Integrating AI-Driven Diagnostics in Arrhythmia Care to Enhance Patient Outcomes: A Narrative Review.
Authors
Affiliations (8)
Affiliations (8)
- Cardiology, St. George's University School of Medicine, St. George's, GRD.
- Surgery, St. George's University School of Medicine, St. George's, GRD.
- Anesthesiology, St. George's University School of Medicine, St. George's, GRD.
- Emergency Medicine, St. George's University School of Medicine, St. George's, GRD.
- Biochemistry, St. George's University School of Medicine, St. George's, GRD.
- Gynecology, St. George's University School of Medicine, St. George's, GRD.
- Biotechnology, BRAC (Bangladesh Rural Advancement Committee) University, Dhaka, BGD.
- Medicine, North Middlesex University Hospital NHS Trust, London, GBR.
Abstract
International morbidity and mortality are led by cardiovascular disease, specifically arrhythmias. The integration of artificial intelligence (AI) can promote earlier identification and, therefore, provide personalized clinical judgments sooner, which can avert these consequences. AI is mainly used in diagnostics, prognostics, and decision support through test interpretations (electrocardiographs (ECGs) and MRI scans) and computing hidden characteristics to utilize a personalized plan rather than a population-based one. While such technology is available in hospitals, some functions are also being integrated into smart wearable devices. These wearable devices allow for continuous monitoring rather than limiting it to in-hospital settings, thus making it easier to enable an earlier diagnosis. However, certain arrhythmias, such as asymptomatic arrhythmias, can go unnoticed by AI. Additionally, there are questions regarding data transparency, privacy, and the financial burden of utilizing and managing AI in medical settings.