Explainable artificial intelligence to detect atrial fibrillation using electrocardiogram

Detection and Classification of electrocardiography using hybrid deep learning models

BACKGROUND

Electrocardiography (ECGs) has been a vital tool for cardiovascular disease (CVD) diagnosis, which visually depicts the heart's electrical activity. To enhance automatic classification between normal and diseased ECG, it is essential to extract consistent and qualitative features.

METHODS

Precision of ECG classification through hybrid Deep Learning (DL) approach leverages both Convolutional Neural Network (CNN) architecture and Variational Autoencoder (VAE) techniques. By combining these methods, we aim to achieve more accurate and robust ECG interpretation. The method is trained and tested over PTB-XL dataset, which contains 21,799 with 12-lead ECGs from 18,869 patients, each spanning 10 seconds. The classification evaluation of 5 super-classes and 23 sub-classes of CVD, with the proposed CNN-VAE model is compared.

RESULTS

The classification of various CVD had resulted with the highest accuracy of 98.51%, specificity of 98.12%, sensitivity 97.9% and F1-score 97.95%. We have also achieved the minimum false positive and false negative rates as 2.07 and 1.87 respectively during validation. The results are validated upon the annotations given by individual cardiologists, who assigned potentially multiple ECG statements to each record.

CONCLUSION

When compared to other deep learning methods, our suggested CNN-VAE model performs significantly better in testing phase. This study proposes a new architecture of combining CNN-VAE for CVD classification from ECG data, this can help the clinicians to identify the disease earlier and carry further treatment. The CNN-VAE model can better characterize input signals due to its hybrid architecture.

Detection of atrial fibrillation using a nonlinear Lorenz Scattergram and deep learning in primary care

BACKGROUND

Atrial fibrillation (AF) is highly correlated with heart failure, stroke and death. Screening increases AF detection and facilitates the early adoption of comprehensive intervention. Long-term wearable devices have become increasingly popular for AF screening in primary care. However, interpreting data obtained by long-term wearable ECG devices is a problem in primary care. To diagnose the disease quickly and accurately, we aimed to build AF episode detection model based on a nonlinear Lorenz scattergram (LS) and deep learning.

METHODS

The MIT-BIH Normal Sinus Rhythm Database, MIT-BIH Arrhythmia Database and the Long-Term AF Database were extracted to construct the MIT-BIH Ambulatory Electrocardiograph (MIT-BIH AE) dataset. We converted the long-term ECG into a two-dimensional LSs. The LSs from MIT-BIH AE dataset was randomly divided into training and internal validation sets in a 9:1 ratio, which was used to develop and internally validated model. We built a MOBILE-SCREEN-AF (MS-AF) dataset from a single-lead wearable ECG device in primary care for external validation. Performance was quantified using a confusion matrix and standard classification metrics.

RESULTS

During the evaluation of model performance based on the LS, the sensitivity, specificity and accuracy of the model in diagnosing AF were 0.992, 0.973, and 0.983 in the internal validation set respectively. In the external validation set, these metrics were 0.989, 0.956, and 0.967, respectively. Furthermore, when evaluating the model's performance based on ECG records in the MS-AF dataset, the sensitivity, specificity and accuracy of model diagnosis paroxysmal AF were 1.000, 0.870 and 0.876 respectively, and 0.927, 1.000 and 0.973 for the persistent AF.

CONCLUSIONS

The model based on the nonlinear LS and deep learning has high accuracy, making it promising for AF screening in primary care. It has potential for generalization and practical application.

Artificial intelligence-enabled atrial fibrillation detection using smartwatches: current status and future perspectives

Atrial fibrillation (AF) significantly increases the risk of stroke and heart failure, but is frequently asymptomatic and intermittent; therefore, its timely diagnosis poses challenges. Early detection in selected patients may aid in stroke prevention and mitigate structural heart complications through prompt intervention. Smartwatches, coupled with powerful artificial intelligence (AI)-enabled algorithms, offer a promising tool for early detection due to their widespread use, easiness of use, and potential cost-effectiveness. Commercially available smartwatches have gained clearance from the FDA to detect AF and are becoming increasingly popular. Despite their promise, the evolving landscape of AI-enabled smartwatch-based AF detection raises questions about the clinical value of this technology. Following the ongoing digital transformation of healthcare, clinicians should familiarize themselves with how AI-enabled smartwatches function in AF detection and navigate their role in clinical settings to deliver optimal patient care. In this review, we provide a concise overview of the characteristics of AI-enabled smartwatch algorithms, their diagnostic performance, clinical value, limitations, and discuss future perspectives in AF diagnosis.

Diagnostic and Prognostic Electrocardiogram-Based Models for Rapid Clinical Applications

Leveraging artificial intelligence (AI) for the analysis of electrocardiograms (ECGs) has the potential to transform diagnosis and estimate the prognosis of not only cardiac but, increasingly, noncardiac conditions. In this review, we summarize clinical studies and AI-enhanced ECG-based clinical applications in the early detection, diagnosis, and estimating prognosis of cardiovascular diseases in the past 5 years (2019-2023). With advancements in deep learning and the rapid increased use of ECG technologies, a large number of clinical studies have been published. However, most of these studies are single-centre, retrospective, proof-of-concept studies that lack external validation. Prospective studies that progress from development toward deployment in clinical settings account for < 15% of the studies. Successful implementations of ECG-based AI applications that have received approval from the Food and Drug Administration have been developed through commercial collaborations, with approximately half of them being for mobile or wearable devices. The field is in its early stages, and overcoming several obstacles is essential, such as prospective validation in multicentre large data sets, addressing technical issues, bias, privacy, data security, model generalizability, and global scalability. This review concludes with a discussion of these challenges and potential solutions. By providing a holistic view of the state of AI in ECG analysis, this review aims to set a foundation for future research directions, emphasizing the need for comprehensive, clinically integrated, and globally deployable AI solutions in cardiovascular disease management.

