Detection of Atrial Fibrillation Using a Ring-Type Wearable Device (CardioTracker) and Deep Learning Analysis of Photoplethysmography Signals: Prospective Observational Proof-of-Concept Study

Photoplethysmography based atrial fibrillation detection: a continually growing field

Objective. Atrial fibrillation (AF) is a prevalent cardiac arrhythmia associated with significant health ramifications, including an elevated susceptibility to ischemic stroke, heart disease, and heightened mortality. Photoplethysmography (PPG) has emerged as a promising technology for continuous AF monitoring for its cost-effectiveness and widespread integration into wearable devices. Our team previously conducted an exhaustive review on PPG-based AF detection before June 2019. However, since then, more advanced technologies have emerged in this field.Approach. This paper offers a comprehensive review of the latest advancements in PPG-based AF detection, utilizing digital health and artificial intelligence (AI) solutions, within the timeframe spanning from July 2019 to December 2022. Through extensive exploration of scientific databases, we have identified 57 pertinent studies.Significance. Our comprehensive review encompasses an in-depth assessment of the statistical methodologies, traditional machine learning techniques, and deep learning approaches employed in these studies. In addition, we address the challenges encountered in the domain of PPG-based AF detection. Furthermore, we maintain a dedicated website to curate the latest research in this area, with regular updates on a regular basis.

Advances and Opportunities of Mobile Health in the Postpandemic Era: Smartphonization of Wearable Devices and Wearable Deviceization of Smartphones

Mobile health (mHealth) with continuous real-time monitoring is leading the era of digital medical convergence. Wearable devices and smartphones optimized as personalized health management platforms enable disease prediction, prevention, diagnosis, and even treatment. Ubiquitous and accessible medical services offered through mHealth strengthen universal health coverage to facilitate service use without discrimination. This viewpoint investigates the latest trends in mHealth technology, which are comprehensive in terms of form factors and detection targets according to body attachment location and type. Insights and breakthroughs from the perspective of mHealth sensing through a new form factor and sensor-integrated display overcome the problems of existing mHealth by proposing a solution of smartphonization of wearable devices and the wearable deviceization of smartphones. This approach maximizes the infinite potential of stagnant mHealth technology and will present a new milestone leading to the popularization of mHealth. In the postpandemic era, innovative mHealth solutions through the smartphonization of wearable devices and the wearable deviceization of smartphones could become the standard for a new paradigm in the field of digital medicine.

Machine Learning Prediction for the Recurrence After Electrical Cardioversion of Patients With Persistent Atrial Fibrillation

BACKGROUND AND OBJECTIVES

There is limited evidence regarding machine-learning prediction for the recurrence of atrial fibrillation (AF) after electrical cardioversion (ECV). This study aimed to predict the recurrence of AF after ECV using machine learning of clinical features and electrocardiograms (ECGs) in persistent AF patients.

METHODS

We analyzed patients who underwent successful ECV for persistent AF. Machine learning was designed to predict patients with 1-month recurrence. Individual 12-lead ECGs were collected before and after ECV. Various clinical features were collected and trained the extreme gradient boost (XGBoost)-based model. Ten-fold cross-validation was used to evaluate the performance of the model. The performance was compared to the C-statistics of the selected clinical features.

RESULTS

Among 718 patients (mean age 63.5±9.3 years, men 78.8%), AF recurred in 435 (60.6%) patients after 1 month. With the XGBoost-based model, the areas under the receiver operating characteristic curves (AUROCs) were 0.57, 0.60, and 0.63 if the model was trained by clinical features, ECGs, and both (the final model), respectively. For the final model, the sensitivity, specificity, and F1-score were 84.7%, 28.2%, and 0.73, respectively. Although the AF duration showed the best predictive performance (AUROC, 0.58) among the clinical features, it was significantly lower than that of the final machine-learning model (p<0.001). Additional training of extended monitoring data of 15-minute single-lead ECG and photoplethysmography in available patients (n=261) did not significantly improve the model's performance.

CONCLUSIONS

Machine learning showed modest performance in predicting AF recurrence after ECV in persistent AF patients, warranting further validation studies.

