Cardiac implantable electronic devices (CIEDs) such as pacemakers, implantable cardioverter-defibrillators (ICDs), and cardiac resynchronisation therapy (CRT) devices are generating unprecedented volumes of data in both inpatient and remote settings. Artificial intelligence (AI) techniques are increasingly being applied to enhance the management of these devices and the patients who rely on them. Recent advances demonstrate that machine learning (ML) and deep learning (DL) can improve diagnostic capabilities (for example, by detecting arrhythmias and predicting clinical events), streamline remote monitoring workflows, and optimise device-based therapies. Key applications include AI-driven algorithms that accurately detect true arrhythmias while filtering out false alerts from pacemakers and implantable monitors, neural network models that predict ventricular arrhythmias weeks before ICD shocks, and personalised models that forecast which heart failure patients will respond to CRT. Moreover, novel approaches such as natural language processing (NLP) and reinforcement learning are being explored to integrate diverse data sources and to enable devices to self-adjust their programming. This narrative review summarises the major applications of AI in the CIED domain—diagnostics, remote monitoring, and therapy optimisation—with an emphasis on the recent literature over the past five years. The review highlights important studies and randomised trials in each area, discusses the variety of AI techniques employed, and outlines future directions and challenges (including data standardisation, validation in clinical trials, and regulatory considerations) for translating these innovations into routine clinical care.

KCa3.1 encodes the intermediate-conductance calcium-activated potassium channel KCa3.1, a regulator of membrane potential and calcium-dependent signalling in cardiovascular and immune cells. Increasing evidence indicates that KCa3.1 is a shared driver of vascular remodelling, inflammation, fibrosis, and electrical instability across multiple cardiovascular diseases. In ischaemic heart disease (IHD), KCa3.1 is upregulated in endothelial cells, vascular smooth muscle cells, macrophages, and T lymphocytes, where it promotes smooth muscle proliferation, neointimal formation, and chronic vascular inflammation. Genetic deletion or pharmacological blockade of KCa3.1 reduces atherosclerotic plaque burden and restenosis in animal models. In atrial fibrillation (AF), KCa3.1 contributes to electrical remodelling by shortening atrial action potential duration and to structural remodelling by driving fibroblast activation and collagen deposition. KCa3.1 also regulates macrophage polarisation and pro-inflammatory cytokine release in atrial tissue, linking immune activation to arrhythmogenic substrate formation. Inhibition of KCa3.1 prolongs atrial refractoriness, attenuates atrial fibrosis, and reduces AF inducibility in multiple preclinical models. Emerging data in valvular heart disease suggest that KCa3.1 is upregulated in valvular interstitial cells and regions of active calcification, where it supports myofibroblast differentiation, osteogenic signalling, and inflammatory crosstalk, implicating the channel in fibrocalcific valve degeneration. Collectively, these findings position KCa3.1 as a central molecular integrator of electrical, fibrotic, and inflammatory pathways in cardiovascular disease. The availability of selective KCa3.1 inhibitors with established human safety profiles supports the feasibility of therapeutic translation. Targeting KCa3.1 may enable disease-modifying strategies that extend beyond symptom control to suppress maladaptive cardiovascular remodelling.

Background/Objectives: Accurate localisation of manifest accessory pathways from the 12-lead electrocardiogram remains clinically relevant in Wolff–Parkinson–White syndrome, particularly for pre-procedural planning. Although purpose-built artificial intelligence models have shown promise in ECG interpretation, the reliability of general-purpose multimodal large language models for accessory pathway localisation is unknown. We evaluated two contemporary general-purpose AI systems against an electrophysiology-confirmed reference standard and assessed reproducibility across repeated analyses. Methods: In this retrospective, single-centre proof-of-concept diagnostic accuracy study, 49 consecutive patients with manifest accessory pathways confirmed during electrophysiology study/ablation were included. Anonymised pre-procedural 12-lead ECGs were compiled into a single PDF and analysed by ChatGPT 5 Thinking and Gemini 2.5 Pro using predefined EASY-WPW anatomical categories. Each model was tested in three independent context-reset runs. The primary outcome was repeated-run diagnostic accuracy against the electrophysiology-confirmed pathway location, with confidence intervals calculated using an ECG-clustered approach. Secondary outcomes included majority-vote accuracy, pathway-specific descriptive accuracy, exact output consistency, no-consensus outputs, and “unable to identify” responses. Results: Each model generated 147 repeated outputs from the same 49 ECGs. ChatGPT 5 Thinking correctly localised 28/147 outputs, corresponding to a repeated-run accuracy of 19.0% (ECG-clustered 95% CI 11.5–26.6), while Gemini 2.5 Pro correctly localised 18/147 outputs, corresponding to 12.2% accuracy (95% CI 6.8–17.7). Both models performed below the no-information majority-class baseline of 36.7%. Majority-vote accuracy was 7/49 for ChatGPT 5 Thinking and 2/49 for Gemini 2.5 Pro. Exact output consistency across all three runs was observed in 2/49 ECGs for ChatGPT 5 Thinking and 0/49 ECGs for Gemini 2.5 Pro. Complete no-consensus outputs occurred in 30/49 and 26/49 ECGs, respectively. “Unable to identify” responses were infrequent: 8/147 outputs for ChatGPT 5 Thinking and 2/147 outputs for Gemini 2.5 Pro. Pathway-specific estimates were descriptive only because of class imbalance and small subgroup denominators. Conclusions: General-purpose multimodal large language models demonstrated poor repeated-run accuracy, very low reproducibility, frequent no-consensus outputs, and limited abstention when localising manifest accessory pathways from 12-lead ECGs. These findings do not support their current clinical use for accessory pathway localisation. Future progress is more likely to come from purpose-built, signal-native, or rigorously validated multimodal cardiac AI systems.