Early warning of atrial fibrillation using deep learning

Atrial fibrillation (AF), the most prevalent cardiac rhythm disorder, significantly increases hospitalization and health risks. Reverting from AF to sinus rhythm (SR) often requires intensive interventions. This study presents a deep-learning model capable of predicting the transition from SR to AF on average 30.8 min before the onset appears, with an accuracy of 83% and an F1 score of 85% on the test data. This performance was obtained from R-to-R interval signals, which can be accessible from wearable technology. Our model, entitled Warning of Atrial Fibrillation (WARN), consists of a deep convolutional neural network trained and validated on 24-h Holter electrocardiogram data from 280 patients, with 70 additional patients used for testing and further evaluation on 33 patients from two external centers. The low computational cost of WARN makes it ideal for integration into wearable technology, allowing for continuous heart monitoring and early AF detection, which can potentially reduce emergency interventions and improve patient outcomes.

xECGArch: a trustworthy deep learning architecture for interpretable ECG analysis considering short-term and long-term features

Deep learning-based methods have demonstrated high classification performance in the detection of cardiovascular diseases from electrocardiograms (ECGs). However, their blackbox character and the associated lack of interpretability limit their clinical applicability. To overcome existing limitations, we present a novel deep learning architecture for interpretable ECG analysis (xECGArch). For the first time, short- and long-term features are analyzed by two independent convolutional neural networks (CNNs) and combined into an ensemble, which is extended by methods of explainable artificial intelligence (xAI) to whiten the blackbox. To demonstrate the trustworthiness of xECGArch, perturbation analysis was used to compare 13 different xAI methods. We parameterized xECGArch for atrial fibrillation (AF) detection using four public ECG databases ( n = 9854 ECGs) and achieved an F1 score of 95.43% in AF versus non-AF classification on an unseen ECG test dataset. A systematic comparison of xAI methods showed that deep Taylor decomposition provided the most trustworthy explanations ( + 24 % compared to the second-best approach). xECGArch can account for short- and long-term features corresponding to clinical features of morphology and rhythm, respectively. Further research will focus on the relationship between xECGArch features and clinical features, which may help in medical applications for diagnosis and therapy.

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

PURPOSE OF REVIEW

Artificial intelligence (AI) is transforming electrocardiography (ECG) interpretation. AI diagnostics can reach beyond human capabilities, facilitate automated access to nuanced ECG interpretation, and expand the scope of cardiovascular screening in the population. AI can be applied to the standard 12-lead resting ECG and single-lead ECGs in external monitors, implantable devices, and direct-to-consumer smart devices. We summarize the current state of the literature on AI-ECG.

RECENT FINDINGS

Rhythm classification was the first application of AI-ECG. Subsequently, AI-ECG models have been developed for screening structural heart disease including hypertrophic cardiomyopathy, cardiac amyloidosis, aortic stenosis, pulmonary hypertension, and left ventricular systolic dysfunction. Further, AI models can predict future events like development of systolic heart failure and atrial fibrillation. AI-ECG exhibits potential in acute cardiac events and non-cardiac applications, including acute pulmonary embolism, electrolyte abnormalities, monitoring drugs therapy, sleep apnea, and predicting all-cause mortality. Many AI models in the domain of cardiac monitors and smart watches have received Food and Drug Administration (FDA) clearance for rhythm classification, while others for identification of cardiac amyloidosis, pulmonary hypertension and left ventricular dysfunction have received breakthrough device designation. As AI-ECG models continue to be developed, in addition to regulatory oversight and monetization challenges, thoughtful clinical implementation to streamline workflows, avoiding information overload and overwhelming of healthcare systems with false positive results is necessary. Research to demonstrate and validate improvement in healthcare efficiency and improved patient outcomes would be required before widespread adoption of any AI-ECG model.

A Q-transform-based deep learning model for the classification of atrial fibrillation types

According to the World Health Organization (WHO), Atrial Fibrillation (AF) is emerging as a global epidemic, which has resulted in a need for techniques to accurately diagnose AF and its various subtypes. While the classification of cardiac arrhythmias with AF is common, distinguishing between AF subtypes is not. Accurate classification of AF subtypes is important for making better clinical decisions and for timely management of the disease. AI techniques are increasingly being considered for image classification and detection in various ailments, as they have shown promising results in improving diagnosis and treatment outcomes. This paper reports the development of a custom 2D Convolutional Neural Network (CNN) model with six layers to automatically differentiate Non-Atrial Fibrillation (Non-AF) rhythm from Paroxysmal Atrial Fibrillation (PAF) and Persistent Atrial Fibrillation (PsAF) rhythms from ECG images. ECG signals were obtained from a publicly available database and segmented into 10-second segments. Applying Constant Q-Transform (CQT) to the segmented ECG signals created a time-frequency depiction, yielding 98,966 images for Non-AF, 16,497 images for PAF, and 52,861 images for PsAF. Due to class imbalance in the PAF and PsAF classes, data augmentation techniques were utilized to increase the number of PAF and PsAF images to match the count of Non-AF images. The training, validation, and testing ratios were 0.7, 0.15, and 0.15, respectively. The training set consisted of 207,828 images, whereas the testing and validation set consisted of 44,538 images and 44,532 images, respectively. The proposed model achieved accuracy, precision, sensitivity, specificity, and F1 score values of 0.98, 0.98, 0.98, 0.97, and 0.98, respectively. This model has the potential to assist physicians in selecting personalized AF treatment and reducing misdiagnosis.

Saliency maps provide insights into artificial intelligence-based electrocardiography models for detecting hypertrophic cardiomyopathy

INTRODUCTION

A 12‑lead electrocardiography (ECG)-based convolutional neural network (CNN) model can detect hypertrophic cardiomyopathy (HCM). However, since these models do not rely on discrete measurements as inputs, it is not apparent what drives their performance. We hypothesized that saliency maps could be used to visually identify ECG segments that contribute to a CNN's robust classification of HCM.

METHODS

We derived a new one‑lead (lead I) CNN model based on median beats using the same methodology and cohort used for the original 12‑lead CNN model (3047 patients with HCM, and 63,926 sex- and age-matched non-HCM controls). One‑lead, median-beat saliency maps were generated and visually evaluated in an independent cohort of 100 patients with a diagnosis of HCM and a high artificial intelligence (AI)-ECG-HCM probability score to determine which ECG segments contributed to the model's detection of HCM.