Classification of Continuous ECG Segments - Performance Analysis of a Deep Learning Model

Classification of electrocardiogram (ECG) signals plays an important role in the diagnosis of heart diseases. It is a complex and non-linear signal, which is the first option to preliminary identify specific pathologies/conditions (e.g., arrhythmias). Currently, the scientific community has proposed a multitude of intelligent systems to automatically process the ECG signal, through deep learning techniques, as well as machine learning, where this present high performance, showing state-of-the-art results. However, most of these models are designed to analyze the ECG signal individually, i.e., segment by segment. The scientific community states that to diagnose a pathology in the ECG signal, it is not enough to analyze a signal segment corresponding to the cardiac cycle, but rather an analysis of successive segments of cardiac cycles, to identify a pathological pattern.In this paper, an intelligent method based on a Convolutional Neural Network 1D paired with a Multilayer Perceptron (CNN 1D+MLP) was evaluated to automatically diagnose a set of pathological conditions, from the analysis of the individual segment of the cardiac cycle. In particular, we intend to study the robustness of the referred method in the analysis of several simultaneous ECG signal segments. Two ECG signal databases were selected, namely: MIT-BIH Arrhythmia Database (D1) and European ST-T Database (D2). The data was processed to create datasets with two, three and five segments in a row, to train and test the performance of the method. The method was evaluated in terms of classification metrics, such as: precision, recall, f1-score, and accuracy, as well as through the calculation of confusion matrices.Overall, the method demonstrated high robustness in the analysis of successive ECG signal segments, which we can conclude that it has the potential to detect anomalous patterns in the ECG signal. In the future, we will use this method to analyze the ECG signal coming in real-time, acquired by a wearable device, through a cloud system.Clinical Relevance-This study evaluates the potential of a deep learning method to classify one or several segments of the cardiac cycle and diagnose pathologies in ECG signals.

Continuous cuffless blood pressure monitoring using photoplethysmography-based PPG2BP-net for high intrasubject blood pressure variations

Continuous, comfortable, convenient (C3), and accurate blood pressure (BP) measurement and monitoring are needed for early diagnosis of various cardiovascular diseases. To supplement the limited C3 BP measurement of existing cuff-based BP technologies, though they may achieve reliable accuracy, cuffless BP measurement technologies, such as pulse transit/arrival time, pulse wave analysis, and image processing, have been studied to obtain C3 BP measurement. One of the recent cuffless BP measurement technologies, innovative machine-learning and artificial intelligence-based technologies that can estimate BP by extracting BP-related features from photoplethysmography (PPG)-based waveforms have attracted interdisciplinary attention of the medical and computer scientists owing to their handiness and effectiveness for both C3 and accurate, i.e., C3A, BP measurement. However, C3A BP measurement remains still unattainable because the accuracy of the existing PPG-based BP methods was not sufficiently justified for subject-independent and highly varying BP, which is a typical case in practice. To circumvent this issue, a novel convolutional neural network(CNN)- and calibration-based model (PPG2BP-Net) was designed by using a comparative paired one-dimensional CNN structure to estimate highly varying intrasubject BP. To this end, approximately [Formula: see text], [Formula: see text], and [Formula: see text] of 4185 cleaned, independent subjects from 25,779 surgical cases were used for training, validating, and testing the proposed PPG2BP-Net, respectively and exclusively (i.e., subject-independent modelling). For quantifying the intrasubject BP variation from an initial calibration BP, a novel 'standard deviation of subject-calibration centring (SDS)' metric is proposed wherein high SDS represents high intrasubject BP variation from the calibration BP and vice versa. PPG2BP-Net achieved accurately estimated systolic and diastolic BP values despite high intrasubject variability. In 629-subject data acquired after 20 minutes following the A-line (arterial line) insertion, low error mean and standard deviation of [Formula: see text] and [Formula: see text] for highly varying A-line systolic and diastolic BP values, respectively, where their SDSs are 15.375 and 8.745. This study moves one step forward in developing the C3A cuffless BP estimation devices that enable the push and agile pull services.

Artificial intelligence in cardiovascular prevention: new ways will open new doors

Prevention and effective treatment of cardiovascular disease are progressive issues that grow in tandem with the average age of the world population. Over recent decades, the potential role of artificial intelligence in cardiovascular medicine has been increasingly recognized because of the incredible amount of real-world data (RWD) regarding patient health status and healthcare delivery that can be collated from a variety of sources wherein patient information is routinely collected, including patient registries, clinical case reports, reimbursement claims and billing reports, medical devices, and electronic health records. Like any other (health) data, RWD can be analysed in accordance with high-quality research methods, and its analysis can deliver valuable patient-centric insights complementing the information obtained from conventional clinical trials. Artificial intelligence application on RWD has the potential to detect a patient's health trajectory leading to personalized medicine and tailored treatment. This article reviews the benefits of artificial intelligence in cardiovascular prevention and management, focusing on diagnostic and therapeutic improvements without neglecting the limitations of this new scientific approach.

