6% could use smartphone applications, and 8·1% lived with their children. Common risk factors were older age, men, hypertension, diabetes, prior stroke, vascular disease, and congestive heart failure. Among the 402 patients who were aware of AF, there were 367 were at high risk of stroke (CHA2DS2-VASc score ≥3 in women or ≥2 in men) and OAC was currently used in only 10·9% (40/367) of these (Figure 2). Only 17·6% (91/516) of patients with known hypertension had a resting blood pressure level &amp;lt;140/90 mmHg, and 6·0% (8/132) of patients with known diabetes had a fasting blood glucose level ≤6·1 mmol/L. Our questionnaire survey for village doctors showed that only 7·3% (9/122) reported having the knowledge or ability for providing integrated care AF management. Conclusions This screening project in rural villages identified AF in 4·3%, but AF management was suboptimal with low use of oral anticoagulation. The current village doctor-dominant rural healthcare system is far from delivering optimal standardized AF management for older patients in rural China. There is a urgent need to support these rural clinics and empower the village doctors in optimising the care of AF patients.The flow chart of this studyThe use of oral anticoagulation

Diagnostic accuracy of handheld single-lead electrocardiographic devices to detect atrial fibrillation: an examination using more than 30,000 rhythm traces in a randomised control trial

Abstract Background Early atrial fibrillation (AF) diagnosis offers an opportunity to initiate management to reduce stroke risk. Hand-held single-lead electrocardiograph (ECG) devices are widely available, yet there is little data on the implementation of AF screening using the devices in high-AF-risk communities and examining the accuracy of the devices over time. Such data may provide insights into the possibility of using artificial intelligence to scale up screening. Purpose To examine the accuracy of AliveCor ECG devices’ automated interpretation against clinicians’ diagnoses and explore the characteristics of the ECGs of older community-dwelling people in a real-world setting. Methods This is an analysis of ECGs received from people aged ≥75 years participating in an implementation trial of a community AF screening program over 12 months. Clinicians reviewed all ECGs transmitted to a central portal. Clinicians’ interpretations were taken as diagnostically accurate. Participants and their general practitioners (GPs) were notified of AF. The devices’ automatic ECG interpretations, including the participants’ pulse rates automatically recorded by the devices, were extracted from the central portal and analysed using R v3.6.0. Results 200 participants were enrolled. From May 2021 to Feb 2023, 30,040 ECGs were received; of these traces, clinicians confirmed AF in 479 traces and no AF in 29,561 traces. The devices’ automatic algorithm had a sensitivity of 91.4 % (i.e., detected AF in 438 of these 479 traces) and specificity of 96.6% (no AF: 28,546 / 29,561 traces). In total, the devices’ automated interpretation identified 1,453 ECGs with "Possible AF", of which clinicians confirmed 911 (62.7%) were in sinus rhythm and 438 (30.1%) had AF (Table 1). Breaking down the statistics for various rhythms and comparing the devices’ automatic algorithms with the clinicians’ diagnoses, discrepancies were found in 5296 ECG traces (Kappa = 0.33). Of these, 4277 (80.8%) were interpreted by the device automated algorithm as "Unreadable" (interferences), "Unclassified" (the device was unable to determine a result), and "Too short" (&amp;lt; 30 seconds of recording). Excluding the 3799 "Unclassified’ traces, the level of agreement between the ECG devices and clinicians improved (Kappa 0.63). The device automatically reported "Unclassified" and "Possible AF" rhythm traces had wide dispersion of the participants’ pulse rates (Figure 1). Conclusions The ECG devices had high sensitivity to detect AF but a low level of agreement in differentiating various rhythms. The characteristics of the longitudinal ECG rhythm traces, including the participants’ pulse rates over time coupled with the clinicians’ diagnoses of this large dataset, could be used to improve the devices’ automated algorithm and inform artificial intelligence strategies for large-scale community AF screening programs.Table 1Figure 1

Your smartphone could act as a pulse-oximeter and as a single-lead ECG

In the post-covid19 era, every new wave of the pandemic causes an increased concern/interest among the masses to learn more about their state of well-being. Therefore, it is the need of the hour to come up with ubiquitous, low-cost, non-invasive tools for rapid and continuous monitoring of body vitals that reflect the status of one’s overall health. In this backdrop, this work proposes a deep learning approach to turn a smartphone—the popular hand-held personal gadget—into a diagnostic tool to measure/monitor the three most important body vitals, i.e., pulse rate (PR), blood oxygen saturation level (aka SpO2), and respiratory rate (RR). Furthermore, we propose another method that could extract a single-lead electrocardiograph (ECG) of the subject. The proposed methods include the following core steps: subject records a small video of his/her fingertip by placing his/her finger on the rear camera of the smartphone, and the recorded video is pre-processed to extract the filtered and/or detrended video-photoplethysmography (vPPG) signal, which is then fed to custom-built convolutional neural networks (CNN), which eventually spit-out the vitals (PR, SpO2, and RR) as well as a single-lead ECG of the subject. To be precise, the contribution of this paper is twofold: (1) estimation of the three body vitals (PR, SpO2, RR) from the vPPG data using custom-built CNNs, vision transformer, and most importantly by CLIP model (a popular image-caption-generator model); (2) a novel discrete cosine transform+feedforward neural network-based method that translates the recorded video-PPG signal to a single-lead ECG signal. The significance of this work is twofold: (i) it allows rapid self-testing of body vitals (e.g., self-monitoring for covid19 symptoms), (ii) it enables rapid self-acquisition of a single-lead ECG, and thus allows early detection of atrial fibrillation (abormal heart beat or arrhythmia), which in turn could enable early intervention in response to a range of cardiovascular diseases, and could help save many precious lives. Our work could help reduce the burden on healthcare facilities and could lead to reduction in health insurance costs.

Multiscale entropy analysis of single lead ECG and ECG derived respiration for AI based prediction of sleep apnea events

Sleep apnea (SA) is a prevalent sleep disorder that affects a significant portion of the adult population. The proposed method involves coarse graining a signal at different scales, using the popular multiscale entropy algorithms to detect apnea and normal events from single lead Electrocardiography (ECG), Instantaneous Heart Rate and ECG derived respiration. The idea of nonlinear dynamical systems analysis for feature extraction along with machine learning approach, the authors present here a moderately accurate sleep apnea detection model with an accuracy ranging from 70% to 100% based on two different probabilistic thresholds of 50 % and 70% with reduction in false positive rate from 28% to 14 % for applications in development of AI based IoT connected smart wearable devices. The two thresholding modes offer a choice to do a trade-off between high training accuracy with high false positive rate and low accuracy with low false positive rate. The performance metrics of each model have been reported and choice is made for best suitable model with prospectives of implementation for diagnostic purposes. The effectiveness of the proposed method in accurate detection of sleep apnea requires further validation of the models with out of distribution dataset.