Advances in screening for undiagnosed atrial fibrillation for stroke prevention and implications for patients with obstructive sleep apnoea: a literature review and research agenda

Exploring the bidirectional relationship between sleep disorders and atrial fibrillation: implications for risk stratification and management

BACKGROUND

Atrial fibrillation (AF) is characterized by the absence of p-waves on ECG and irregular rhythm. It often presents with palpitations either palpitations may occur acutely over a short period or intermittently over several years. Other cardinal symptoms of atrial fibrillation include fatigue, dyspnea, and lightheadedness; it is important however to note that most affected individuals are asymptomatic. Concurrently, sleep disorders such as obstructive sleep apnea (OSA), insomnia, narcolepsy, and circadian rhythm disorders which are a group of conditions associated with the body's internal clock that affect the timing of sleep and alertness, are raising concerns due to their potential associations to arrhythmias. This review explores the bidirectional relationship between AF and sleep disorders, highlighting their implications for risk stratification and management strategies.

MAIN BODY

The narrative approach of this review synthesizes evidence from numerous studies obtained through meticulous literature searches. Specific sleep disorders with a bidirectional relationship with AF are the focus, with scrutiny on the prevalence of this connection. The examination delves into the pathophysiology of sleep-related autonomic dysregulation and inflammation, emphasizing potential management modalities. Various meta-analysis cohorts have highlighted a strong connection between sleep disorders and atrial fibrillation (AF). Patients with sleep disorders, especially OSA, have a higher likelihood of developing AF, and conversely, those with AF are more prone to sleep disorders. This impact is not limited to development, as sleep disorders also contribute to the progression of AF, with AF, in turn, negatively impacting sleep duration and quality. Sleep disorders may play an important role in atrial remodeling as well as electrophysiological abnormalities, rendering the atrial tissue more susceptible to arrhythmogenesis. The narrative review suggests that treating sleep disorders could not only improve sleep quality but also reduce risk factors associated with atrial fibrillation. The effective management of sleep disorders emerges as a potential challenge in preventing and treating atrial fibrillation.

CONCLUSION

In conclusion, this narrative study highlights the bidirectional relationship between sleep disorders and atrial fibrillation. There is a positive correlation, affecting the development, progression, and management of atrial fibrillation. The detrimental impact of sleep disorders on atrial remodeling and electrophysiological abnormalities underscores the significance of their diagnosis and treatment. Education about the importance of sleep and the benefits of sleep disorder treatment becomes imperative for patients with AF and sleep disorders.

Prevention and Treatment of Atrial Fibrillation via Risk Factor Modification

Atrial fibrillation (AF) is the most common clinically significant arrhythmia, and it increases stroke risk. A preventive approach to AF is needed because virtually all treatments such as cardioversion, antiarrhythmic drugs, ablation, and anticoagulation are associated with high cost and carry significant risk. A systematic review was performed to identify effective lifestyle-based strategies for reducing primary and secondary AF. A PubMed search was performed using articles up to March 1, 2021. Search terms included atrial fibrillation, atrial flutter, exercise, diet, metabolic syndrome, type 2 diabetes mellitus, obesity, hypertension, stress, tobacco smoking, alcohol, Mediterranean diet, sodium, and omega-3 fatty acids. Additional articles were identified from the bibliographies of retrieved articles. The control of hypertension, ideally with a renin-angiotensin-aldosterone system inhibitor, is effective for preventing primary AF and recurrence. Obstructive sleep apnea is a common cause of AF, and treating it effectively reduces AF episodes. Alcohol increases the risk of AF in a dose-dependent manner, and abstinence reduces risk of recurrence. Sedentary behavior and chronic high-intensity endurance exercise are both risk factors for AF; however, moderate physical activity is associated with lower risk of AF. Recently, sodium-glucose cotransporter-2 inhibitors and glucagon-like peptide-1 agonists have been associated with reduced risk of AF. Among overweight/obese patients, weight loss of ≥10% is associated with reduced AF risk. Lifestyle changes and risk factor modification are highly effective for preventing AF.

Transfer learning artificial intelligence for automated detection of atrial fibrillation in patients undergoing evaluation for suspected obstructive sleep apnoea: a feasibility study

BACKGROUND

Individuals with obstructive sleep apnoea (OSA) experience a higher burden of atrial fibrillation (AF) than the general population, and many cases of AF remain undetected. We tested the feasibility of an artificial intelligence (AI) approach to opportunistic detection of AF from single-lead electrocardiograms (ECGs) which are routinely recorded during in-laboratory polysomnographic sleep studies.

METHODS

Using transfer learning, an existing ECG AI model was applied to 1839 single-lead ECG traces recorded during in-laboratory sleep studies without any training of the algorithm. Manual review of all traces was performed by two trained clinicians who were blinded to each other's review. Discrepancies between the two investigators were resolved by two cardiologists who were also unaware of each other's scoring. The diagnostic accuracy of the AI algorithm was calculated against the results of the manual ECG review which were considered gold standard.

RESULTS

Manual review identified AF in 144 of the 1839 single-lead ECGs (7.8%). The AI detected all cases of manually confirmed AF (sensitivity = 100%, 95% CI: 97.5-100.0). The AI model misclassified many ECGs with artefacts as AF, resulting in a specificity of 76.0 (95% CI: 73.9-78.0), and an overall diagnostic accuracy of 77.9% (95% CI: 75.9%-97.8%).

CONCLUSION

Transfer learning AI, without additional training, can be successfully applied to disparate ECG signals, with excellent negative predictive values, and can exclude AF among patients undergoing evaluation for suspected OSA. Further signal-specific training is likely to improve the AI's specificity and decrease the need for manual verification.