Wearable Multisensor Ring-Shaped Probe for Assessing Stress and Blood Oxygenation: Design and Preliminary Measurements

The increasing interest in innovative solutions for health and physiological monitoring has recently fostered the development of smaller biomedical devices. These devices are capable of recording an increasingly large number of biosignals simultaneously, while maximizing the user's comfort. In this study, we have designed and realized a novel wearable multisensor ring-shaped probe that enables synchronous, real-time acquisition of photoplethysmographic (PPG) and galvanic skin response (GSR) signals. The device integrates both the PPG and GSR sensors onto a single probe that can be easily placed on the finger, thereby minimizing the device footprint and overall size. The system enables the extraction of various physiological indices, including heart rate (HR) and its variability, oxygen saturation (SpO₂), and GSR levels, as well as their dynamic changes over time, to facilitate the detection of different physiological states, e.g., rest and stress. After a preliminary SpO₂ calibration procedure, measurements have been carried out in laboratory on healthy subjects to demonstrate the feasibility of using our system to detect rapid changes in HR, skin conductance, and SpO₂ across various physiological conditions (i.e., rest, sudden stress-like situation and breath holding). The early findings encourage the use of the device in daily-life conditions for real-time monitoring of different physiological states.

Novel Technologies in the Detection of Atrial Fibrillation: Review of Literature and Comparison of Different Novel Technologies for Screening of Atrial Fibrillation

Atrial fibrillation (AF) is globally the most common arrhythmia associated with significant morbidity and mortality. It impairs the quality of the patient's life, imposing a remarkable burden on public health, and the healthcare budget. The detection of AF is important in the decision to initiate anticoagulation therapy to prevent thromboembolic events. Nonetheless, AF detection is still a major clinical challenge as AF is often paroxysmal and asymptomatic. AF screening recommendations include opportunistic or systematic screening in patients ≥65 years of age or in those individuals with other characteristics pointing to an increased risk of stroke. The popularities of well-being and taking personal responsibility for one's own health are reflected in the continuous development and growth of mobile health technologies. These novel mobile health technologies could provide a cost-effective solution for AF screening and an additional opportunity to detect AF, particularly its paroxysmal and asymptomatic forms.

Wearables in Cardiovascular Disease

Wearable devices stand to revolutionize the way healthcare is delivered. From consumer devices that provide general health information and screen for medical conditions to medical-grade devices that allow collection of larger datasets that include multiple modalities, wearables have a myriad of potential uses, especially in cardiovascular disorders. In this review, we summarize the underlying technologies employed in these devices and discuss the regulatory and economic aspects of such devices as well as the future implications of their use.

ESC Working Group on e-Cardiology Position Paper: accuracy and reliability of electrocardiogram monitoring in the detection of atrial fibrillation in cryptogenic stroke patients : In collaboration with the Council on Stroke, the European Heart Rhythm Association, and the Digital Health Committee

The role of subclinical atrial fibrillation as a cause of cryptogenic stroke is unambiguously established. Long-term electrocardiogram (ECG) monitoring remains the sole method for determining its presence following a negative initial workup. This position paper of the European Society of Cardiology Working Group on e-Cardiology first presents the definition, epidemiology, and clinical impact of cryptogenic ischaemic stroke, as well as its aetiopathogenic association with occult atrial fibrillation. Then, classification methods for ischaemic stroke will be discussed, along with their value in providing meaningful guidance for further diagnostic efforts, given disappointing findings of studies based on the embolic stroke of unknown significance construct. Patient selection criteria for long-term ECG monitoring, crucial for determining pre-test probability of subclinical atrial fibrillation, will also be discussed. Subsequently, the two major classes of long-term ECG monitoring tools (non-invasive and invasive) will be presented, with a discussion of each method's pitfalls and related algorithms to improve diagnostic yield and accuracy. Although novel mobile health (mHealth) devices, including smartphones and smartwatches, have dramatically increased atrial fibrillation detection post ischaemic stroke, the latest evidence appears to favour implantable cardiac monitors as the modality of choice; however, the answer to whether they should constitute the initial diagnostic choice for all cryptogenic stroke patients remains elusive. Finally, institutional and organizational issues, such as reimbursement, responsibility for patient management, data ownership, and handling will be briefly touched upon, despite the fact that guidance remains scarce and widespread clinical application and experience are the most likely sources for definite answers.

