Diagnostic assessment of a deep learning system for detecting atrial fibrillation in pulse waveforms

Development and Validation of Artificial Intelligence-Based Algorithms for Predicting the Segments Debulked by Rotational Atherectomy Using Intravascular Ultrasound Images

We develop and evaluate an artificial intelligence (AI)-based algorithm that uses pre-rotation atherectomy (RA) intravascular ultrasound (IVUS) images to automatically predict regions debulked by RA. A total of 2106 IVUS cross-sections from 60 patients with de novo severely calcified coronary lesions who underwent IVUS-guided RA were consecutively collected. The 2 identical IVUS images of pre- and post-RA were merged, and the orientations of the debulked segments identified in the merged images were marked on the outer circle of each IVUS image. The AI model was developed based on ResNet (deep residual learning for image recognition). The architecture connected 36 fully connected layers, each corresponding to 1 of the 36 orientations segmented every 10°, to a single feature extractor. In each cross-sectional analysis, our AI model achieved an average sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 81%, 72%, 46%, 90%, and 75%, respectively. In conclusion, the AI-based algorithm can use information from pre-RA IVUS images to accurately predict regions debulked by RA and will assist interventional cardiologists in determining the treatment strategies for severely calcified coronary lesions.

Automatic detection of cardiac conditions from photos of electrocardiogram captured by smartphones

BACKGROUND

Researchers have developed machine learning-based ECG diagnostic algorithms that match or even surpass cardiologist level of performance. However, most of them cannot be used in real-world, as older generation ECG machines do not permit installation of new algorithms.

OBJECTIVE

To develop a smartphone application that automatically extract ECG waveforms from photos and to convert them to voltage-time series for downstream analysis by a variety of diagnostic algorithms built by researchers.

METHODS

A novel approach of using objective detection and image segmentation models to automatically extract ECG waveforms from photos taken by clinicians was devised. Modular machine learning models were developed to sequentially perform waveform identification, gridline removal, and scale calibration. The extracted data were then analysed using a machine learning-based cardiac rhythm classifier.

RESULTS

Waveforms from 40 516 scanned and 444 photographed ECGs were automatically extracted. 12 828 of 13 258 (96.8%) scanned and 5399 of 5743 (94.0%) photographed waveforms were correctly cropped and labelled. 11 604 of 12 735 (91.1%) scanned and 5062 of 5752 (88.0%) photographed waveforms achieved successful voltage-time signal extraction after automatic gridline and background noise removal. In a proof-of-concept demonstration, an atrial fibrillation diagnostic algorithm achieved 91.3% sensitivity, 94.2% specificity, 95.6% positive predictive value, 88.6% negative predictive value and 93.4% F1 score, using photos of ECGs as input.

CONCLUSION

Object detection and image segmentation models allow automatic extraction of ECG signals from photos for downstream diagnostics. This novel pipeline circumvents the need for costly ECG hardware upgrades, thereby paving the way for large-scale implementation of machine learning-based diagnostic algorithms.

Learning From Alarms: A Robust Learning Approach for Accurate Photoplethysmography-Based Atrial Fibrillation Detection Using Eight Million Samples Labeled With Imprecise Arrhythmia Alarms

Atrial fibrillation (AF) is a common cardiac arrhythmia with serious health consequences if not detected and treated early. Detecting AF using wearable devices with photoplethysmography (PPG) sensors and deep neural networks has demonstrated some success using proprietary algorithms in commercial solutions. However, to improve continuous AF detection in ambulatory settings towards a population-wide screening use case, we face several challenges, one of which is the lack of large-scale labeled training data. To address this challenge, we propose to leverage AF alarms from bedside patient monitors to label concurrent PPG signals, resulting in the largest PPG-AF dataset so far (8.5 M 30-second records from 24,100 patients) and demonstrating a practical approach to build large labeled PPG datasets. Furthermore, we recognize that the AF labels thus obtained contain errors because of false AF alarms generated from imperfect built-in algorithms from bedside monitors. Dealing with label noise with unknown distribution characteristics in this case requires advanced algorithms. We, therefore, introduce and open-source a novel loss design, the cluster membership consistency (CMC) loss, to mitigate label errors. By comparing CMC with state-of-the-art methods selected from a noisy label competition, we demonstrate its superiority in handling label noise in PPG data, resilience to poor-quality signals, and computational efficiency.

Adopting artificial intelligence in cardiovascular medicine: a scoping review

Recent years have witnessed significant transformations in cardiovascular medicine, driven by the rapid evolution of artificial intelligence (AI). This scoping review was conducted to capture the breadth of AI applications within cardiovascular science. Employing a structured approach, we sourced relevant articles from PubMed, with an emphasis on journals encompassing general cardiology and digital medicine. We applied filters to highlight cardiovascular articles published in journals focusing on general internal medicine, cardiology and digital medicine, thereby identifying the prevailing trends in the field. Following a comprehensive full-text screening, a total of 140 studies were identified. Over the preceding 5 years, cardiovascular medicine's interplay with AI has seen an over tenfold augmentation. This expansive growth encompasses multiple cardiovascular subspecialties, including but not limited to, general cardiology, ischemic heart disease, heart failure, and arrhythmia. Deep learning emerged as the predominant methodology. The majority of AI endeavors in this domain have been channeled toward enhancing diagnostic and prognostic capabilities, utilizing resources such as hospital datasets, electrocardiograms, and echocardiography. A significant uptrend was observed in AI's application for omics data analysis. However, a clear gap persists in AI's full-scale integration into the clinical decision-making framework. AI, particularly deep learning, has demonstrated robust applications across cardiovascular subspecialties, indicating its transformative potential in this field. As we continue on this trajectory, ensuring the alignment of technological progress with medical ethics becomes crucial. The abundant digital health data today further accentuates the need for meticulous systematic reviews, tailoring them to each cardiovascular subspecialty.

Continuous Atrial Fibrillation Monitoring From Photoplethysmography: Comparison Between Supervised Deep Learning and Heuristic Signal Processing

BACKGROUND

Continuous monitoring for atrial fibrillation (AF) using photoplethysmography (PPG) from smartwatches or other wearables is challenging due to periods of poor signal quality during motion or suboptimal wearing. As a result, many consumer wearables sample infrequently and only analyze when the user is at rest, which limits the ability to perform continuous monitoring or to quantify AF.

OBJECTIVES

This study aimed to compare 2 methods of continuous monitoring for AF in free-living patients: a well-validated signal processing (SP) heuristic and a convolutional deep neural network (DNN) trained on raw signal.

METHODS

We collected 4 weeks of continuous PPG and electrocardiography signals in 204 free-living patients. Both SP and DNN models were developed and validated both on holdout patients and an external validation set.

