Artificial Intelligence Driven Software Systems for Cardiovascular Disease Detection Using Physiological Signals: A Systematic Review

Cardiovascular disease (CVD) exacts an extraordinary global toll, with annual mortality exceeding 17.9 million lives and representing nearly one-third of all deaths worldwide. Reducing diagnostic delays, particularly in resource-limited settings, requires innovative, scalable, and cost-effective solutions. Artificial intelligence (AI) integrated with mobile and wearable technologies offers a promising pathway, leveraging physiological signals such as electrocardiogram (ECG), photoplethysmogram (PPG), and phonocardiogram (PCG) for real-time cardiovascular assessment. Despite rapid advances, the current evidence base remains fragmented, impeding identification of validated approaches and actionable pathways toward clinical translation. A systematic review is therefore essential to consolidate existing evidence and establish the current technological landscape. A PRISMA-guided search across five electronic databases-Scopus, Web of Science, PubMed, Embase, and IEEE Xplore-yielded 30 eligible studies. Most systems utilised ECG (66.6%) and deep learning models such as long short-term memory (LSTM) and convolutional neural networks (CNNs). Although several studies (n = 10) reported accuracies approaching or exceeding 98%, only a few (n = 7) demonstrated external validation, and fewer still (n = 3) reported large-scale clinical deployment. While AI-enabled CVD systems are becoming technically sophisticated, limitations in data diversity, interpretability, regulatory compliance, and clinical integration hinder real-world translation. This review establishes a structured taxonomy of AI-enabled software and mobile-based CVD diagnostic systems, revealing substantial technical progress alongside persistent barriers. A three-directional framework is proposed, addressing generalisability through multi-signal models, interpretability via LLM-driven clinical narratives, and accessibility through edge-cloud deployment, to guide future research toward clinically deployable systems.