Wearable Devices for Physical Monitoring of Heart: A Review

Cardiovascular diseases (CVDs) are the leading cause of death globally. An effective strategy to mitigate the burden of CVDs has been to monitor patients’ biomedical variables during daily activities with wearable technology. Nowadays, technological advance has contributed to wearables technology by reducing the size of the devices, improving the accuracy of sensing biomedical variables to be devices with relatively low energy consumption that can manage security and privacy of the patient’s medical information, have adaptability to any data storage system, and have reasonable costs with regard to the traditional scheme where the patient must go to a hospital for an electrocardiogram, thus contributing a serious option in diagnosis and treatment of CVDs. In this work, we review commercial and noncommercial wearable devices used to monitor CVD biomedical variables. Our main findings revealed that commercial wearables usually include smart wristbands, patches, and smartwatches, and they generally monitor variables such as heart rate, blood oxygen saturation, and electrocardiogram data. Noncommercial wearables focus on monitoring electrocardiogram and photoplethysmography data, and they mostly include accelerometers and smartwatches for detecting atrial fibrillation and heart failure. However, using wearable devices without healthy personal habits will cause disappointing results in the patient’s health.

Mobile health technology in atrial fibrillation

INTRODUCTION

Mobile health (mHealth) solutions in atrial fibrillation (AF) are becoming widespread, thanks to everyday life devices such as smartphones. Their use is validated both in monitoring and in screening scenarios. In the published literature, the diagnostic accuracy of mHealth solutions wide differs, and their current clinical use is not well established in principal guidelines.

AREAS COVERED

mHealth solutions have progressively built an AF-detection chain to guide patients from the device's alert signal to the health care practitioners' (HCPs) attention. This review aims to critically evaluate the latest evidence regarding mHealth devices and the future possible patient's uses in everyday life.

EXPERT OPINION

The patients are the first to be informed of the rhythm anomaly, leading to the urgency of increasing the patients' AF self-management. Furthermore, HCPs need to update themselves about mHealth devices use in clinical practice. Nevertheless, these are promising instruments in specific populations, such as post-stroke patients, to promote an early arrhythmia diagnosis in the post-ablation/cardioversion period, allowing checks on the efficacy of the treatment or intervention.

Application of photoplethysmography signals for healthcare systems: An in-depth review

BACKGROUND AND OBJECTIVES

Photoplethysmography (PPG) is a device that measures the amount of light absorbed by the blood vessel, blood, and tissues, which can, in turn, translate into various measurements such as the variation in blood flow volume, heart rate variability, blood pressure, etc. Hence, PPG signals can produce a wide variety of biological information that can be useful for the detection and diagnosis of various health problems. In this review, we are interested in the possible health disorders that can be detected using PPG signals.

METHODS

We applied PRISMA guidelines to systematically search various journal databases and identified 43 PPG studies that fit the criteria of this review.

RESULTS

Twenty-five health issues were identified from these studies that were classified into six categories: cardiac, blood pressure, sleep health, mental health, diabetes, and miscellaneous. Various routes were employed in these PPG studies to perform the diagnosis: machine learning, deep learning, and statistical routes. The studies were reviewed and summarized.

CONCLUSIONS

We identified limitations such as poor standardization of sampling frequencies and lack of publicly available PPG databases. We urge that future work should consider creating more publicly available databases so that a wide spectrum of health problems can be covered. We also want to promote the use of PPG signals as a potential precision medicine tool in both ambulatory and hospital settings.

The Impact of Wearable Technologies in Health Research: Scoping Review

Background

Wearable devices hold great promise, particularly for data generation for cutting-edge health research, and their demand has risen substantially in recent years. However, there is a shortage of aggregated insights into how wearables have been used in health research.

Objective

In this review, we aim to broadly overview and categorize the current research conducted with affordable wearable devices for health research.