RESULTS

The results show that the SP model demonstrated receiver-operating characteristic area under the curve (AUC) of 0.972 (sensitivity 99.6%, specificity: 94.4%), which was similar to the DNN receiver-operating characteristic AUC of 0.973 (sensitivity 92.2, specificity: 95.5%); however, the DNN classified significantly more data (95% vs 62%), revealing its superior tolerance of tracings prone to motion artifact. Explainability analysis revealed that the DNN automatically suppresses motion artifacts, evaluates irregularity, and learns natural AF interbeat variability. The DNN performed better and analyzed more signal in the external validation cohort using a different population and PPG sensor (AUC, 0.994; 97% analyzed vs AUC, 0.989; 88% analyzed).

CONCLUSIONS

DNNs perform at least as well as SP models, classify more data, and thus may be better for continuous PPG monitoring.

Imaging and biophysical modelling of thrombogenic mechanisms in atrial fibrillation and stroke

Atrial fibrillation (AF) underlies almost one third of all ischaemic strokes, with the left atrial appendage (LAA) identified as the primary thromboembolic source. Current stroke risk stratification approaches, such as the CHA₂DS₂-VASc score, rely mostly on clinical comorbidities, rather than thrombogenic mechanisms such as blood stasis, hypercoagulability and endothelial dysfunction-known as Virchow's triad. While detection of AF-related thrombi is possible using established cardiac imaging techniques, such as transoesophageal echocardiography, there is a growing need to reliably assess AF-patient thrombogenicity prior to thrombus formation. Over the past decade, cardiac imaging and image-based biophysical modelling have emerged as powerful tools for reproducing the mechanisms of thrombogenesis. Clinical imaging modalities such as cardiac computed tomography, magnetic resonance and echocardiographic techniques can measure blood flow velocities and identify LA fibrosis (an indicator of endothelial dysfunction), but imaging remains limited in its ability to assess blood coagulation dynamics. In-silico cardiac modelling tools-such as computational fluid dynamics for blood flow, reaction-diffusion-convection equations to mimic the coagulation cascade, and surrogate flow metrics associated with endothelial damage-have grown in prevalence and advanced mechanistic understanding of thrombogenesis. However, neither technique alone can fully elucidate thrombogenicity in AF. In future, combining cardiac imaging with in-silico modelling and integrating machine learning approaches for rapid results directly from imaging data will require development under a rigorous framework of verification and clinical validation, but may pave the way towards enhanced personalised stroke risk stratification in the growing population of AF patients. This Review will focus on the significant progress in these fields.

Smartphone detection of atrial fibrillation using photoplethysmography: a systematic review and meta-analysis

OBJECTIVES

Timely diagnosis of atrial fibrillation (AF) is essential to reduce complications from this increasingly common condition. We sought to assess the diagnostic accuracy of smartphone camera photoplethysmography (PPG) compared with conventional electrocardiogram (ECG) for AF detection.

METHODS

This is a systematic review of MEDLINE, EMBASE and Cochrane (1980-December 2020), including any study or abstract, where smartphone PPG was compared with a reference ECG (1, 3 or 12-lead). Random effects meta-analysis was performed to pool sensitivity/specificity and identify publication bias, with study quality assessed using the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies-2) risk of bias tool.

RESULTS

28 studies were included (10 full-text publications and 18 abstracts), providing 31 comparisons of smartphone PPG versus ECG for AF detection. 11 404 participants were included (2950 in AF), with most studies being small and based in secondary care. Sensitivity and specificity for AF detection were high, ranging from 81% to 100%, and from 85% to 100%, respectively. 20 comparisons from 17 studies were meta-analysed, including 6891 participants (2299 with AF); the pooled sensitivity was 94% (95% CI 92% to 95%) and specificity 97% (96%-98%), with substantial heterogeneity (p<0.01). Studies were of poor quality overall and none met all the QUADAS-2 criteria, with particular issues regarding selection bias and the potential for publication bias.

CONCLUSION

PPG provides a non-invasive, patient-led screening tool for AF. However, current evidence is limited to small, biased, low-quality studies with unrealistically high sensitivity and specificity. Further studies are needed, preferably independent from manufacturers, in order to advise clinicians on the true value of PPG technology for AF detection.

Non-Contact Atrial Fibrillation Detection From Face Videos by Learning Systolic Peaks

OBJECTIVE

We propose a non-contact approach for atrial fibrillation (AF) detection from face videos.

METHODS

Face videos, electrocardiography (ECG), and contact photoplethysmography (PPG) from 100 healthy subjects and 100 AF patients are recorded. Data recordings from healthy subjects are all labeled as healthy. Two cardiologists evaluated ECG recordings of patients and labeled each recording as AF, sinus rhythm (SR), or atrial flutter (AFL). We use the 3D convolutional neural network for remote PPG monitoring and propose a novel loss function (Wasserstein distance) to use the timing of systolic peaks from contact PPG as the label for our model training. Then a set of heart rate variability (HRV) features are calculated from the inter-beat intervals, and a support vector machine (SVM) classifier is trained with HRV features.

RESULTS

Our proposed method can accurately extract systolic peaks from face videos for AF detection. The proposed method is trained with subject-independent 10-fold cross-validation with 30s video clips and tested on two tasks. 1) Classification of healthy versus AF: the accuracy, sensitivity, and specificity are 96.00%, 95.36%, and 96.12%. 2) Classification of SR versus AF: the accuracy, sensitivity, and specificity are 95.23%, 98.53%, and 91.12%. In addition, we also demonstrate the feasibility of non-contact AFL detection.

CONCLUSION

We achieve good performance of non-contact AF detection by learning systolic peaks.

SIGNIFICANCE

non-contact AF detection can be used for self-screening of AF symptoms for suspectable populations at home or self-monitoring of AF recurrence after treatment for chronic patients.

Is machine learning the future for atrial fibrillation screening?

Atrial fibrillation (AF) is the most common arrhythmia and causes significant morbidity and mortality. Early identification of AF may lead to early treatment of AF and may thus prevent AF-related strokes and complications. However, there is no current formal, cost-effective strategy for population screening for AF. In this review, we give a brief overview of targeted screening for AF, AF risk score models used for screening and describe the different screening tools. We then go on to extensively discuss the potential applications of machine learning in AF screening.

Daily ambulatory remote monitoring system for drug escalation in chronic heart failure with reduced ejection fraction: pilot phase of DAVID-HF study

AIMS

Underutilization of guideline-directed heart failure with reduced ejection fraction (HFrEF) medications contributes to poor outcomes.

