Editorial: The role of artificial intelligence technologies in revolutionizing and aiding cardiovascular medicine

Abstract

Cardiovascular disease (CVD) continues to be the foremost worldwide contributor to mortality and morbidity (Roth et al., 2020), accounting for roughly 17.9 million fatalities each year-a burden anticipated to increase due to aging populations and lifestyle modifications (World Health Organization, 2021). Despite progress in prevention, diagnosis, and treatment, the application of research in clinical practice continues to be difficult, as cardiologists face complicated decision-making amidst varied patient requirements, swiftly changing evidence, and the incorporation of multimodal data from high-resolution imaging and ongoing biomedical signal tracking (Johnson et al., 2018). The exponential increase in medical data and the advancement of diagnostic tools present a potential for enhancing care, yet they also pose challenges in providing timely and personalised interventions. Artificial intelligence (AI) has been recognised as a transformative technology capable of improving diagnostic precision, optimising treatment methodologies, and ultimately alleviating the worldwide incidence of CVD by connecting research innovation with practical clinical application (Lopez-Jimenez et al., 2020). AI encompasses a variety of technologies that have rapidly progressed to improve individual decisionmaking and address important issues in cardiovascular care, including machine learning, deep learning, computer vision, pattern recognition, federated learning, natural language processing, and generative AI (Haq et al., 2022). Traditionally, the diagnosis and treatment of cardiovascular diseases have mostly relied on conventional approaches, which usually face restrictions in accuracy, fast identification, and tailored strategies for treatment (Olawade et al., 2024). The utilisation of AI in cardiology takes note of an unprecedented evolution in the manner of data-driven decisions and predictive models leading to personalised medicine tailored to the individual preferences of each patient (Olawade et al., 2023). Utilising extensive data obtained from various sources, including electronic health records (EHRs), medical imaging (MRI, CT), genomic profiles, wearable technology, biosignals (ECG, PPG), and realtime tracking platforms (Gupta et al., 2022), AI makes limitless breakthroughs in deciphering complex patterns concerning population demographics (Olawade et al., 2024) by means of computational power to evaluate these massive datasets. For example, AI-predictive models can predict the chances of clinical-anatomical intervention after endovascular repair (Attallah and Ma, 2014;Karthikesalingam et al., 2015). Additionally, computer-aided diagnostic systems based on deep learning techniques assist in diagnosing myocardial infarction (MI) in its early stages using MRI scans (Attallah and Ragab, 2023). Moreover, ML-based analytics, in conjunction with biosignals such as the ECG, can detect cardiac abnormalities in fetal during pregnancy (Al-Saadany et al., 2022). This change in technology is particularly of utmost importance with the rapid growth of wearable AI-based devices like smartwatches that support atrial fibrillation (AF) detection and treatment in real-time (Tison et al., 2018). These advances help to enhance both risk stratification and diagnosis accuracy for personalised outcome predictions such as recurrent heart failure or post-interventional effects (Johnson et al., 2018).Advanced AI technologies are also going to enhance research and clinical programs within cardiology to achieve validity, efficiency, and improved patient-centered care AI drives a transformative impact on cardiovascular healthcare including drug discovery and development, risk profiling, predictive analysis, and clinical decision support system advancement. However, reaching the full potential of AI in cardiology requires synergistic cooperation among cardiologists, computer scientists, and biomedical engineers to create comprehensive models with multiple data types