Methods

We performed a scoping review to understand the use of affordable, consumer-grade wearables for health research from a population health perspective using the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) framework. A total of 7499 articles were found in 4 medical databases (PubMed, Ovid, Web of Science, and CINAHL). Studies were eligible if they used noninvasive wearables: worn on the wrist, arm, hip, and chest; measured vital signs; and analyzed the collected data quantitatively. We excluded studies that did not use wearables for outcome assessment and prototype studies, devices that cost >€500 (US $570), or obtrusive smart clothing.

Results

We included 179 studies using 189 wearable devices covering 10,835,733 participants. Most studies were observational (128/179, 71.5%), conducted in 2020 (56/179, 31.3%) and in North America (94/179, 52.5%), and 93% (10,104,217/10,835,733) of the participants were part of global health studies. The most popular wearables were fitness trackers (86/189, 45.5%) and accelerometer wearables, which primarily measure movement (49/189, 25.9%). Typical measurements included steps (95/179, 53.1%), heart rate (HR; 55/179, 30.7%), and sleep duration (51/179, 28.5%). Other devices measured blood pressure (3/179, 1.7%), skin temperature (3/179, 1.7%), oximetry (3/179, 1.7%), or respiratory rate (2/179, 1.1%). The wearables were mostly worn on the wrist (138/189, 73%) and cost <€200 (US $228; 120/189, 63.5%). The aims and approaches of all 179 studies revealed six prominent uses for wearables, comprising correlations—wearable and other physiological data (40/179, 22.3%), method evaluations (with subgroups; 40/179, 22.3%), population-based research (31/179, 17.3%), experimental outcome assessment (30/179, 16.8%), prognostic forecasting (28/179, 15.6%), and explorative analysis of big data sets (10/179, 5.6%). The most frequent strengths of affordable wearables were validation, accuracy, and clinical certification (104/179, 58.1%).

Conclusions

Wearables showed an increasingly diverse field of application such as COVID-19 prediction, fertility tracking, heat-related illness, drug effects, and psychological interventions; they also included underrepresented populations, such as individuals with rare diseases. There is a lack of research on wearable devices in low-resource contexts. Fueled by the COVID-19 pandemic, we see a shift toward more large-sized, web-based studies where wearables increased insights into the developing pandemic, including forecasting models and the effects of the pandemic. Some studies have indicated that big data extracted from wearables may potentially transform the understanding of population health dynamics and the ability to forecast health trends.

Machine Learning for Cardiovascular Outcomes From Wearable Data: Systematic Review From a Technology Readiness Level Point of View

BACKGROUND

Wearable technology has the potential to improve cardiovascular health monitoring by using machine learning. Such technology enables remote health monitoring and allows for the diagnosis and prevention of cardiovascular diseases. In addition to the detection of cardiovascular disease, it can exclude this diagnosis in symptomatic patients, thereby preventing unnecessary hospital visits. In addition, early warning systems can aid cardiologists in timely treatment and prevention.

OBJECTIVE

This study aims to systematically assess the literature on detecting and predicting outcomes of patients with cardiovascular diseases by using machine learning with data obtained from wearables to gain insights into the current state, challenges, and limitations of this technology.

METHODS

We searched PubMed, Scopus, and IEEE Xplore on September 26, 2020, with no restrictions on the publication date and by using keywords such as "wearables," "machine learning," and "cardiovascular disease." Methodologies were categorized and analyzed according to machine learning-based technology readiness levels (TRLs), which score studies on their potential to be deployed in an operational setting from 1 to 9 (most ready).

RESULTS

After the removal of duplicates, application of exclusion criteria, and full-text screening, 55 eligible studies were included in the analysis, covering a variety of cardiovascular diseases. We assessed the quality of the included studies and found that none of the studies were integrated into a health care system (TRL<6), prospective phase 2 and phase 3 trials were absent (TRL<7 and 8), and group cross-validation was rarely used. These issues limited these studies' ability to demonstrate the effectiveness of their methodologies. Furthermore, there seemed to be no agreement on the sample size needed to train these studies' models, the size of the observation window used to make predictions, how long participants should be observed, and the type of machine learning model that is suitable for predicting cardiovascular outcomes.

CONCLUSIONS

Although current studies show the potential of wearables to monitor cardiovascular events, their deployment as a diagnostic or prognostic cardiovascular clinical tool is hampered by the lack of a realistic data set and proper systematic and prospective evaluation.