METHODS AND RESULTS

A pilot study to evaluate the safety and efficacy of a home-based remote monitoring system for HFrEF management was performed. The system included wearable armband monitors paired with the smartphone application. An HFrEF medication titration algorithm was used to adjust medication daily. The primary endpoint was HFrEF medication utilization at 120 days. Twenty patients (60.5 ± 8.2 years, men: 85%) with HFrEF were recruited. All received angiotensin-converting enzyme inhibitor (ACEI)/angiotensin receptor blocker (ARB)/angiotensin receptor-neprilysin inhibitor (ARNI) at recruitment; 45% received ≥50% maximal targeted dose (MTD) with % MTD of 44.4 ± 31.7%. At baseline, 90 and 70% received beta-adrenergic blocker and mineralocorticoid receptor antagonist (MRA), 35% received ≥50% MTD beta-adrenergic blocker with % MTD of 34.1 ± 29.6%, and 25% received ≥50% MTD MRA with % MTD of 25.0 ± 19.9%. At 120 days, 70% received ≥50% MTD ACEI/ARB/ARNI (P = 0.110) with % MTD increased to 64.4 ± 33.5% (P = 0.060). The proportion receiving ≥50% MTD ARNI increased from 15 to 55% (P = 0.089) with % MTD ARNI increased from 20.6 ± 30.9 to 53.1 ± 39.5% (P = 0.006*). More patients received ≥50% MTD MRA (65 vs. 25%, P = 0.011*) with % MTD MRA increased from 25.0 ± 19.9 to 46.2 ± 28.8% (P = 0.009*). Ninety-five per cent of patients had reduced NT-proBNP with the percentage reduction of 26.7 ± 19.7%.

CONCLUSION

Heart failure with reduced ejection fraction medication escalation with remote monitoring appeared feasible.

Visual Reassessment with Flux-Interval Plot Configuration after Automatic Classification for Accurate Atrial Fibrillation Detection by Photoplethysmography

Atrial fibrillation (AFib) is a common type of arrhythmia that is often clinically asymptomatic, which increases the risk of stroke significantly but can be prevented with anticoagulation. The photoplethysmogram (PPG) has recently attracted a lot of attention as a surrogate for electrocardiography (ECG) on atrial fibrillation (AFib) detection, with its out-of-hospital usability for rapid screening or long-term monitoring. Previous studies on AFib detection via PPG signals have achieved good results, but were short of intuitive criteria like ECG p-wave absence or not, especially while using interval randomness to detect AFib suffering from conjunction with premature contractions (PAC/PVC). In this study, we newly developed a PPG flux (pulse amplitude) and interval plots-based methodology, simply comprising an irregularity index threshold of 20 and regression error threshold of 0.06 for the precise automatic detection of AFib. The proposed method with automated detection on AFib shows a combined sensitivity, specificity, accuracy, and precision of 1, 0.995, 0.995, and 0.952 across the 460 samples. Furthermore, the flux-interval plot configuration also acts as a very intuitive tool for visual reassessment to confirm the automatic detection of AFib by its distinctive plot pattern compared to other cardiac rhythms. The study demonstrated that exclusive 2 false-positive cases could be corrected after the reassessment. With the methodology’s background theory well established, the detection process automated and visualized, and the PPG sensors already extensively used, this technology is very user-friendly and convincing for promoted to in-house AFib diagnostics.

Multiclass Arrhythmia Detection and Classification From Photoplethysmography Signals Using a Deep Convolutional Neural Network

Background

Studies have reported the use of photoplethysmography signals to detect atrial fibrillation; however, the use of photoplethysmography signals in classifying multiclass arrhythmias has rarely been reported. Our study investigated the feasibility of using photoplethysmography signals and a deep convolutional neural network to classify multiclass arrhythmia types.

Methods and Results

ECG and photoplethysmography signals were collected simultaneously from a group of patients who underwent radiofrequency ablation for arrhythmias. A deep convolutional neural network was developed to classify multiple rhythms based on 10‐second photoplethysmography waveforms. Classification performance was evaluated by calculating the area under the microaverage receiver operating characteristic curve, overall accuracy, sensitivity, specificity, and positive and negative predictive values against annotations on the rhythm of arrhythmias provided by 2 cardiologists consulting the ECG results. A total of 228 patients were included; 118 217 pairs of 10‐second photoplethysmography and ECG waveforms were used. When validated against an independent test data set (23 384 photoplethysmography waveforms from 45 patients), the DCNN achieved an overall accuracy of 85.0% for 6 rhythm types (sinus rhythm, premature ventricular contraction, premature atrial contraction, ventricular tachycardia, supraventricular tachycardia, and atrial fibrillation); the microaverage area under the microaverage receiver operating characteristic curve was 0.978; the average sensitivity, specificity, and positive and negative predictive values were 75.8%, 96.9%, 75.2%, and 97.0%, respectively.

Conclusions

This study demonstrated the feasibility of classifying multiclass arrhythmias from photoplethysmography signals using deep learning techniques. The approach is attractive for population‐based screening and may hold promise for the long‐term surveillance and management of arrhythmia.

Registration

URL: www.chictr.org.cn. Identifier: ChiCTR2000031170.

Artificial Intelligence and Atrial Fibrillation

In the context of atrial fibrillation (AF), traditional clinical practices have thus far fallen short in several domains such as identifying patients at risk of incident AF or patients with concomitant undetected paroxysmal AF. Novel approaches leveraging artificial intelligence have the potential to provide new tools to deal with some of these old problems. In this review we focus on the roles of artificial intelligence-enabled ECG pertaining to AF, potential roles of deep learning (DL) models in the context of current knowledge gaps, as well as limitations of these models. One key area where DL models can translate to better patient outcomes is through automated ECG interpretation. Further, we overview some of the challenges facing AF screening and the harms and benefits of screening. In this context, a unique model was developed to detect underlying hidden AF from sinus rhythm and is discussed in detail with its potential uses. Knowledge gaps also remain regarding the best ways to monitor patients with embolic stroke of undetermined source (ESUS) and who would benefit most from oral anticoagulation. The AI-enabled AF model is one potential way to tackle this complex problem as it could be used to identify a subset of high-risk ESUS patients likely to benefit from empirical oral anticoagulation. Role of DL models assessing AF burden from long duration ECG data is also discussed as a way of guiding management. There is a trend towards the use of consumer-grade wristbands and watches to detect AF from photoplethysmography data. However, ECG currently remains the gold standard to detect arrythmias including AF. Lastly, role of adequate external validation of the models and clinical trials to study true performance is discussed. This article is protected by copyright. All rights reserved.

Photoplethysmogram Analysis and Applications: An Integrative Review

Beyond its use in a clinical environment, photoplethysmogram (PPG) is increasingly used for measuring the physiological state of an individual in daily life. This review aims to examine existing research on photoplethysmogram concerning its generation mechanisms, measurement principles, clinical applications, noise definition, pre-processing techniques, feature detection techniques, and post-processing techniques for photoplethysmogram processing, especially from an engineering point of view. We performed an extensive search with the PubMed, Google Scholar, Institute of Electrical and Electronics Engineers (IEEE), ScienceDirect, and Web of Science databases. Exclusion conditions did not include the year of publication, but articles not published in English were excluded. Based on 118 articles, we identified four main topics of enabling PPG: (A) PPG waveform, (B) PPG features and clinical applications including basic features based on the original PPG waveform, combined features of PPG, and derivative features of PPG, (C) PPG noise including motion artifact baseline wandering and hypoperfusion, and (D) PPG signal processing including PPG preprocessing, PPG peak detection, and signal quality index. The application field of photoplethysmogram has been extending from the clinical to the mobile environment. Although there is no standardized pre-processing pipeline for PPG signal processing, as PPG data are acquired and accumulated in various ways, the recently proposed machine learning-based method is expected to offer a promising solution.