RESULTS

The one‑lead, median-beat CNN had an AUC of 0.90 (95% CI 0.89-0.92) for HCM detection, similar to the original 12‑lead ECG model. In the independent HCM cohort (n = 100), saliency maps highlighted the ST-T segment in 92 ECGs, the atrial depolarization segment in 12 ECGs, and the QRS complex in 5 ECGs.

CONCLUSIONS

Saliency maps of a one‑lead, median-beat-based CNN model identified perturbations in ventricular repolarization as the main region of interest in detecting HCM.

Detecting Paroxysmal Atrial Fibrillation From an Electrocardiogram in Sinus Rhythm: External Validation of the AI Approach

BACKGROUND

Atrial fibrillation (AF) may occur asymptomatically and can be diagnosed only with electrocardiography (ECG) while the arrhythmia is present.

OBJECTIVES

The aim of this study was to independently validate the approach of using artificial intelligence (AI) to identify underlying paroxysmal AF from a 12-lead ECG in sinus rhythm (SR).

METHODS

An AI algorithm was trained to identify patients with underlying paroxysmal AF, using electrocardiographic data from all in- and outpatients from a single center with at least 1 ECG in SR. For patients without AF, all ECGs in SR were included. For patients with AF, all ECGs in SR starting 31 days before the first AF event were included. The patients were randomly allocated to training, internal validation, and testing datasets in a 7:1:2 ratio. In a secondary analysis, the AF prevalence of the testing group was modified. Additionally, the performance of the algorithm was validated at an external hospital.

RESULTS

The dataset consisted of 494,042 ECGs in SR from 142,310 patients. Testing the model on the first ECG of each patient (AF prevalence 9.0%) resulted in accuracy of 78.1% (95% CI: 77.6%-78.5%), area under the receiver-operating characteristic curve of 0.87 (95% CI: 0.86-0.87), and area under the precision recall curve (AUPRC) of 0.48 (95% CI: 0.46-0.50). In a low-risk group (AF prevalence 3%), the AUPRC decreased to 0.21 (95% CI: 0.18-0.24). In a high-risk group (AF prevalence 30%), the AUPRC increased to 0.76 (95% CI: 0.75-0.78). This performance was robust when validated in an external hospital.

CONCLUSIONS

The approach of using an AI-enabled electrocardiographic algorithm for the identification of patients with underlying paroxysmal AF from ECGs in SR was independently validated.

Usefulness of Heat Map Explanations for Deep-Learning-Based Electrocardiogram Analysis

Deep neural networks are complex machine learning models that have shown promising results in analyzing high-dimensional data such as those collected from medical examinations. Such models have the potential to provide fast and accurate medical diagnoses. However, the high complexity makes deep neural networks and their predictions difficult to understand. Providing model explanations can be a way of increasing the understanding of "black box" models and building trust. In this work, we applied transfer learning to develop a deep neural network to predict sex from electrocardiograms. Using the visual explanation method Grad-CAM, heat maps were generated from the model in order to understand how it makes predictions. To evaluate the usefulness of the heat maps and determine if the heat maps identified electrocardiogram features that could be recognized to discriminate sex, medical doctors provided feedback. Based on the feedback, we concluded that, in our setting, this mode of explainable artificial intelligence does not provide meaningful information to medical doctors and is not useful in the clinic. Our results indicate that improved explanation techniques that are tailored to medical data should be developed before deep neural networks can be applied in the clinic for diagnostic purposes.

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.

Automatic screening of patients with atrial fibrillation from 24-h Holter recording using deep learning

Aims

As the demand for atrial fibrillation (AF) screening increases, clinicians spend a significant amount of time identifying AF signals from massive amounts of data obtained during long-term dynamic electrocardiogram (ECG) monitoring. The identification of AF signals is subjective and depends on the experience of clinicians. However, experienced cardiologists are scarce. This study aimed to apply a deep learning-based algorithm to fully automate primary screening of patients with AF using 24-h Holter monitoring.

Methods and results

A deep learning model was developed to automatically detect AF episodes using RR intervals and was trained and evaluated on 23 621 (2297 AF and 21 324 non-AF) 24-h Holter recordings from 23 452 patients. Based on the AF episode detection results, patients with AF were automatically identified using the criterion of at least one AF episode lasting 6 min or longer. Performance was assessed on an independent real-world hospital-scenario test set (19 227 recordings) and a community-scenario test set (1299 recordings). For the two test sets, the model obtained high performance for the identification of patients with AF (sensitivity: 0.995 and 1.000; specificity: 0.985 and 0.997, respectively). Moreover, it obtained good and consistent performance (sensitivity: 1.000; specificity: 0.972) for an external public data set.

Conclusion

Using the criterion of at least one AF episode of 6 min or longer, the deep learning model can fully automatically screen patients for AF with high accuracy from long-term Holter monitoring data. This method may serve as a powerful and cost-effective tool for primary screening for AF.

Artificial Intelligence for the Detection and Treatment of Atrial Fibrillation

AF is the most common clinically relevant cardiac arrhythmia associated with multiple comorbidities, cardiovascular complications (e.g. stroke) and increased mortality. As artificial intelligence (AI) continues to transform the practice of medicine, this review article highlights specific applications of AI for the screening, diagnosis and treatment of AF. Routinely used digital devices and diagnostic technology have been significantly enhanced by these AI algorithms, increasing the potential for large-scale population-based screening and improved diagnostic assessments. These technologies have similarly impacted the treatment pathway of AF, identifying patients who may benefit from specific therapeutic interventions. While the application of AI to the diagnostic and therapeutic pathway of AF has been tremendously successful, the pitfalls and limitations of these algorithms must be thoroughly considered. Overall, the multifaceted applications of AI for AF are a hallmark of this emerging era of medicine.

Stacked machine learning models to classify atrial disorders based on clinical ECG features: a method to predict early atrial fibrillation

OBJECTIVES

Atrial Tachycardia (AT) and Left Atrial Enlargement (LAE) are atrial diseases that are significant precursors to Atrial Fibrillation (AF). There are ML models for ECG classification; clinical features-based classification is required. The suggested work aims to create stacked ML models that categorize Sinus Rhythm (SR), Sinus Tachycardia (ST), AT, and LAE signals based on clinical parameters for AF prognosis.