Deep Learning-Assisted Burn Wound Diagnosis: Diagnostic Model Development Study

BACKGROUND

Accurate assessment of the percentage total body surface area (%TBSA) of burn wounds is crucial in the management of burn patients. The resuscitation fluid and nutritional needs of burn patients, their need for intensive unit care, and probability of mortality are all directly related to %TBSA. It is difficult to estimate a burn area of irregular shape by inspection. Many articles have reported discrepancies in estimating %TBSA by different doctors.

OBJECTIVE

We propose a method, based on deep learning, for burn wound detection, segmentation, and calculation of %TBSA on a pixel-to-pixel basis.

METHODS

A 2-step procedure was used to convert burn wound diagnosis into %TBSA. In the first step, images of burn wounds were collected from medical records and labeled by burn surgeons, and the data set was then input into 2 deep learning architectures, U-Net and Mask R-CNN, each configured with 2 different backbones, to segment the burn wounds. In the second step, we collected and labeled images of hands to create another data set, which was also input into U-Net and Mask R-CNN to segment the hands. The %TBSA of burn wounds was then calculated by comparing the pixels of mask areas on images of the burn wound and hand of the same patient according to the rule of hand, which states that one's hand accounts for 0.8% of TBSA.

RESULTS

A total of 2591 images of burn wounds were collected and labeled to form the burn wound data set. The data set was randomly split into training, validation, and testing sets in a ratio of 8:1:1. Four hundred images of volar hands were collected and labeled to form the hand data set, which was also split into 3 sets using the same method. For the images of burn wounds, Mask R-CNN with ResNet101 had the best segmentation result with a Dice coefficient (DC) of 0.9496, while U-Net with ResNet101 had a DC of 0.8545. For the hand images, U-Net and Mask R-CNN had similar performance with DC values of 0.9920 and 0.9910, respectively. Lastly, we conducted a test diagnosis in a burn patient. Mask R-CNN with ResNet101 had on average less deviation (0.115% TBSA) from the ground truth than burn surgeons.

CONCLUSIONS

This is one of the first studies to diagnose all depths of burn wounds and convert the segmentation results into %TBSA using different deep learning models. We aimed to assist medical staff in estimating burn size more accurately, thereby helping to provide precise care to burn victims.

Deep Learning-Based Data-Point Precise R-Peak Detection in Single-Lead Electrocardiograms

Low-cost wearables with capability to record electrocardiograms (ECG) are becoming increasingly available. These wearables typically acquire single-lead ECGs that are mainly used for screening of cardiac arrhythmias such as atrial fibrillation. Most arrhythmias are characteruzed by changes in the RR-interval, hence automatic methods to diagnose arrythmia may utilize R-peak detection. Existing R-peak detection methods are fairly accurate but have limited precision. To enable data-point precise detection of R-peaks, we propose a method that uses a fully convolutional dilated neural network. The network is trained and evaluated with manually annotated R-peaks in a heterogeneous set of ECGs that contain a wide range of cardiac rhythms and acquisition noise. 700 randomly chosen ECGs from the PhysioNet/CinC challenge 2017 were used for training (n=500), validation (n=100) and testing (n=100). The network achieves a precision of 0.910, recall of 0.926, and an F1-score of 0.918 on the test set. Our data-point precise R-peak detector may be important step towards fully automatic cardiac arrhythmia detection.Clinical relevance- This method enables data-point precise detection of R-peaks that provides a basis for detection and characterization of arrhythmias.

Using Transfer Learning Method to Develop an Artificial Intelligence Assisted Triaging for Endotracheal Tube Position on Chest X-ray

Endotracheal tubes (ETTs) provide a vital connection between the ventilator and patient; however, improper placement can hinder ventilation efficiency or injure the patient. Chest X-ray (CXR) is the most common approach to confirming ETT placement; however, technicians require considerable expertise in the interpretation of CXRs, and formal reports are often delayed. In this study, we developed an artificial intelligence-based triage system to enable the automated assessment of ETT placement in CXRs. Three intensivists performed a review of 4293 CXRs obtained from 2568 ICU patients. The CXRs were labeled "CORRECT" or "INCORRECT" in accordance with ETT placement. A region of interest (ROI) was also cropped out, including the bilateral head of the clavicle, the carina, and the tip of the ETT. Transfer learning was used to train four pre-trained models (VGG16, INCEPTION_V3, RESNET, and DENSENET169) and two models developed in the current study (VGG16_Tensor Projection Layer and CNN_Tensor Projection Layer) with the aim of differentiating the placement of ETTs. Only VGG16 based on ROI images presented acceptable performance (AUROC = 92%, F1 score = 0.87). The results obtained in this study demonstrate the feasibility of using the transfer learning method in the development of AI models by which to assess the placement of ETTs in CXRs.