Background: Contemporary AF ablation practice has changed rapidly with the introduction of newer energy-delivery platforms. How these changes translate into longitudinal patterns of technology use and procedural characteristics within routine electrophysiology services is less well described. Methods: We performed a retrospective, procedure-level longitudinal service evaluation of AF ablations performed between April 2014 and June 2025 at a United Kingdom (UK) tertiary center. Index and repeat procedures were included. We describe annual technology use and observed skin-to-skin procedure time, fluoroscopy time, and dose-area product (DAP). These are operational measures, not surrogate clinical endpoints. We undertook no adjusted comparative analysis because technology choice was coupled with calendar era and relevant clinical and operator-level covariates were incomplete. Results: The analysis included 2862 procedures, comprising 1878 (66%) radiofrequency ablation (RFA), 735 (26%) cryoballoon, and 249 (9%) pulsed field ablation (PFA). RFA remained the predominant approach until 2020, cryoballoon use peaked in 2018 (n = 138), and PFA increased from 56 procedures in 2023 to 98 in 2024 and 95 in the first half of 2025. The median skin-to-skin time changed from 205 min in 2014 to 104 min in 2025. Observed median fluoroscopy time changed from 32 to 13 min, and median DAP from 3405 to 782 Gy.cm². Conclusions: Over 11 years, the centre experienced a marked change in AF ablation practice, characterised by the progressive adoption of newer technologies, alongside lower recorded procedure durations and radiation exposure. These observations describe service-level temporal trends and should not be interpreted as evidence that any individual ablation modality caused the observed changes or improved clinical outcomes.

Pacemaker therapy is a cornerstone in the management of bradyarrhythmias, yet accumulating data highlight important sex-based disparities across indications, procedural care and long-term outcomes. Women are consistently under-represented among pacemaker recipients, tend to be older at implantation, and are more frequently admitted via emergency pathways despite substantial symptom burden from sinus node dysfunction. Men more often receive pacemakers for atrioventricular conduction disease, at younger ages and with greater cumulative exposure to long-term pacing and device-related procedures. Procedurally, women have higher rates of acute complications, particularly pneumothorax, pocket haematoma and lead perforation, reflecting differences in body size, venous anatomy and myocardial vulnerability. At the same time, men appear to carry a higher long-term risk of device infection. Historical inequities in device selection, with lower use of dual-chamber systems in women, are narrowing but remain a concern in some cohorts. Long-term outcomes suggest that although women experience more early procedural risk, their survival after pacemaker implantation is at least comparable to, and sometimes better than, that of men, with distinct profiles of heart failure, pacing-induced cardiomyopathy and quality-of-life trajectories. Emerging technologies such as leadless pacemakers and conduction system pacing may mitigate several of these disparities by avoiding leads and pockets, reducing dyssynchrony and lowering complication rates in high-risk subgroups. However, women remain under-enrolled in device trials, mechanistic explanations for many sex differences are incomplete, and systematic sex-specific reporting is often lacking. Addressing these gaps is essential to deliver equitable, evidence-based and personalised pacemaker therapy for both women and men. However, most available evidence derives from high-income countries and selected national registries, with limited representation from low and middle-income regions, which may constrain the generalisability of these findings across diverse healthcare settings.

Chronic coronary syndromes (CCSs) are no longer defined only by fixed stenosis of the epicardial coronary arteries. CCSs reflect a dynamic biological process. Key contributors include endothelial activation, lipid retention, macrophage foam-cell formation, vascular smooth muscle cell phenotypic switching, and extracellular matrix remodelling. Microvascular rarefaction, perivascular adipose tissue inflammation, cardiometabolic comorbidity, and biological ageing add further complexity. This broader cellular and molecular model provides a rationale for artificial intelligence (AI), because conventional tools often assess anatomy, physiology, inflammation, and systemic biology in isolation. In this narrative review, we examine how AI and machine learning may support a more mechanistic and individualised approach to CCS by linking cellular pathways to measurable clinical signatures. We focus on AI-enabled plaque phenotyping, non-invasive physiology and ischaemia modelling, assessment of coronary microvascular dysfunction, perivascular inflammation mapping, and the integration of multi-omics with cardiometabolic risk profiling. Most of these tools, however, provide imaging-based or data-derived surrogates rather than direct measurements of endothelial activation, inflammation, or calcification biology. Within this limitation, current evidence suggests that AI can quantify subvisual high-risk plaque features, support non-invasive flow assessment, detect imaging patterns associated with microvascular dysfunction and perivascular inflammation, and, in research settings, relate molecular signatures to long-term cardiovascular risk. Clinical adoption remains constrained by retrospective study designs, limited external validation, heterogeneous imaging protocols, gaps in explainability, regulatory uncertainty, and algorithmic bias across sex, ethnicity, age, and resource settings. Future work should prioritise prospective trials, transparent reporting, federated validation, clinically interpretable outputs, and integration with guideline-based decision pathways. The greatest value of AI in CCS is likely to lie in augmenting mechanistic risk stratification and enabling precision prevention for patients whose risk is poorly captured by anatomy alone.