METHODS

The classification was based on thirteen clinical parameters, such as amplitude, time domain ECG aspects, and P-Wave Indices (PWI), such as the ratio of P-wave length and amplitude ((P (ms)/P (µV)), P-wave area (µV*ms), and P-wave terminal force (PTFV1(µV*ms). Apart from classifying the ECG signals, the stacked ML models prioritized the clinical features using a pie formula-based technique.

RESULTS

The Stack 1 model achieves 99% accuracy, sensitivity, precision, and F1 score, while the Stack 2 model achieves 91%, 91%, 94%, and 92% for identifying SR, ST, LAE, and AT, respectively. Both stack models obtained a computational time of 0.06 seconds. PTFV1 (µV*ms), P (ms)/P (µV)), and P-wave area (µV*ms) were ranked as crucial clinical features.

CONCLUSION

Clinical feature-based stacking ML models may help doctors obtain insight into important clinical ECG aspects for early AF prediction.

Image based deep learning in 12-lead ECG diagnosis

Background

The electrocardiogram is an integral tool in the diagnosis of cardiovascular disease. Most studies on machine learning classification of electrocardiogram (ECG) diagnoses focus on processing raw signal data rather than ECG images. This presents a challenge for models in many areas of clinical practice where ECGs are printed on paper or only digital images are accessible, especially in remote and regional settings. This study aims to evaluate the accuracy of image based deep learning algorithms on 12-lead ECG diagnosis.

Methods

Deep learning models using VGG architecture were trained on various 12-lead ECG datasets and evaluated for accuracy by testing on holdout test data as well as data from datasets not seen in training. Grad-CAM was utilized to depict heatmaps of diagnosis.

Results

The results demonstrated excellent AUROC, AUPRC, sensitivity and specificity on holdout test data from datasets used in training comparable to the best signal and image-based models. Detection of hidden characteristics such as gender were achieved at a high rate while Grad-CAM successfully highlight pertinent features on ECGs traditionally used by human interpreters.

Discussion

This study demonstrates feasibility of image based deep learning algorithms in ECG diagnosis and identifies directions for future research in order to develop clinically applicable image based deep-learning models in ECG diagnosis.

Role of deep learning methods in screening for subcutaneous implantable cardioverter defibrillator in heart failure

INTRODUCTION

S-ICD eligibility is assessed at pre-implant screening where surface ECG traces are used as surrogates for S-ICD vectors. In heart failure (HF) patients undergoing diuresis, electrolytes and fluid shifts can cause changes in R and T waves. Subsequently, T:R ratio, a major predictor of S-ICD eligibility, can be dynamic.

METHODS

This is a prospective study of patients with structurally normal hearts and HF patients undergoing diuresis. All patients were fitted with Holters® to record their S-ICD vectors. Our deep learning model was used to analyze the T:R ratios across the recordings. Welch two sample t-test and Mann-Whitney U were used to compare the data between the two groups.

RESULTS

Twenty-one patients (age 58.43 ± 18.92, 62% male, 14 HF, 7 normal hearts) were enrolled. There was a significant difference in the T:R ratios between both groups. Mean T: R was higher in the HF group (0.18 ± 0.08 vs 0.10 ± 0.05, p < .001). Standard deviation of T: R was also higher in the HF group (0.09 ± 0.05 vs 0.07 ± 0.04, p = .024). There was no difference between leads within the same group.

CONCLUSIONS

T:R ratio, a main determinant for S-ICD eligibility, is higher and has more tendency to fluctuate in HF patients undergoing diuresis. We hypothesize that our novel neural network model could be used to select HF patients eligible for S-ICD by better characterization of T:R ratio reducing the risk of T-wave over-sensing (TWO) and inappropriate shocks. Further work is required to consolidate our findings before applying to clinical practice.

Wearable Devices Combined with Artificial Intelligence-A Future Technology for Atrial Fibrillation Detection?

Atrial fibrillation (AF) is the most common cardiac arrhythmia in the world. The arrhythmia and methods developed to cure it have been studied for several decades. However, professionals worldwide are still working to improve treatment quality. One novel technology that can be useful is a wearable device. The two most used recordings from these devices are photoplethysmogram (PPG) and electrocardiogram (ECG) signals. As the price lowers, these devices will become significant technology to increase sensitivity, for monitoring and for treatment quality support. This is important as AF can be challenging to detect in advance, especially during home monitoring. Modern artificial intelligence (AI) has the potential to respond to this challenge. AI has already achieved state of the art results in many applications, including bioengineering. In this perspective, we discuss wearable devices combined with AI for AF detection, an approach that enables a new era of possibilities for the future.

Early diagnosis and better rhythm management to improve outcomes in patients with atrial fibrillation: the 8th AFNET/EHRA consensus conference

Despite marked progress in the management of atrial fibrillation (AF), detecting AF remains difficult and AF-related complications cause unacceptable morbidity and mortality even on optimal current therapy. This document summarizes the key outcomes of the 8th AFNET/EHRA Consensus Conference of the Atrial Fibrillation NETwork (AFNET) and the European Heart Rhythm Association (EHRA). Eighty-three international experts met in Hamburg for 2 days in October 2021. Results of the interdisciplinary, hybrid discussions in breakout groups and the plenary based on recently published and unpublished observations are summarized in this consensus paper to support improved care for patients with AF by guiding prevention, individualized management, and research strategies. The main outcomes are (i) new evidence supports a simple, scalable, and pragmatic population-based AF screening pathway; (ii) rhythm management is evolving from therapy aimed at improving symptoms to an integrated domain in the prevention of AF-related outcomes, especially in patients with recently diagnosed AF; (iii) improved characterization of atrial cardiomyopathy may help to identify patients in need for therapy; (iv) standardized assessment of cognitive function in patients with AF could lead to improvement in patient outcomes; and (v) artificial intelligence (AI) can support all of the above aims, but requires advanced interdisciplinary knowledge and collaboration as well as a better medico-legal framework. Implementation of new evidence-based approaches to AF screening and rhythm management can improve outcomes in patients with AF. Additional benefits are possible with further efforts to identify and target atrial cardiomyopathy and cognitive impairment, which can be facilitated by AI.