Mobile health applications for the detection of atrial fibrillation: a systematic review

AIMS

Atrial fibrillation (AF) is the most common sustained arrhythmia and an important risk factor for stroke and heart failure. We aimed to conduct a systematic review of the literature and summarize the performance of mobile health (mHealth) devices in diagnosing and screening for AF.

METHODS AND RESULTS

We conducted a systematic search of MEDLINE, Embase, and the Cochrane Central Register of Controlled Trials. Forty-three studies met the inclusion criteria and were divided into two groups: 28 studies aimed at validating smart devices for AF diagnosis, and 15 studies used smart devices to screen for AF. Evaluated technologies included smartphones, with photoplethysmographic (PPG) pulse waveform measurement or accelerometer sensors, smartbands, external electrodes that can provide a smartphone single-lead electrocardiogram (iECG), such as AliveCor, Zenicor and MyDiagnostick, and earlobe monitor. The accuracy of these devices depended on the technology and the population, AliveCor and smartphone PPG sensors being the most frequent systems analysed. The iECG provided by AliveCor demonstrated a sensitivity and specificity between 66.7% and 98.5% and 99.4% and 99.0%, respectively. The PPG sensors detected AF with a sensitivity of 85.0-100% and a specificity of 93.5-99.0%. The incidence of newly diagnosed arrhythmia ranged from 0.12% in a healthy population to 8% among hospitalized patients.

CONCLUSION

Although the evidence for clinical effectiveness is limited, these devices may be useful in detecting AF. While mHealth is growing in popularity, its clinical, economic, and policy implications merit further investigation. More head-to-head comparisons between mHealth and medical devices are needed to establish their comparative effectiveness.

Virtual Reality for Sedation During Atrial Fibrillation Ablation in Clinical Practice: Observational Study

Background

Connected devices are dramatically changing many aspects in health care. One such device, the virtual reality (VR) headset, has recently been shown to improve analgesia in a small sample of patients undergoing transcatheter aortic valve implantation.

Objective

We aimed to investigate the feasibility and effectiveness of VR in patients undergoing atrial fibrillation (AF) ablation under conscious sedation.

Methods

All patients who underwent an AF ablation with VR from March to May 2020 were included. Patients were compared to a consecutive cohort of patients who underwent AF ablation in the 3 months prior to the study. Primary efficacy was assessed by using a visual analog scale, summarizing the overall pain experienced during the ablation.

Results

The AF cryoablation procedure with VR was performed for 48 patients (mean age 63.0, SD 10.9 years; n=16, 33.3% females). No patient refused to use the device, although 14.6% (n=7) terminated the VR session prematurely. Preparation of the VR headset took on average 78 (SD 13) seconds. Compared to the control group, the mean perceived pain, assessed with the visual analog scale, was lower in the VR group (3.5 [SD 1.5] vs 4.3 [SD 1.6]; P=.004), and comfort was higher in the VR group (7.5 [SD 1.6] vs 6.8 [SD 1.7]; P=.03). On the other hand, morphine consumption was not different between the groups. Lastly, complications, as well as procedure and fluoroscopy duration, were not different between the two groups.

Conclusions

We found that VR was associated with a reduction in the perception of pain in patients undergoing AF ablation under conscious sedation. Our findings demonstrate that VR can be easily incorporated into the standard ablation workflow.

Wearable sensors for continuous oral cavity and dietary monitoring toward personalized healthcare and digital medicine

Oral monitoring plays an essential role in preventing and diagnosing systemic diseases through saliva in the mouth. Dietary monitoring is also crucial to reduce the likelihood of chronic diseases such as hypertension and diabetes by analyzing food types, amounts and diet patterns. Therefore, the oral cavity and dietary monitoring are vital for accurate personalized healthcare management that can improve healthcare. To perform continuous oral cavity and dietary monitoring in real-time, a wearable sensing system capable of continuous analysis is necessary. In this review, we classify chemical and physical biosensing methods and summarize recent progress in wearable sensor development for oral cavity and dietary monitoring for personalized healthcare and digital medicine. We also discuss future perspectives and the potential of wearable sensors to provide robust data for food-intake monitoring and the saliva analysis of super-aged/aging societies, non-face-to-face social life, and global pandemic disease issues. We believe that this review will result in a paradigm shift toward personalized healthcare and digital medicine using wearable sensors through the analysis of massively parallel healthcare data.

