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

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.

[Digital competence in rhythmology : Training and education]

BACKGROUND

The digital transformation in medicine, particularly in technology-orientated areas such as rhythmology, is leading to a rapid change in diagnostic and therapeutic options. Digital skills are helpful and need to keep up with this pace of change.

RESEARCH QUESTION

Which digital technologies and resources with rhythmological relevance play a role today and in the future?

METHODS

Review of the various digital technologies for rhythm detection and monitoring, as well as current digital resources for training and education.

RESULTS

Rhythm detection and monitoring can be optimized with smart devices and telemedicine, while digital platforms such as social media and virtual reality offer new perspectives in the training of rhythmology specialists.

CONCLUSION

Acquiring digital skills will be the basis for future work in rhythmology.

Longer and better lives for patients with atrial fibrillation: the 9th AFNET/EHRA consensus conference

AIMS

Recent trial data demonstrate beneficial effects of active rhythm management in patients with atrial fibrillation (AF) and support the concept that a low arrhythmia burden is associated with a low risk of AF-related complications. The aim of this document is to summarize the key outcomes of the 9th AFNET/EHRA Consensus Conference of the Atrial Fibrillation NETwork (AFNET) and the European Heart Rhythm Association (EHRA).

METHODS AND RESULTS

Eighty-three international experts met in Münster for 2 days in September 2023. Key findings are as follows: (i) Active rhythm management should be part of the default initial treatment for all suitable patients with AF. (ii) Patients with device-detected AF have a low burden of AF and a low risk of stroke. Anticoagulation prevents some strokes and also increases major but non-lethal bleeding. (iii) More research is needed to improve stroke risk prediction in patients with AF, especially in those with a low AF burden. Biomolecules, genetics, and imaging can support this. (iv) The presence of AF should trigger systematic workup and comprehensive treatment of concomitant cardiovascular conditions. (v) Machine learning algorithms have been used to improve detection or likely development of AF. Cooperation between clinicians and data scientists is needed to leverage the potential of data science applications for patients with AF.

CONCLUSIONS

Patients with AF and a low arrhythmia burden have a lower risk of stroke and other cardiovascular events than those with a high arrhythmia burden. Combining active rhythm control, anticoagulation, rate control, and therapy of concomitant cardiovascular conditions can improve the lives of patients with AF.

Artificial intelligence predicts undiagnosed atrial fibrillation in patients with embolic stroke of undetermined source using sinus rhythm electrocardiograms

BACKGROUND

Artificial intelligence (AI)-enabled sinus rhythm (SR) electrocardiogram (ECG) interpretation can aid in identifying undiagnosed paroxysmal atrial fibrillation (AF) in patients with embolic stroke of undetermined source (ESUS).

OBJECTIVE

The purpose of this study was to assess the efficacy of an AI model in identifying AF based on SR ECGs in patients with ESUS.

METHODS

A transformer-based vision AI model was developed using 737,815 SR ECGs from patients with and without AF to detect current paroxysmal AF or predict the future development of AF within a 2-year period. Probability of AF was calculated from baseline SR ECGs using this algorithm. Its diagnostic performance was further tested in a cohort of 352 ESUS patients from 4 tertiary hospitals, all of whom were monitored using an insertable cardiac monitor (ICM) for AF surveillance.

RESULTS

Over 25.1-month follow-up, AF episodes lasting ≥1 hour were identified in 58 patients (14.4%) using ICMs. In the receiver operating curve (ROC) analysis, the area under the curve for the AI algorithm to identify AF ≥1 hour was 0.806, which improved to 0.880 after integrating the clinical parameters into the model. The AI algorithm exhibited greater accuracy in identifying longer AF episodes (ROC for AF ≥12 hours: 0.837, for AF ≥24 hours: 0.879) and a temporal trend indicating that the AI-based AF risk score increased as the ECG recording approached the AF onset (P for trend <.0001).

CONCLUSIONS

Our AI model demonstrated excellent diagnostic performance in predicting AF in patients with ESUS, potentially enhancing patient prognosis through timely intervention and secondary prevention of ischemic stroke in ESUS cohorts.

Machine Learning and Deep Learning Techniques Applied to Diabetes Research: A Bibliometric Analysis

BACKGROUND

The use of machine learning and deep learning techniques in the research on diabetes has garnered attention in recent times. Nonetheless, few studies offer a thorough picture of the knowledge generation landscape in this field. To address this, a bibliometric analysis of scientific articles published from 2000 to 2022 was conducted to discover global research trends and networks and to emphasize the most prominent countries, institutions, journals, articles, and key topics in this domain.

METHODS

The Scopus database was used to identify and retrieve high-quality scientific documents. The results were classified into categories of detection (covering diagnosis, screening, identification, segmentation, among others), prediction (prognosis, forecasting, estimation), and management (treatment, control, monitoring, education, telemedicine integration). Biblioshiny and RStudio were used to analyze the data.

RESULTS

A total of 1773 articles were collected and analyzed. The number of publications and citations increased substantially since 2012, with a notable increase in the last 3 years. Of the 3 categories considered, detection was the most dominant, followed by prediction and management. Around 53.2% of the total journals started disseminating articles on this subject in 2020. China, India, and the United States were the most productive countries. Although no evidence of outstanding leadership by specific authors was found, the University of California emerged as the most influential institution for the development of scientific production.

CONCLUSION

This is an evolving field that has experienced a rapid increase in productivity, especially over the last years with exponential growth. This trend is expected to continue in the coming years.

