Introduction: Chest pain is one of the most common and high-risk presentations in the emergency department (ED), necessitating timely and accurate evaluation to prevent adverse cardiovascular outcomes. Coronary Computed Tomography Angiography (CCTA) has emerged as a promising non-invasive modality with high sensitivity (90–100%) and a negative predictive value (98–100%) for ruling out significant coronary artery disease (CAD), as evidenced by trials such as ROMICAT II and ACRIN-PA. Despite its expanding role in ED triage, further evaluation of its impact on patient-centered outcomes is essential. Methods: A systematic review was conducted in accordance with PRISMA guidelines. Studies published between January 2010 and June 2025 were identified from PubMed, Embase, and the Cochrane Library. Eligible studies included randomized controlled trials and prospective cohort studies assessing CCTA in ED patients with suspected acute coronary syndrome (ACS), compared with alternative diagnostic strategies, and reporting outcomes, including diagnostic accuracy, time to diagnosis, ED discharge rates, hospital admissions, and cost-effectiveness. Results: Twenty-three studies comprising over 60,000 patients were included. CCTA in low- to intermediate-risk patients significantly reduced diagnostic time (up to 54%), increased early ED discharges, and lowered unnecessary admissions. It consistently demonstrated excellent diagnostic performance, with pooled sensitivity ≥90% and near-perfect negative predictive value. Economic evaluations showed reduced costs due to shorter ED stays and less downstream testing. Challenges included radiation exposure, contrast use, and incidental findings. Conclusions: CCTA enhances ED efficiency and safety in ACS evaluation, offering accurate CAD exclusion and resource optimization. Future studies should explore its long-term cost-effectiveness and integration into high-sensitivity troponin protocols.

Background: AI is rapidly reshaping cardiovascular medicine, particularly within imaging-intensive fields such as interventional cardiology. Advances in machine learning and deep learning have enabled automated analysis of complex cardiovascular datasets and opened new opportunities for decision support across the coronary care continuum. Objectives: This review summarises current and emerging applications of AI in interventional cardiology, spanning pre-procedural imaging, intraprocedural guidance, outcome prediction, and future technological developments. Key findings: In the pre-procedural setting, AI-enhanced coronary CT angiography, AI-derived fractional flow reserve, and automated plaque characterisation improve risk stratification and patient selection for invasive angiography. Within the catheterisation laboratory, AI applications include automated angiographic interpretation, intravascular ultrasound and optical coherence tomography analysis, lesion classification, optimisation of stent sizing and deployment, emerging roles in structural heart interventions, and periprocedural haemodynamic monitoring. Machine learning models are also increasingly used for risk stratification, predicting bleeding, contrast-induced nephropathy, and mortality after percutaneous coronary intervention. Despite these advances, important challenges remain, including regulatory oversight, algorithm validation, bias mitigation, data governance, clinician education, and unresolved liability issues. Conclusion: AI is evolving from a diagnostic imaging adjunct to a comprehensive decision-support platform in interventional cardiology. Emerging technologies such as real-time AI-assisted catheterisation laboratory systems, multimodal data integration, digital twin modelling, and AI-guided robotic interventions may further transform coronary intervention workflows, positioning AI as a procedural co-pilot that augments rather than replaces physician expertise.