Artificial intelligence for the detection, prediction, and management of atrial fibrillation

The present article reviews the state of the art of machine learning algorithms for the detection, prediction, and management of atrial fibrillation (AF), as well as of the development and evaluation of artificial intelligence (AI) in cardiology and beyond. Today, AI detects AF with a high accuracy using 12-lead or single-lead electrocardiograms or photoplethysmography. The prediction of paroxysmal or future AF currently operates at a level of precision that is too low for clinical use. Further studies are needed to determine whether patient selection for interventions may be possible with machine learning.

Application of artificial intelligence to the electrocardiogram

Artificial intelligence (AI) has given the electrocardiogram (ECG) and clinicians reading them super-human diagnostic abilities. Trained without hard-coded rules by finding often subclinical patterns in huge datasets, AI transforms the ECG, a ubiquitous, non-invasive cardiac test that is integrated into practice workflows, into a screening tool and predictor of cardiac and non-cardiac diseases, often in asymptomatic individuals. This review describes the mathematical background behind supervised AI algorithms, and discusses selected AI ECG cardiac screening algorithms including those for the detection of left ventricular dysfunction, episodic atrial fibrillation from a tracing recorded during normal sinus rhythm, and other structural and valvular diseases. The ability to learn from big data sets, without the need to understand the biological mechanism, has created opportunities for detecting non-cardiac diseases as COVID-19 and introduced challenges with regards to data privacy. Like all medical tests, the AI ECG must be carefully vetted and validated in real-world clinical environments. Finally, with mobile form factors that allow acquisition of medical-grade ECGs from smartphones and wearables, the use of AI may enable massive scalability to democratize healthcare.

Application of Artificial Intelligence in Cardiovascular Medicine

The advent of advances in machine learning (ML)-based techniques has popularized wide applications of artificial intelligence (AI) in various fields ranging from robotics to medicine. In recent years, there has been a surge in the application of AI to research in cardiovascular medicine, which is largely driven by the availability of large-scale clinical and multi-omics datasets. Such applications are providing a new perspective for a better understanding of cardiovascular disease (CVD), which could be used to develop novel diagnostic and therapeutic strategies. For example, studies have shown that ML has a substantial potential for early diagnosis of different types of CVD, prediction of adverse disease outcomes such as heart failure, and development of newer and personalized treatments. In this article, we provide an overview and discuss the current status of a wide range of AI applications, including machine learning, reinforcement learning, and deep learning, in cardiovascular medicine. © 2021 American Physiological Society. Compr Physiol 11:1-12, 2021.

The Role of Artificial Intelligence in Arrhythmia Monitoring

Arrhythmia management has been revolutionized by the ability to monitor the cardiac rhythm in a patient's home environment in real-time using high-fidelity prescription-grade and commercially available wearable electrodes. The vast amount of digitally acquired electrophysiological signals has generated the need for scalable and efficient data processing with actionable output that can be provided directly to clinicians and patients. In this setting, artificial intelligence applications are increasingly important in arrhythmia monitoring, ranging from conventional algorithmic analysis for rhythm determination to more complex deep machine learning methods that have led to the realization of fully automated humanlike rhythm determination in real-time.

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.

Returning Cardiac Rhythm Data to Patients: Opportunities and Challenges

Spurred by federal legislation, professional organizations, and patients themselves, patient access to data from electronic cardiac devices is increasingly transparent. Patients can collect data through consumer devices and access data traditionally shared only with health care providers. These data may improve screening, self-management, and shared decision-making for cardiac arrhythmias, but challenges remain, including patient comprehension, communication with providers, and sustained engagement. Ways to address these challenges include leveraging visualizations that support comprehension, involving patients in designing and developing patient-facing digital tools, and establishing clear practices and goals for data exchange with health care providers.

Automated classification of coronary atherosclerotic plaque in optical frequency domain imaging based on deep learning

BACKGROUND AND AIMS

We developed a deep learning (DL) model for automated atherosclerotic plaque categorization using optical frequency domain imaging (OFDI) and performed quantitative and visual evaluations.

METHODS

A total of 1103 histological cross-sections from 45 autopsy hearts were examined to compare the ex vivo OFDI scans. The images were segmented and annotated considering four histological categories: pathological intimal thickening (PIT), fibrous cap atheroma (FA), fibrocalcific plaque (FC), and healed erosion/rupture (HER). The DL model was developed based on pyramid scene parsing network (PSPNet). Given an input image, a convolutional neural network (ResNet50) was used as an encoder to generate feature maps of the last convolutional layer.

RESULTS

For the quantitative evaluation, the mean F-score and IoU values, which are used to evaluate how close the predicted results are to the ground truth, were used. The validation and test dataset had F-score and IoU values of 0.63, 0.49, and 0.66, 0.52, respectively. For the section-level diagnostic accuracy, the areas under the receiver-operating characteristic curve produced by the DL model for FC, PIT, FA, and HER were 0.91, 0.85, 0.86, and 0.86, respectively, and were comparable to those of an expert observer.

CONCLUSIONS

DL semantic segmentation of coronary plaques in OFDI images was used as a tool to automatically categorize atherosclerotic plaques using histological findings as the gold standard. The proposed method can support interventional cardiologists in understanding histological properties of plaques.

Explainable Artificial Intelligence Model for Diagnosis of Atrial Fibrillation Using Holter Electrocardiogram Waveforms

Atrial fibrillation is a clinically important arrhythmia. There are some reports on machine learning models for AF diagnosis using electrocardiogram data. However, few reports have proposed an eXplainable Artificial Intelligence (XAI) model to enable physicians to easily understand the machine learning model's diagnosis results.We developed and validated an XAI-enabled atrial fibrillation diagnosis model based on a convolutional neural network (CNN) algorithm. We used Holter electrocardiogram monitoring data and the gradient-weighted class activation mapping (Grad-CAM) method.Electrocardiogram data recorded from patients between January 4, 2016, and October 31, 2019, totaling 57,273 electrocardiogram waveform slots of 30 seconds each with diagnostic information annotated by cardiologists, were used for training our proposed model. Performance metrics of our AI model for AF diagnosis are as follows: sensitivity, 97.1% (95% CI: 0.969-0.972); specificity, 94.5% (95% CI: 0.943-0.946); accuracy, 95.3% (95% CI: 0.952-0.955); positive predictive value, 89.3% (95% CI: 0.892-0.897); and F-value, 93.1% (95% CI: 0.929-0.933). The area under the receiver operating characteristic curve for AF detection using our model was 0.988 (95% CI: 0.987-0.988). Furthermore, using the XAI method, 94.5 ± 3.5% of the areas identified as regions of interest using our machine learning model were identified as characteristic sites for AF diagnosis by cardiologists.AF was accurately diagnosed and favorably explained with Holter ECG waveforms using our proposed CNN-based XAI model. Our study presents another step toward realizing a viable XAI-based detection model for AF diagnoses for use by physicians.