Optoelectronic control of cardiac rhythm: Toward shock-free ambulatory cardioversion of atrial fibrillation

Atrial fibrillation (AF) is the most prevalent cardiac arrhythmia, progressive in nature, and known to have a negative impact on mortality, morbidity, and quality of life. Patients requiring acute termination of AF to restore sinus rhythm are subjected to electrical cardioversion, which requires sedation and therefore hospitalization due to pain resulting from the electrical shocks. However, considering the progressive nature of AF and its detrimental effects, there is a clear need for acute out-of-hospital (i.e., ambulatory) cardioversion of AF. In the search for shock-free cardioversion methods to realize such ambulatory therapy, a method referred to as optogenetics has been put forward. Optogenetics enables optical control over the electrical activity of cardiomyocytes by targeted expression of light-activated ion channels or pumps and may therefore serve as a means for cardioversion. First proof-of-principle for such light-induced cardioversion came from in vitro studies, proving optogenetic AF termination to be very effective. Later, these results were confirmed in various rodent models of AF using different transgenes, illumination methods, and protocols, whereas computational studies in the human heart provided additional translational insight. Based on these results and fueled by recent advances in molecular biology, gene therapy, and optoelectronic engineering, a basis is now being formed to explore clinical translations of optoelectronic control of cardiac rhythm. In this review, we discuss the current literature regarding optogenetic cardioversion of AF to restore normal rhythm in a shock-free manner. Moreover, key translational steps will be discussed, both from a biological and technological point of view, to outline a path toward realizing acute shock-free ambulatory termination of AF.

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.

Electrocardiographic P terminal force in lead V1, its components, and the association with stroke and atrial fibrillation or flutter

BACKGROUND

The electrocardiographic (ECG) marker P terminal force V1 (PTFV1) is generally perceived as a marker of left atrial pathology and has been associated with atrial fibrillation or flutter (AF).

OBJECTIVE

The purpose of this study was to determine the association between PTFV1 components (duration and amplitude) and incident AF and stroke/transient ischemic attack (TIA).

METHODS

The study included patients with an ECG recorded at the Copenhagen General Practitioners Laboratory in 2001 to 2011. PTFV1 ≥4 mV·ms was considered abnormal. Patients with abnormal PTFV1 were stratified into tertiles based on duration (PTDV1) and amplitude (PTAV1) values. Cox regressions adjusted for age, sex, and relevant comorbidities were used to investigate associations between abnormal PTFV1 components and AF and stroke/TIA.

RESULTS

Of 267,636 patients, 5803 had AF and 18,176 had stroke/TIA (follow-up 6.5 years). Abnormal PTFV1 was present in 44,549 subjects (16.7%) and was associated with an increased risk of AF and stroke/TIA. Among patients with abnormal PTFV1, the highest tertile of PTDV1 (78-97 ms) was associated with the highest risk of AF (hazard ratio [HR] 1.37; 95% confidence interval [CI] 1.23-1.52) and highest risk of stroke/TIA (HR 1.13; 95% CI 1.05 -1.20). For PTAV1, the highest tertile (78-126 μV) conferred the highest risk of AF and stroke/TIA (HR 1.20; 95% CI 1.09-1.32; and HR 1.21; 95% CI 1.14-1.25, respectively).

CONCLUSION

Abnormal PTFV1 was associated with an increased risk of AF and stroke/TIA. Increasing PTDV1 showed a dose-response relationship with the development of AF and stroke/TIA, whereas the association between PTAV1 and AF was less apparent.

Accuracy of continuous photoplethysmography-based 1 min mean heart rate assessment during atrial fibrillation

AIMS

Although mobile health tools using photoplethysmography (PPG) technology have been validated for the detection of atrial fibrillation (AF), their utility for heart rate assessment during AF remains unclear. Therefore, we aimed to evaluate the accuracy of continuous PPG-based 1 min mean heart rate assessment during AF.

METHODS AND RESULTS

Persistent AF patients were provided with Holter electrocardiography (ECG) (for ≥24 h) simultaneously with a PPG-equipped smartwatch. Both the PPG-based smartwatch and Holter ECG automatically and continuously monitored patients' heart rate/rhythm. ECG and PPG recordings were synchronized and divided into 1 min segments, from which a PPG-based and an ECG-based average heart rate estimation were extracted. In total, 47 661 simultaneous ECG and PPG 1 min heart rate segments were analysed in 50 patients (34% women, age 73 ± 8 years). The agreement between ECG-determined and PPG-determined 1 min mean heart rate was high [root mean squared error (RMSE): 4.7 bpm]. The 1 min mean heart rate estimated using PPG was accurate within ±10% in 93.7% of the corresponding ECG-derived 1 min mean heart rate segments. PPG-based 1 min mean heart rate estimation was more often accurate during night-time (97%) than day-time (91%, P < 0.001) and during low levels (96%) compared to high levels of motion (92%, P < 0.001). A neural network with a 10 min history of the recording did not further improve the PPG-based 1 min mean heart rate assessment [RMSE: 4.4 (95% confidence interval: 3.5-5.2 bpm)]. Only chronic heart failure was associated with a lower agreement between ECG-derived and PPG-derived 1 min mean heart rates (P = 0.040).

CONCLUSION

During persistent AF, continuous PPG-based 1 min mean heart rate assessment is feasible in 60% of the analysed period and shows high accuracy compared with Holter ECG for heart rates <110 bpm.

New concepts in atrial fibrillation pathophysiology

The current classification of atrial fibrillation (AF) is mainly focused on the clinical presentation according to the duration of AF episodes and the mode of termination, which incompletely reflect the severity and progressive nature of the underlying atrial disease. In this review article, "atrial cardiomyopathy" is discussed as a new concept in AF pathophysiology. Electrogram-, imaging-, and biomarker-derived measures and parameters to assess atrial cardiomyopathy, which will likely impact how AF is clinically classified and managed in the future, are presented.