ECG-iCOVIDNet: Interpretable AI model to identify changes in the ECG signals of post-COVID subjects

OBJECTIVE

Studies showed that many COVID-19 survivors develop sub-clinical to clinical heart damage, even if subjects did not have underlying heart disease before COVID. Since Electrocardiogram (ECG) is a reliable technique for cardiovascular disease diagnosis, this study analyzes the 12-lead ECG recordings of healthy and post-COVID (COVID-recovered) subjects to ascertain ECG changes after suffering from COVID-19.

METHOD

We propose a shallow 1-D convolutional neural network (CNN) deep learning architecture, namely ECG-iCOVIDNet, to distinguish ECG data of post-COVID subjects and healthy subjects. Further, we employed ShAP technique to interpret ECG segments that are highlighted by the CNN model for the classification of ECG recordings into healthy and post-COVID subjects.

RESULTS

ECG data of 427 healthy and 105 post-COVID subjects were analyzed. Results show that the proposed ECG-iCOVIDNet model could classify the ECG recordings of healthy and post-COVID subjects better than the state-of-the-art deep learning models. The proposed model yields an F₁-score of 100%.

CONCLUSION

So far, we have not come across any other study with an in-depth ECG signal analysis of the COVID-recovered subjects. In this study, it is shown that the shallow ECG-iCOVIDNet CNN model performed good for distinguishing ECG signals of COVID-recovered subjects from those of healthy subjects. In line with the literature, this study confirms changes in the ECG signals of COVID-recovered patients that could be captured by the proposed CNN model. Successful deployment of such systems can help the doctors identify the changes in the ECG of the post-COVID subjects on time that can save many lives.

Artificial Intelligence-Enabled ECG: Physiologic and Pathophysiologic Insights and Implications

Advancements in machine learning and computing methods have given new life and great excitement to one of the most essential diagnostic tools to date-the electrocardiogram (ECG). The application of artificial intelligence-enabled ECG (AI-ECG) has resulted in the ability to identify electrocardiographic signatures of conventional and unique variables and pathologies, giving way to tremendous clinical potential. However, what these AI-ECG models are detecting that the human eye is missing remains unclear. In this article, we highlight some of the recent developments in the field and their potential clinical implications, while also attempting to shed light on the physiologic and pathophysiologic features that enable these models to have such high diagnostic yield. © 2022 American Physiological Society. Compr Physiol 12:3417-3424, 2022.

Exploiting exercise electrocardiography to improve early diagnosis of atrial fibrillation with deep learning neural networks

Atrial fibrillation (AF) is the most common type of sustained arrhythmia. It results from abnormal irregularities in the electrical performance of the atria, and may cause heart thrombosis, stroke, arterial disease, thromboembolism, and heart failure. Prior to the onset of atrial fibrillation, most people experience atrial cardiomyopathy which, if effectively managed, can be prevented from progressing to atrial fibrillation. Electrocardiogram (ECG) can show changes in the heartbeats, and is a common and painless tool to detect heart problems. P-waves in exercise ECGs change more drastically than those in regular ECG, and are more effective in the detection of atrial myocardial diseases. In this paper, we propose a deep learning system to help clinicians to early detect if a patient has atrial enlargement or fibrillation. Firstly, a Convolutional Recurrent Neural Network is employed to locate the P-waves in the patient's exercise ECGs taken in the exercise ECG test process. Relevant parameters are then calculated from the located P-waves. Then a Parallel Bi-directional Long Short-Term Memory Network is applied to analyze the obtained parameters and make a diagnosis for the patient. With our proposed deep learning system, the changes of P-waves collected in different phases in the exercise ECG test can be analyzed simultaneously to get more stable and accurate results. The system can take data of different length as input, and is also applicable to any number of ECG collections. We conduct various experiments to show the effectiveness of our proposed system. We also show that the more ECG data collected in the exercise phase are involved, the more effective our system is in diagnosis of the diseases.

Artificial intelligence assessment for early detection and prediction of renal impairment using electrocardiography

Purpose

Although renal failure is a major healthcare burden globally and the cornerstone for preventing its irreversible progression is an early diagnosis, an adequate and noninvasive tool to screen renal impairment (RI) reliably and economically does not exist. We developed an interpretable deep learning model (DLM) using electrocardiography (ECG) and validated its performance.

Methods

This retrospective cohort study included two hospitals. We included 115,361 patients who had at least one ECG taken with an estimated glomerular filtration rate measurement within 30 min of the index ECG. A DLM was developed using 96,549 ECGs of 55,222 patients. The internal validation included 22,949 ECGs of 22,949 patients. Furthermore, we conducted an external validation with 37,190 ECGs of 37,190 patients from another hospital. The endpoint was to detect a moderate to severe RI (estimated glomerular filtration rate < 45 ml/min/1.73m²).

Results

The area under the receiver operating characteristic curve (AUC) of a DLM using a 12-lead ECG for detecting RI during the internal and external validation was 0.858 (95% confidence interval 0.851–0.866) and 0.906 (0.900–0.912), respectively. In the initial evaluation of 25,536 individuals without RI patients whose DLM was defined as having a higher risk had a significantly higher chance of developing RI than those in the low-risk group (17.2% vs. 2.4%, p < 0.001). The sensitivity map indicated that the DLM focused on the QRS complex and T-wave for detecting RI.

Conclusion

The DLM demonstrated high performance for RI detection and prediction using 12-, 6-, single-lead ECGs.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11255-022-03165-w.

State-of-the-art Deep Learning Methods on Electrocardiogram Data: A Systematic Review (Preprint)

Background

Electrocardiogram (ECG) is one of the most common noninvasive diagnostic tools that can provide useful information regarding a patient’s health status. Deep learning (DL) is an area of intense exploration that leads the way in most attempts to create powerful diagnostic models based on physiological signals.

Objective

This study aimed to provide a systematic review of DL methods applied to ECG data for various clinical applications.