Recent Research for Unobtrusive Atrial Fibrillation Detection Methods Based on Cardiac Dynamics Signals: A Survey

Atrial fibrillation (AF) is the most common cardiac arrhythmia. It tends to cause multiple cardiac conditions, such as cerebral artery blockage, stroke, and heart failure. The morbidity and mortality of AF have been progressively increasing over the past few decades, which has raised widespread concern about unobtrusive AF detection in routine life. The up-to-date non-invasive AF detection methods include electrocardiogram (ECG) signals and cardiac dynamics signals, such as the ballistocardiogram (BCG) signal, the seismocardiogram (SCG) signal and the photoplethysmogram (PPG) signal. Cardiac dynamics signals can be collected by cushions, mattresses, fabrics, or even cameras, which is more suitable for long-term monitoring. Therefore, methods for AF detection by cardiac dynamics signals bring about extensive attention for recent research. This paper reviews the current unobtrusive AF detection methods based on the three cardiac dynamics signals, summarized as data acquisition and preprocessing, feature extraction and selection, classification and diagnosis. In addition, the drawbacks and limitations of the existing methods are analyzed, and the challenges in future work are discussed.

Toward Patient-Specific Prediction of Ablation Strategies for Atrial Fibrillation Using Deep Learning

Atrial fibrillation (AF) is a common cardiac arrhythmia that affects 1% of the population worldwide and is associated with high levels of morbidity and mortality. Catheter ablation (CA) has become one of the first line treatments for AF, but its success rates are suboptimal, especially in the case of persistent AF. Computational approaches have shown promise in predicting the CA strategy using simulations of atrial models, as well as applying deep learning to atrial images. We propose a novel approach that combines image-based computational modelling of the atria with deep learning classifiers trained on patient-specific atrial models, which can be used to assist in CA therapy selection. Therefore, we trained a deep convolutional neural network (CNN) using a combination of (i) 122 atrial tissue images obtained by unfolding patient LGE-MRI datasets, (ii) 157 additional synthetic images derived from the patient data to enhance the training dataset, and (iii) the outcomes of 558 CA simulations to terminate several AF scenarios in the corresponding image-based atrial models. Four CNN classifiers were trained on this patient-specific dataset balanced using several techniques to predict three common CA strategies from the patient atrial images: pulmonary vein isolation (PVI), rotor-based ablation (Rotor) and fibrosis-based ablation (Fibro). The training accuracy for these classifiers ranged from 96.22 to 97.69%, while the validation accuracy was from 78.68 to 86.50%. After training, the classifiers were applied to predict CA strategies for an unseen holdout test set of atrial images, and the results were compared to outcomes of the respective image-based simulations. The highest success rate was observed in the correct prediction of the Rotor and Fibro strategies (100%), whereas the PVI class was predicted in 33.33% of the cases. In conclusion, this study provides a proof-of-concept that deep neural networks can learn from patient-specific MRI datasets and image-derived models of AF, providing a novel technology to assist in tailoring CA therapy to a patient.

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.

Explainability Metrics of Deep Convolutional Networks for Photoplethysmography Quality Assessment

Photoplethysmography (PPG) is a noninvasive way to monitor various aspects of the circulatory system, and is becoming more and more widespread in biomedical processing. Recently, deep learning methods for analyzing PPG have also become prevalent, achieving state of the art results on heart rate estimation, atrial fibrillation detection, and motion artifact identification. Consequently, a need for interpretable deep learning has arisen within the field of biomedical signal processing. In this paper, we pioneer novel explanatory metrics which leverage domain-expert knowledge to validate a deep learning model. We visualize model attention over a whole testset using saliency methods and compare it to human expert annotations. Congruence, our first metric, measures the proportion of model attention within expert-annotated regions. Our second metric, Annotation Classification, measures how much of the expert annotations our deep learning model pays attention to. Finally, we apply our metrics to compare between a signal based model and an image based model for PPG signal quality classification. Both models are deep convolutional networks based on the ResNet architectures. We show that our signal-based one dimensional model acts in a more explainable manner than our image based model; on average 50.78% of the one dimensional model's attention are within expert annotations, whereas 36.03% of the two dimensional model's attention are within expert annotations. Similarly, when thresholding the one dimensional model attention, one can more accurately predict if each pixel of the PPG is annotated as artifactual by an expert. Through this testcase, we demonstrate how our metrics can provide a quantitative and dataset-wide analysis of how explainable the model is.

An Application of Machine Learning to Etiological Diagnosis of Secondary Hypertension: Retrospective Study Using Electronic Medical Records

Background

Secondary hypertension is a kind of hypertension with a definite etiology and may be cured. Patients with suspected secondary hypertension can benefit from timely detection and treatment and, conversely, will have a higher risk of morbidity and mortality than those with primary hypertension.

Objective

The aim of this study was to develop and validate machine learning (ML) prediction models of common etiologies in patients with suspected secondary hypertension.

Methods

The analyzed data set was retrospectively extracted from electronic medical records of patients discharged from Fuwai Hospital between January 1, 2016, and June 30, 2019. A total of 7532 unique patients were included and divided into 2 data sets by time: 6302 patients in 2016-2018 as the training data set for model building and 1230 patients in 2019 as the validation data set for further evaluation. Extreme Gradient Boosting (XGBoost) was adopted to develop 5 models to predict 4 etiologies of secondary hypertension and occurrence of any of them (named as composite outcome), including renovascular hypertension (RVH), primary aldosteronism (PA), thyroid dysfunction, and aortic stenosis. Both univariate logistic analysis and Gini Impurity were used for feature selection. Grid search and 10-fold cross-validation were used to select the optimal hyperparameters for each model.

Results

Validation of the composite outcome prediction model showed good performance with an area under the receiver-operating characteristic curve (AUC) of 0.924 in the validation data set, while the 4 prediction models of RVH, PA, thyroid dysfunction, and aortic stenosis achieved AUC of 0.938, 0.965, 0.959, and 0.946, respectively, in the validation data set. A total of 79 clinical indicators were identified in all and finally used in our prediction models. The result of subgroup analysis on the composite outcome prediction model demonstrated high discrimination with AUCs all higher than 0.890 among all age groups of adults.

Conclusions

The ML prediction models in this study showed good performance in detecting 4 etiologies of patients with suspected secondary hypertension; thus, they may potentially facilitate clinical diagnosis decision making of secondary hypertension in an intelligent way.

