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.

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.