Methods

The PubMed search engine was systematically searched by combining “deep learning” and keywords such as “ecg,” “ekg,” “electrocardiogram,” “electrocardiography,” and “electrocardiology.” Irrelevant articles were excluded from the study after screening titles and abstracts, and the remaining articles were further reviewed. The reasons for article exclusion were manuscripts written in any language other than English, absence of ECG data or DL methods involved in the study, and absence of a quantitative evaluation of the proposed approaches.

Results

We identified 230 relevant articles published between January 2020 and December 2021 and grouped them into 6 distinct medical applications, namely, blood pressure estimation, cardiovascular disease diagnosis, ECG analysis, biometric recognition, sleep analysis, and other clinical analyses. We provide a complete account of the state-of-the-art DL strategies per the field of application, as well as major ECG data sources. We also present open research problems, such as the lack of attempts to address the issue of blood pressure variability in training data sets, and point out potential gaps in the design and implementation of DL models.

Conclusions

We expect that this review will provide insights into state-of-the-art DL methods applied to ECG data and point to future directions for research on DL to create robust models that can assist medical experts in clinical decision-making.

Predicting the Risk of Future Multiple Suicide Attempt among First-Time Suicide Attempters: Implications for Suicide Prevention Policy

Suicide is listed in the top ten causes of death in Taiwan. Previous studies have pointed out that psychiatric patients having suicide attempts in their history are more likely to attempt suicide again than non-psychiatric patients. Therefore, how to predict the future multiple suicide attempts of psychiatric patients is an important issue of public health. Different from previous studies, we collect the psychiatric patients who have a suicide diagnosis in the National Health Insurance Research Database (NHIRD) as the study cohort. Study variables include psychiatric patients’ characteristics, medical behavior characteristics, physician characteristics, and hospital characteristics. Three machine learning techniques, including decision tree (DT), support vector machine (SVM), and artificial neural network (ANN), are used to develop models for predicting the risk of future multiple suicide attempts. The Adaboost technique is further used to improve prediction performance in model development. The experimental results show that Adaboost+DT performs the best in predicting the behavior of multiple suicide attempts among psychiatric patients. The findings of this study can help clinical staffs to early identify high-risk patients and improve the effectiveness of suicide prevention.

Classification of De novo post-operative and persistent atrial fibrillation using multi-channel ECG recordings

Atrial fibrillation (AF) is the most sustained arrhythmia in the heart and also the most common complication developed after cardiac surgery. Due to its progressive nature, timely detection of AF is important. Currently, physicians use a surface electrocardiogram (ECG) for AF diagnosis. However, when the patient develops AF, its various development stages are not distinguishable for cardiologists based on visual inspection of the surface ECG signals. Therefore, severity detection of AF could start from differentiating between short-lasting AF and long-lasting AF. Here, de novo post-operative AF (POAF) is a good model for short-lasting AF while long-lasting AF can be represented by persistent AF. Therefore, we address in this paper a binary severity detection of AF for two specific types of AF. We focus on the differentiation of these two types as de novo POAF is the first time that a patient develops AF. Hence, comparing its development to a more severe stage of AF (e.g., persistent AF) could be beneficial in unveiling the electrical changes in the atrium. To the best of our knowledge, this is the first paper that aims to differentiate these different AF stages. We propose a method that consists of three sets of discriminative features based on fundamentally different aspects of the multi-channel ECG data, namely based on the analysis of RR intervals, a greyscale image representation of the vectorcardiogram, and the frequency domain representation of the ECG. Due to the nature of AF, these features are able to capture both morphological and rhythmic changes in the ECGs. Our classification system consists of a random forest classifier, after a feature selection stage using the ReliefF method. The detection efficiency is tested on 151 patients using 5-fold cross-validation. We achieved 89.07% accuracy in the classification of de novo POAF and persistent AF. The results show that the features are discriminative to reveal the severity of AF. Moreover, inspection of the most important features sheds light on the different characteristics of de novo post-operative and persistent AF.

Identification of Characteristic Points in Multivariate Physiological Signals by Sensor Fusion and Multi-Task Deep Networks

Identification of characteristic points in physiological signals, such as the peak of the R wave in the electrocardiogram and the peak of the systolic wave of the photopletismogram, is a fundamental step for the quantification of clinical parameters, such as the pulse transit time. In this work, we presented a novel neural architecture, called eMTUnet, to automate point identification in multivariate signals acquired with a chest-worn device. The eMTUnet consists of a single deep network capable of performing three tasks simultaneously: (i) localization in time of characteristic points (labeling task), (ii) evaluation of the quality of signals (classification task); (iii) estimation of the reliability of classification (reliability task). Preliminary results in overnight monitoring showcased the ability to detect characteristic points in the four signals with a recall index of about 1.00, 0.90, 0.90, and 0.80, respectively. The accuracy of the signal quality classification was about 0.90, on average over four different classes. The average confidence of the correctly classified signals, against the misclassifications, was 0.93 vs. 0.52, proving the worthiness of the confidence index, which may better qualify the point identification. From the achieved outcomes, we point out that high-quality segmentation and classification are both ensured, which brings the use of a multi-modal framework, composed of wearable sensors and artificial intelligence, incrementally closer to clinical translation.

WaSP-ECG: A Wave Segmentation Pretraining Toolkit for Electrocardiogram Analysis

Introduction

Representation learning allows artificial intelligence (AI) models to learn useful features from large, unlabelled datasets. This can reduce the need for labelled data across a range of downstream tasks. It was hypothesised that wave segmentation would be a useful form of electrocardiogram (ECG) representation learning. In addition to reducing labelled data requirements, segmentation masks may provide a mechanism for explainable AI. This study details the development and evaluation of a Wave Segmentation Pretraining (WaSP) application.

Materials and Methods

Pretraining: A non-AI-based ECG signal and image simulator was developed to generate ECGs and wave segmentation masks. U-Net models were trained to segment waves from synthetic ECGs. Dataset: The raw sample files from the PTB-XL dataset were downloaded. Each ECG was also plotted into an image. Fine-tuning and evaluation: A hold-out approach was used with a 60:20:20 training/validation/test set split. The encoder portions of the U-Net models were fine-tuned to classify PTB-XL ECGs for two tasks: sinus rhythm (SR) vs atrial fibrillation (AF), and myocardial infarction (MI) vs normal ECGs. The fine-tuning was repeated without pretraining. Results were compared. Explainable AI: an example pipeline combining AI-derived segmentation masks and a rule-based AF detector was developed and evaluated.