Artificial intelligence for the detection of vertebral fractures on plain spinal radiography

Vertebral fractures (VFs) cause serious problems, such as substantial functional loss and a high mortality rate, and a delayed diagnosis may further worsen the prognosis. Plain thoracolumbar radiography (PTLR) is an essential method for the evaluation of VFs. Therefore, minimizing the diagnostic errors of VFs on PTLR is crucial. Image identification based on a deep convolutional neural network (DCNN) has been recognized to be potentially effective as a diagnostic strategy; however, the accuracy for detecting VFs has not been fully investigated. A DCNN was trained with PTLR images of 300 patients (150 patients with and 150 without VFs). The accuracy, sensitivity, and specificity of diagnosis of the model were calculated and compared with those of orthopedic residents, orthopedic surgeons, and spine surgeons. The DCNN achieved accuracy, sensitivity, and specificity rates of 86.0% [95% confidence interval (CI) 82.0-90.0%], 84.7% (95% CI 78.8-90.5%), and 87.3% (95% CI 81.9-92.7%), respectively. Both the accuracy and sensitivity of the model were suggested to be noninferior to those of orthopedic surgeons. The DCNN can assist clinicians in the early identification of VFs and in managing patients, to prevent further invasive interventions and a decreased quality of life.

Prediction of vascular aging based on smartphone acquired PPG signals

Photoplethysmography (PPG) measured by smartphone has the potential for a large scale, non-invasive, and easy-to-use screening tool. Vascular aging is linked to increased arterial stiffness, which can be measured by PPG. We investigate the feasibility of using PPG to predict healthy vascular aging (HVA) based on two approaches: machine learning (ML) and deep learning (DL). We performed data preprocessing, including detrending, demodulating, and denoising on the raw PPG signals. For ML, ridge penalized regression has been applied to 38 features extracted from PPG, whereas for DL several convolutional neural networks (CNNs) have been applied to the whole PPG signals as input. The analysis has been conducted using the crowd-sourced Heart for Heart data. The prediction performance of ML using two features (AUC of 94.7%) – the a wave of the second derivative PPG and tpr, including four covariates, sex, height, weight, and smoking – was similar to that of the best performing CNN, 12-layer ResNet (AUC of 95.3%). Without having the heavy computational cost of DL, ML might be advantageous in finding potential biomarkers for HVA prediction. The whole workflow of the procedure is clearly described, and open software has been made available to facilitate replication of the results.

Computational Diagnostic Techniques for Electrocardiogram Signal Analysis

Cardiovascular diseases (CVDs), including asymptomatic myocardial ischemia, angina, myocardial infarction, and ischemic heart failure, are the leading cause of death globally. Early detection and treatment of CVDs significantly contribute to the prevention or delay of cardiovascular death. Electrocardiogram (ECG) records the electrical impulses generated by heart muscles, which reflect regular or irregular beating activity. Computer-aided techniques provide fast and accurate tools to identify CVDs using a patient's ECG signal, which have achieved great success in recent years. Latest computational diagnostic techniques based on ECG signals for estimating CVDs conditions are summarized here. The procedure of ECG signals analysis is discussed in several subsections, including data preprocessing, feature engineering, classification, and application. In particular, the End-to-End models integrate feature extraction and classification into learning algorithms, which not only greatly simplifies the process of data analysis, but also shows excellent accuracy and robustness. Portable devices enable users to monitor their cardiovascular status at any time, bringing new scenarios as well as challenges to the application of ECG algorithms. Computational diagnostic techniques for ECG signal analysis show great potential for helping health care professionals, and their application in daily life benefits both patients and sub-healthy people.

Robust PPG motion artifact detection using a 1-D convolution neural network

BACKGROUND AND OBJECTIVES

Continuous monitoring of physiological parameters such as photoplethysmography (PPG) has attracted increased interest due to advances in wearable sensors. However, PPG recordings are susceptible to various artifacts, and thus reducing the reliability of PPG-driven parameters, such as oxygen saturation, heart rate, blood pressure and respiration. This paper proposes a one-dimensional convolution neural network (1-D-CNN) to classify five-second PPG segments into clean or artifact-affected segments, avoiding data-dependent pulse segmentation techniques and heavy manual feature engineering.

METHODS

Continuous raw PPG waveforms were blindly allocated into segments with an equal length (5s) without leveraging any pulse location information and were normalized with Z-score normalization methods. A 1-D-CNN was designed to automatically learn the intrinsic features of the PPG waveform, and perform the required classification. Several training hyperparameters (initial learning rate and gradient threshold) were varied to investigate the effect of these parameters on the performance of the network. Subsequently, this proposed network was trained and validated with 30 subjects, and then tested with eight subjects, with our local dataset. Moreover, two independent datasets downloaded from the PhysioNet MIMIC II database were used to evaluate the robustness of the proposed network.

RESULTS

A 13 layer 1-D-CNN model was designed. Within our local study dataset evaluation, the proposed network achieved a testing accuracy of 94.9%. The classification accuracy of two independent datasets also achieved satisfactory accuracy of 93.8% and 86.7% respectively. Our model achieved a comparable performance with most reported works, with the potential to show good generalization as the proposed network was evaluated with multiple cohorts (overall accuracy of 94.5%).

CONCLUSION

This paper demonstrated the feasibility and effectiveness of applying blind signal processing and deep learning techniques to PPG motion artifact detection, whereby manual feature thresholding was avoided and yet a high generalization ability was achieved.

Identification of undiagnosed atrial fibrillation patients using a machine learning risk prediction algorithm and diagnostic testing (PULsE-AI): Study protocol for a randomised controlled trial

Atrial fibrillation (AF) is associated with an increased risk of stroke, enhanced stroke severity, and other comorbidities. However, AF is often asymptomatic, and frequently remains undiagnosed until complications occur. Current screening approaches for AF lack either cost-effectiveness or diagnostic sensitivity; thus, there is interest in tools that could be used for population screening. An AF risk prediction algorithm, developed using machine learning from a UK dataset of 2,994,837 patients, was found to be more effective than existing models at identifying patients at risk of AF. Therefore, the aim of the trial is to assess the effectiveness of this risk prediction algorithm combined with diagnostic testing for the identification of AF in a real-world primary care setting. Eligible participants (aged ≥30 years and without an existing AF diagnosis) registered at participating UK general practices will be randomised into intervention and control arms. Intervention arm participants identified at highest risk of developing AF (algorithm risk score ≥ 7.4%) will be invited for a 12‑lead electrocardiogram (ECG) followed by two-weeks of home-based ECG monitoring with a KardiaMobile device. Control arm participants will be used for comparison and will be managed routinely. The primary outcome is the number of AF diagnoses in the intervention arm compared with the control arm during the research window. If the trial is successful, there is potential for the risk prediction algorithm to be implemented throughout primary care for narrowing the population considered at highest risk for AF who could benefit from more intensive screening for AF. Trial Registration: NCT04045639.

Diagnostic accuracy of smart gadgets/wearable devices in detecting atrial fibrillation: A systematic review and meta-analysis

BACKGROUND

Recently, smart devices have been used for medical purposes, particularly to screen for atrial fibrillation. However, current data on the diagnostic performance of these devices are scarce.