How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management

There has been an exponential growth of artificial intelligence (AI) and machine learning (ML) publications aimed at advancing our understanding of atrial fibrillation (AF), which has been mainly driven by the confluence of two factors: the advances in deep neural networks (DeepNNs) and the availability of large, open access databases. It is observed that most of the attention has centred on applying ML for dvsetecting AF, particularly using electrocardiograms (ECGs) as the main data modality. Nearly a third of them used DeepNNs to minimize or eliminate the need for transforming the ECGs to extract features prior to ML modelling; however, we did not observe a significant advantage in following this approach. We also found a fraction of studies using other data modalities, and others centred in aims, such as risk prediction, AF management, and others. From the clinical perspective, AI/ML can help expand the utility of AF detection and risk prediction, especially for patients with additional comorbidities. The use of AI/ML for detection and risk prediction into applications and smart mobile health (mHealth) technology would enable ‘real time’ dynamic assessments. AI/ML could also adapt to treatment changes over time, as well as incident risk factors. Incorporation of a dynamic AI/ML model into mHealth technology would facilitate ‘real time’ assessment of stroke risk, facilitating mitigation of modifiable risk factors (e.g. blood pressure control). Overall, this would lead to an improvement in clinical care for patients with AF.

Detection of Atrial Fibrillation Using a Machine Learning Approach

The atrial fibrillation (AF) is one of the most well-known cardiac arrhythmias in clinical practice, with a prevalence of 1–2% in the community, which can increase the risk of stroke and myocardial infarction. The detection of AF electrocardiogram (ECG) can improve the early detection of diagnosis. In this paper, we have further developed a framework for processing the ECG signal in order to determine the AF episodes. We have implemented machine learning and deep learning algorithms to detect AF. Moreover, the experimental results show that better performance can be achieved with long short-term memory (LSTM) as compared to other algorithms. The initial experimental results illustrate that the deep learning algorithms, such as LSTM and convolutional neural network (CNN), achieved better performance (10%) as compared to machine learning classifiers, such as support vectors, logistic regression, etc. This preliminary work can help clinicians in AF detection with high accuracy and less probability of errors, which can ultimately result in reduction in fatality rate.

Premature Atrial and Ventricular Contraction Detection using Photoplethysmographic Data from a Smartwatch

We developed an algorithm to detect premature atrial contraction (PAC) and premature ventricular contraction (PVC) using photoplethysmographic (PPG) data acquired from a smartwatch. Our PAC/PVC detection algorithm is composed of a sequence of algorithms that are combined to discriminate various arrhythmias. A novel vector resemblance method is used to enhance the PAC/PVC detection results of the Poincaré plot method. The new PAC/PVC detection algorithm with our automated motion and noise artifact detection approach yielded a sensitivity of 86% for atrial fibrillation (AF) subjects while the overall sensitivity was 67% when normal sinus rhythm (NSR) subjects were also included. The specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy values for the combined data consisting of both NSR and AF subjects were 97%, 81%, 94% and 92%, respectively, for PAC/PVC detection combined with our automated motion and noise artifact detection approach. Moreover, when AF detection was compared with and without PAC/PVC, the sensitivity and specificity increased from 94.55% to 98.18% and from 95.75% to 97.90%, respectively. For additional independent testing data, we used two datasets: a smartwatch PPG dataset that was collected in our ongoing clinical study, and a pulse oximetry PPG dataset from the Medical Information Mart for Intensive Care III database. The PAC/PVC classification results of the independent testing on these two other datasets are all above 92% for sensitivity, specificity, PPV, NPV, and accuracy. The proposed combined approach to detect PAC and PVC can ultimately lead to better accuracy in AF detection. This is one of the first studies involving detection of PAC and PVC using PPG recordings from a smartwatch. The proposed method can potentially be of clinical importance as this enhanced capability can lead to fewer false positive detections of AF, especially for those NSR subjects with frequent episodes of PAC/PVC.