Results

WaSP consistently improved model performance on downstream tasks for both ECG signals and images. The difference between non-pretrained models and models pretrained for wave segmentation was particularly marked for ECG image analysis. A selection of segmentation masks are shown. An AF detection algorithm comprising both AI and rule-based components performed less well than end-to-end AI models but its outputs are proposed to be highly explainable. An example output is shown.

Conclusion

WaSP using synthetic data and labels allows AI models to learn useful features for downstream ECG analysis with real-world data. Segmentation masks provide an intermediate output that may facilitate confidence calibration in the context of end-to-end AI. It is possible to combine AI-derived segmentation masks and rule-based diagnostic classifiers for explainable ECG analysis.

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.

Current trends and opportunities in the methodology of electrodermal activity measurement

Electrodermal activity (EDA) has been measured in the laboratory since the late 1800s. Although the influence of sudomotor nerve activity and the sympathetic nervous system on EDA is well established, the mechanisms underlying EDA signal generation are not completely understood. Owing to simplicity of instrumentation and modern electronics, these measurements have recently seen a transfer from the laboratory to wearable devices, sparking numerous novel applications while bringing along both challenges and new opportunities. In addition to developments in electronics and miniaturization, current trends in material technology and manufacturing have sparked innovations in electrode technologies, and trends in data science such as machine learning and sensor fusion are expanding the ways that measurement data can be processed and utilized. Although challenges remain for the quality of wearable EDA measurement, ongoing research and developments may shorten the quality gap between wearable EDA and standardized recordings in the laboratory. In this topical review, we provide an overview of the basics of EDA measurement, discuss the challenges and opportunities of wearable EDA, and review recent developments in instrumentation, material technology, signal processing, modeling and data science tools that may advance the field of EDA research and applications over the coming years.

Artificial Intelligence for Detection of Cardiovascular-Related Diseases from Wearable Devices: A Systematic Review and Meta-Analysis

PURPOSE

Several artificial intelligence (AI) models for the detection and prediction of cardiovascular-related diseases, including arrhythmias, diabetes, and sleep apnea, have been reported. This systematic review and meta-analysis aimed to identify AI models developed for or applicable to wearable and mobile devices for diverse cardiovascular-related diseases.

MATERIALS AND METHODS

The searched databases included Medline, Embase, and Cochrane Library. For AI models for atrial fibrillation (AF) detection, a meta-analysis of diagnostic accuracy was performed to summarize sensitivity and specificity.

RESULTS

A total of 102 studies were included in the qualitative review. There were AI models for the detection of arrythmia (n=62), followed by sleep apnea (n=11), peripheral vascular diseases (n=6), diabetes mellitus (n=5), hyper/hypotension (n=5), valvular heart disease (n=4), heart failure (n=3), myocardial infarction and cardiac arrest (n=2), and others (n=4). For quantitative analysis of 26 studies reporting AI models for AF detection, meta-analyzed sensitivity was 94.80% and specificity was 96.96%. Deep neural networks showed superior performance [meta-analyzed area under receiver operating characteristics curve (AUROC) of 0.981] compared to conventional machine learning algorithms (meta-analyzed AUROC of 0.961). However, AI models tested with proprietary dataset (meta-analyzed AUROC of 0.972) or data acquired from wearable devices (meta-analyzed AUROC of 0.977) showed inferior performance than those with public dataset (meta-analyzed AUROC of 0.986) or data from in-hospital devices (meta-analyzed AUROC of 0.983).

CONCLUSION

This review found that AI models for diverse cardiovascular-related diseases are being developed, and that they are gradually developing into a form that is suitable for wearable and mobile devices.

Deep Learning Techniques in the Classification of ECG Signals Using R-Peak Detection Based on the PTB-XL Dataset

Deep Neural Networks (DNNs) are state-of-the-art machine learning algorithms, the application of which in electrocardiographic signals is gaining importance. So far, limited studies or optimizations using DNN can be found using ECG databases. To explore and achieve effective ECG recognition, this paper presents a convolutional neural network to perform the encoding of a single QRS complex with the addition of entropy-based features. This study aims to determine what combination of signal information provides the best result for classification purposes. The analyzed information included the raw ECG signal, entropy-based features computed from raw ECG signals, extracted QRS complexes, and entropy-based features computed from extracted QRS complexes. The tests were based on the classification of 2, 5, and 20 classes of heart diseases. The research was carried out on the data contained in a PTB-XL database. An innovative method of extracting QRS complexes based on the aggregation of results from established algorithms for multi-lead signals using the k-mean method, at the same time, was presented. The obtained results prove that adding entropy-based features and extracted QRS complexes to the raw signal is beneficial. Raw signals with entropy-based features but without extracted QRS complexes performed much worse.

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.

Review of Deep Learning-Based Atrial Fibrillation Detection Studies

Atrial fibrillation (AF) is a common arrhythmia that can lead to stroke, heart failure, and premature death. Manual screening of AF on electrocardiography (ECG) is time-consuming and prone to errors. To overcome these limitations, computer-aided diagnosis systems are developed using artificial intelligence techniques for automated detection of AF. Various machine learning and deep learning (DL) techniques have been developed for the automated detection of AF. In this review, we focused on the automated AF detection models developed using DL techniques. Twenty-four relevant articles published in international journals were reviewed. DL models based on deep neural network, convolutional neural network (CNN), recurrent neural network, long short-term memory, and hybrid structures were discussed. Our analysis showed that the majority of the studies used CNN models, which yielded the highest detection performance using ECG and heart rate variability signals. Details of the ECG databases used in the studies, performance metrics of the various models deployed, associated advantages and limitations, as well as proposed future work were summarized and discussed. This review paper serves as a useful resource for the researchers interested in developing innovative computer-assisted ECG-based DL approaches for AF detection.