AIMS

We performed a systemic review and meta-analysis to assess the accuracy of atrial fibrillation diagnosis by smart gadgets/wearable devices.

METHODS

We comprehensively searched the MEDLINE, EMBASE and Cochrane databases for all works since the inception of each database until January 2020. Included in this review were published observational studies of the diagnostic accuracy of smartphones or smartwatches in detecting atrial fibrillation. We calculated the area under the summary receiver operating characteristic curves and pooled sensitivities and specificities.

RESULTS

Participants in our study were from the general population or were patients with underlying atrial fibrillation. In the overall analyses, the areas under the summary receiver operating characteristic curves were 0.96 and 0.94 for smartphones and smartwatches, respectively. Smartphones had a sensitivity of 94% and a specificity of 96%, and smartwatches showed similar diagnostic accuracy, with a specificity of 94% and a sensitivity of 93%. In subgroup analyses, we found no difference in diagnostic accuracy between photoplethysmography and single-lead electrocardiography.

CONCLUSIONS

This study suggests that smart devices have similar diagnostic accuracies. Regarding atrial fibrillation detection methods, there was also no difference between photoplethysmography and single-lead electrocardiography. However, further studies are warranted to determine their clinical implications in atrial fibrillation management.

Multi-task deep learning for cardiac rhythm detection in wearable devices

Wearable devices enable theoretically continuous, longitudinal monitoring of physiological measurements such as step count, energy expenditure, and heart rate. Although the classification of abnormal cardiac rhythms such as atrial fibrillation from wearable devices has great potential, commercial algorithms remain proprietary and tend to focus on heart rate variability derived from green spectrum LED sensors placed on the wrist, where noise remains an unsolved problem. Here we develop DeepBeat, a multitask deep learning method to jointly assess signal quality and arrhythmia event detection in wearable photoplethysmography devices for real-time detection of atrial fibrillation. The model is trained on approximately one million simulated unlabeled physiological signals and fine-tuned on a curated dataset of over 500 K labeled signals from over 100 individuals from 3 different wearable devices. We demonstrate that, in comparison with a single-task model, our architecture using unsupervised transfer learning through convolutional denoising autoencoders dramatically improves the performance of atrial fibrillation detection from a F1 score of 0.54 to 0.96. We also include in our evaluation a prospectively derived replication cohort of ambulatory participants where the algorithm performed with high sensitivity (0.98), specificity (0.99), and F1 score (0.93). We show that two-stage training can help address the unbalanced data problem common to biomedical applications, where large-scale well-annotated datasets are hard to generate due to the expense of manual annotation, data acquisition, and participant privacy.

Detecting undiagnosed atrial fibrillation in UK primary care: Validation of a machine learning prediction algorithm in a retrospective cohort study

AIMS

To evaluate the ability of a machine learning algorithm to identify patients at high risk of atrial fibrillation in primary care.

METHODS

A retrospective cohort study was undertaken using the DISCOVER registry to validate an algorithm developed using a Clinical Practice Research Datalink (CPRD) dataset. The validation dataset included primary care patients in London, England aged ≥30 years from 1 January 2006 to 31 December 2013, without a diagnosis of atrial fibrillation in the prior 5 years. Algorithm performance metrics were sensitivity, specificity, positive predictive value, negative predictive value (NPV) and number needed to screen (NNS). Subgroup analysis of patients aged ≥65 years was also performed.

RESULTS

Of 2,542,732 patients in DISCOVER, the algorithm identified 604,135 patients suitable for risk assessment. Of these, 3.0% (17,880 patients) had a diagnosis of atrial fibrillation recorded before study end. The area under the curve of the receiver operating characteristic was 0.87, compared with 0.83 in algorithm development. The NNS was nine patients, matching the CPRD cohort. In patients aged ≥30 years, the algorithm correctly identified 99.1% of patients who did not have atrial fibrillation (NPV) and 75.0% of true atrial fibrillation cases (sensitivity). Among patients aged ≥65 years (n = 117,965), the NPV was 96.7% with 91.8% sensitivity.

CONCLUSIONS

This atrial fibrillation risk prediction algorithm, based on machine learning methods, identified patients at highest risk of atrial fibrillation. It performed comparably in a large, real-world population-based cohort and the developmental registry cohort. If implemented in primary care, the algorithm could be an effective tool for narrowing the population who would benefit from atrial fibrillation screening in the United Kingdom.

Path to precision: prevention of post-operative atrial fibrillation

Development of post-operative atrial fibrillation (POAF) following open-heart surgery is a significant clinical and economic burden. Despite advancements in medical therapies, the incidence of POAF remains elevated at 25-40%. Early work focused on detecting arrhythmias from electrocardiograms as well as identifying pre-operative risk factors from medical records. However, further progress has been stagnant, and a deeper understanding of pathogenesis and significant influences is warranted. With the advent of more complex machine learning (ML) algorithms and high-throughput sequencing, we have an unprecedented ability to capture and predict POAF in real-time. Integration of multimodal heterogeneous data and application of ML can generate a paradigm shift for diagnosis and treatment. This will require a concerted effort to consolidate and streamline real-time data. Herein, we will review the current literature and emerging opportunities aimed at predictive targets and new insights into the mechanisms underlying long-term sequelae of POAF.

Machine learning algorithms estimating prognosis and guiding therapy in adult congenital heart disease: data from a single tertiary centre including 10 019 patients

AIMS

To assess the utility of machine learning algorithms on estimating prognosis and guiding therapy in a large cohort of patients with adult congenital heart disease (ACHD) or pulmonary hypertension at a single, tertiary centre.

METHODS AND RESULTS

We included 10 019 adult patients (age 36.3 ± 17.3 years) under follow-up at our institution between 2000 and 2018. Clinical and demographic data, ECG parameters, cardiopulmonary exercise testing, and selected laboratory markers where collected and included in deep learning (DL) algorithms. Specific DL-models were built based on raw data to categorize diagnostic group, disease complexity, and New York Heart Association (NYHA) class. In addition, models were developed to estimate need for discussion at multidisciplinary team (MDT) meetings and to gauge prognosis of individual patients. Overall, the DL-algorithms-based on over 44 000 medical records-categorized diagnosis, disease complexity, and NYHA class with an accuracy of 91.1%, 97.0%, and 90.6%, respectively in the test sample. Similarly, patient presentation at MDT-meetings was predicted with a test sample accuracy of 90.2%. During a median follow-up time of 8 years, 785 patients died. The automatically derived disease severity-score derived from clinical information was related to survival on Cox analysis independently of demographic, exercise, laboratory, and ECG parameters.

CONCLUSION

We present herewith the utility of machine learning algorithms trained on large datasets to estimate prognosis and potentially to guide therapy in ACHD. Due to the largely automated process involved, these DL-algorithms can easily be scaled to multi-institutional datasets to further improve accuracy and ultimately serve as online based decision-making tools.

Cardiovascular disease diagnosis using cross-domain transfer learning

While cardiovascular diseases (CVDs) are commonly diagnosed by cardiologists via inspecting electrocardiogram (ECG) waveforms, these decisions can be supported by a data-driven approach, which may automate this process. An automatic diagnostic approach often employs hand-crafted features extracted from ECG waveforms. These features, however, do not generalise well, challenged by variation in acquisition settings such as sampling rate and mounting points. Existing deep learning (DL) approaches, on the other hand, extract features from ECG automatically but require construction of dedicated networks that require huge data and computational resource if trained from scratch. Here we propose an end-to-end trainable cross-domain transfer learning for CVD classification from ECG waveforms, by utilising existing vision-based CNN frameworks as feature extractors, followed by ECG feature learning layers. Because these frameworks are designed for image inputs, we employ a stacked spectrogram representation of multi-lead ECG waveforms as a preprocessing step. We also proposed a fusion of multiple ECG leads, using plausible stacking arrangements of the spectrograms, to encode their spatial relations. The proposed approach is validated on multiple ECG datasets and competitive performance is achieved.

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

Background

Continuous photoplethysmography (PPG) monitoring with a wearable device may aid the early detection of atrial fibrillation (AF).

Objective

We aimed to evaluate the diagnostic performance of a ring-type wearable device (CardioTracker, CART), which can detect AF using deep learning analysis of PPG signals.

Methods

Patients with persistent AF who underwent cardioversion were recruited prospectively. We recorded PPG signals at the finger with CART and a conventional pulse oximeter before and after cardioversion over a period of 15 min (each instrument). Cardiologists validated the PPG rhythms with simultaneous single-lead electrocardiography. The PPG data were transmitted to a smartphone wirelessly and analyzed with a deep learning algorithm. We also validated the deep learning algorithm in 20 healthy subjects with sinus rhythm (SR).

Results

In 100 study participants, CART generated a total of 13,038 30-s PPG samples (5850 for SR and 7188 for AF). Using the deep learning algorithm, the diagnostic accuracy, sensitivity, specificity, positive-predictive value, and negative-predictive value were 96.9%, 99.0%, 94.3%, 95.6%, and 98.7%, respectively. Although the diagnostic accuracy decreased with shorter sample lengths, the accuracy was maintained at 94.7% with 10-s measurements. For SR, the specificity decreased with higher variability of peak-to-peak intervals. However, for AF, CART maintained consistent sensitivity regardless of variability. Pulse rates had a lower impact on sensitivity than on specificity. The performance of CART was comparable to that of the conventional device when using a proper threshold. External validation showed that 94.99% (16,529/17,400) of the PPG samples from the control group were correctly identified with SR.

Conclusions

A ring-type wearable device with deep learning analysis of PPG signals could accurately diagnose AF without relying on electrocardiography. With this device, continuous monitoring for AF may be promising in high-risk populations.

Trial Registration

ClinicalTrials.gov NCT04023188; https://clinicaltrials.gov/ct2/show/NCT04023188

Review of mobile applications for the detection and management of atrial fibrillation

BACKGROUND

Free mobile applications (apps) that use photoplethysmography (PPG) waveforms may extend atrial fibrillation (AF) detection to underserved populations, but they have not been rigorously evaluated.

OBJECTIVE

The purpose of this study was to systematically review and evaluate the quality, functionality, and adherence to self-management behaviors of existing mobile apps for AF.

METHODS

We systematically searched 3 app stores for apps that were free, available in English, and intended for use by patients to detect and manage AF. A minimum of 2 reviewers evaluated (1) app quality, using the Mobile Application Rating Scale (MARS); (2) functionality using published criteria; and (3) features that support 4 self-management behaviors (including PPG waveform monitoring) identified using evidence-based guidelines. Interrater reliability between the reviewers was calculated.

RESULTS

Of 12 included apps, 5 (42%) scored above average for quality (MARS score ≥3.0). App quality was highest for their ease of use, navigation, layout, and visual appeal (eg, functionality and aesthetics) and lowest for their behavioral change support and subjective impressions of quality. The most common app functionalities were capturing and graphically displaying user-entered data (n = 9 [75%]). Nearly all apps (n = 11 [92%]) supported PPG waveform monitoring, but only 2 (17%) supported all 4 self-management behaviors. Interrater reliability was high (0.75-0.83).

CONCLUSION

The reviewed apps had wide variability in quality, functionality, and adherence to self-management behaviors. Given the accessibility of these apps to underserved populations and the tremendous potential they hold for improving AF detection and management, high priority should be given to improving app quality and functionality.

Wearable Electronics Based on 2D Materials for Human Physiological Information Detection

Recently, advancement in materials production, device fabrication, and flexible circuit has led to the huge prosperity of wearable electronics for human healthcare monitoring and medical diagnosis. Particularly, with the emergence of 2D materials many merits including light weight, high stretchability, excellent biocompatibility, and high performance are used for those potential applications. Thus, it is urgent to review the wearable electronics based on 2D materials for the detection of various human signals. In this work, the typical graphene-based materials, transition-metal dichalcogenides, and transition metal carbides or carbonitrides used for the wearable electronics are discussed. To well understand the human physiological information, it is divided into two dominated categories, namely, the human physical and the human chemical signals. The monitoring of body temperature, electrograms, subtle signals, and limb motions is described for the physical signals while the detection of body fluid including sweat, breathing gas, and saliva is reviewed for the chemical signals. Recent progress and development toward those specific utilizations are highlighted in the Review with the representative examples. The future outlook of wearable healthcare techniques is briefly discussed for their commercialization.

Analysis of Relevant Features from Photoplethysmographic Signals for Atrial Fibrillation Classification

Atrial Fibrillation (AF) is the most common cardiac arrhythmia found in clinical practice. It affects an estimated 33.5 million people, representing approximately 0.5% of the world's population. Electrocardiogram (ECG) is the main diagnostic criterion for AF. Recently, photoplethysmography (PPG) has emerged as a simple and portable alternative for AF detection. However, it is not completely clear which are the most important features of the PPG signal to perform this process. The objective of this paper is to determine which are the most relevant features for PPG signal analysis in the detection of AF. This study is divided into two stages: (a) a systematic review carried out following the Preferred Reporting Items for a Systematic Review and Meta-analysis of Diagnostic Test Accuracy Studies (PRISMA-DTA) statement in six databases, in order to identify the features of the PPG signal reported in the literature for the detection of AF, and (b) an experimental evaluation of them, using machine learning, in order to determine which have the greatest influence on the process of detecting AF. Forty-four features were found when analyzing the signal in the time, frequency, or time-frequency domains. From those 44 features, 27 were implemented, and through machine learning, it was found that only 11 are relevant in the detection process. An algorithm was developed for the detection of AF based on these 11 features, which obtained an optimal performance in terms of sensitivity (98.43%), specificity (99.52%), and accuracy (98.97%).