Deep learning methods for screening patients' S-ICD implantation eligibility

Subcutaneous Implantable Cardioverter-Defibrillators (S-ICDs) are used for prevention of sudden cardiac death triggered by ventricular arrhythmias. T Wave Over Sensing (TWOS) is an inherent risk with S-ICDs which can lead to inappropriate shocks. A major predictor of TWOS is a high T:R ratio (the ratio between the amplitudes of the T and R waves). Currently, patients' Electrocardiograms (ECGs) are screened over 10 s to measure the T:R ratio to determine the patients' eligibility for S-ICD implantation. Due to temporal variations in the T:R ratio, 10 s is not a long enough window to reliably determine the normal values of a patient's T:R ratio. In this paper, we develop a convolutional neural network (CNN) based model utilising phase space reconstruction matrices to predict T:R ratios from 10-second ECG segments without explicitly locating the R or T waves, thus avoiding the issue of TWOS. This tool can be used to automatically screen patients over a much longer period and provide an in-depth description of the behavior of the T:R ratio over that period. The tool can also enable much more reliable and descriptive screenings to better assess patients' eligibility for S-ICD implantation.

ECG Signal Classification Using Deep Learning Techniques Based on the PTB-XL Dataset

The analysis and processing of ECG signals are a key approach in the diagnosis of cardiovascular diseases. The main field of work in this area is classification, which is increasingly supported by machine learning-based algorithms. In this work, a deep neural network was developed for the automatic classification of primary ECG signals. The research was carried out on the data contained in a PTB-XL database. Three neural network architectures were proposed: the first based on the convolutional network, the second on SincNet, and the third on the convolutional network, but with additional entropy-based features. The dataset was divided into training, validation, and test sets in proportions of 70%, 15%, and 15%, respectively. The studies were conducted for 2, 5, and 20 classes of disease entities. The convolutional network with entropy features obtained the best classification result. The convolutional network without entropy-based features obtained a slightly less successful result, but had the highest computational efficiency, due to the significantly lower number of neurons.

Artificial intelligence to diagnose paroxysmal supraventricular tachycardia using electrocardiography during normal sinus rhythm

Aims

Paroxysmal supraventricular tachycardia (PSVT) is not detected owing to its paroxysmal nature, but it is associated with the risk of cardiovascular disease and worsens the patient quality of life. A deep learning model (DLM) was developed and validated to identify patients with PSVT during normal sinus rhythm in this multicentre retrospective study.

Methods and results

This study included 12 955 patients with normal sinus rhythm, confirmed by a cardiologist. A DLM was developed using 31 147 electrocardiograms (ECGs) of 9069 patients from one hospital. We conducted an accuracy test with 13 753 ECGs of 3886 patients from another hospital. The DLM was developed based on residual neural network. Digitally stored ECG were used as predictor variables and the outcome of the study was ability of the DLM to identify patients with PSVT using an ECG during sinus rhythm. We employed a sensitivity map method to identify an ECG region that had a significant effect on developing PSVT. During accuracy test, the area under the receiver operating characteristic curve of a DLM using a 12-lead ECG for identifying PSVT patients during sinus rhythm was 0.966 (0.948-0.984). The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of DLM were 0.970, 0.868, 0.972, 0.255, and 0.998, respectively. The DLM showed delta wave and QT interval were important to identify the PSVT.

Conclusion

The proposed DLM demonstrated a high performance in identifying PSVT during normal sinus rhythm. Thus, it can be used as a rapid, inexpensive, point-of-care means of identifying PSVT in patients.

The application of deep learning in electrocardiogram: Where we came from and where we should go?

Electrocardiogram (ECG) is a commonly-used, non-invasive examination recording cardiac voltage versus time traces over a period. Deep learning technology, a robust artificial intelligence algorithm, can imitate the data processing patterns of the human brain, and it has experienced remarkable success in disease screening, diagnosis, and prediction. Compared with traditional machine learning, deep learning algorithms possess more powerful learning capabilities and can automatically extract features without extensive data pre-processing or hand-crafted feature extraction, which makes it a suitable tool to analyze complex structures of high-dimensional data. With the advances in computing power and digitized data availability, deep learning provides us an opportunity to improve ECG data interpretation with higher efficacy and accuracy and, more importantly, expand the original functions of ECG. The application of deep learning has led us to stand at the edge of ECG innovation and will potentially change the current clinical monitoring and management strategies. In this review, we introduce deep learning technology and summarize its advantages compared with traditional machine learning algorithms. Moreover, we provide an overview on the current application of deep learning in ECGs, with a focus on arrhythmia (especially atrial fibrillation during normal sinus rhythm), cardiac dysfunction, electrolyte imbalance, and sleep apnea. Last but not least, we discuss the current challenges and prospect directions for the following studies.

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.

Artificial intelligence for detecting electrolyte imbalance using electrocardiography

Introduction

The detection and monitoring of electrolyte imbalance is essential for appropriate management of many metabolic diseases; however, there is no tool that detects such imbalances reliably and noninvasively. In this study, we developed a deep learning model (DLM) using electrocardiography (ECG) for detecting electrolyte imbalance and validated its performance in a multicenter study.

Methods and Results

This retrospective cohort study included two hospitals: 92,140 patients who underwent a laboratory electrolyte examination and an ECG within 30 min were included in this study. A DLM was developed using 83,449 ECGs of 48,356 patients; the internal validation included 12,091 ECGs of 12,091 patients. We conducted an external validation with 31,693 ECGs of 31,693 patients from another hospital, and the result was electrolyte imbalance detection. During internal, the area under the receiving operating characteristic curve (AUC) of a DLM using a 12‐lead ECG for detecting hyperkalemia, hypokalemia, hypernatremia, hyponatremia, hypercalcemia, and hypocalcemia were 0.945, 0.866, 0.944, 0.885, 0.905, and 0.901, respectively. The values during external validation of the AUC of hyperkalemia, hypokalemia, hypernatremia, hyponatremia, hypercalcemia, and hypocalcemia were 0.873, 0.857, 0.839, 0.856, 0.831, and 0.813 respectively. The DLM helped to visualize the important ECG region for detecting each electrolyte imbalance, and it showed how the P wave, QRS complex, or T wave differs in importance in detecting each electrolyte imbalance.

Conclusion

The proposed DLM demonstrated high performance in detecting electrolyte imbalance. These results suggest that a DLM can be used for detecting and monitoring electrolyte imbalance using ECG on a daily basis.