Journal of Invasive Cardiology最新文献

Objectives: Large language models (LLMs) have the potential to assist in complex decision making for interventional cardiology (IC). However, their comparative performance in providing clinical recommendations remains uncertain. In this blinded model‑comparison study, the authors evaluated and compared the quality of recommendations produced by 6 LLMs for complex IC cases.

Methods: Twenty detailed and complex clinical cases focusing on coronary artery disease (n=10) and structural heart disease (n=10) were developed. Six LLMs were tested: default ChatGPT (ChatGPTd), ChatGPT with European Society of Cardiology guidelines (ChatGPT-gl), ChatGPT with internet search enabled (ChatGPTi), Gemini (Google), Mistral 7B (Mistral AI), and Perplexity AI (Perplexity AI, Inc.). Only the ordering of anonymized outputs was randomized to ensure blinding. Five expert ICs independently assessed the anonymized and randomized responses using a 0 to 10 scale for appropriateness, accuracy, relevance, clarity, and clinical utility, generating a composite score. Statistical analysis was performed using a mixed linear model.

Results: Six hundred blinded evaluations (20 cases x 6 models x 5 raters) were analyzed, yielding an overall composite score of 7.1 (95% CI, 7.0-7.2). Performance significantly varied across LLMs (P less than .001), with ChatGPTi (7.8 [7.5-8.0]) and ChatGPT-gl (7.7 [7.4-7.9]) outperforming others. ChatGPTd (6.9 [6.6-7.3]), Mistral 7B (7.0 [6.7-7.3]), and Perplexity AI (7.0 [6.7-7.3]) performed moderately, while Gemini had the lowest score (6.3 [6.0-6.7]). These differences were consistent across all scoring dimensions (P less than .001). Case type did not affect LLM performance (P = .900).

Conclusions: LLMs show promise in IC decision making, but their performance remains suboptimal. Maximizing their potential requires systematic integration of web search capabilities and guideline-based knowledge retrieval.

Objectives: While the transradial approach (TRA) is associated with fewer bleeding complications than the transfemoral approach (TFA), its effect on mortality outcomes in real-world clinical practice remains unclear. This study examines the relationship between vascular access site and mortality in patients undergoing percutaneous coronary intervention (PCI).

Methods: This retrospective cohort study used prospectively collected data from the Netherlands Heart Registration, including 130,813 PCI procedures between 2017 and 2021. The primary outcome was 30-day mortality and the secondary outcome was 1-year mortality. Outcomes were adjusted for baseline variables using multivariable logistic regression and propensity score matching.

Results: TFA was associated with significantly higher mortality at 30 days (odds ratio, 2.00; 95% CI, 1.78-2.25) and 1 year (odds ratio, 1.50; 95% CI, 1.39-1.61). Mortality benefits with TRA were pronounced in acute coronary syndrome and in patients 80 years or older, and were consistent across procedural volumes and center-level TRA adoption rates.

Conclusions: TRA is associated with lower short- and long-term mortality in PCI, supporting its broader adoption in routine clinical practice.

Percutaneous left atrial appendage closure (LAAC) is a rapidly emerging therapy for atrial fibrillation patients not suitable for anticoagulation. The study compared procedural time and adverse events between mechanical Brockenbrough needle and the VersaCross radiofrequency system for WATCHMAN implantation. All patients undergoing LAAC at Vancouver General Hospital were prospectively enrolled. Procedural workflow, times, and complications were compared in 20 patients: 10 using VersaCross radiofrequency system and 10 using Brockenbrough needle. Transseptal puncture success was 100%. The radiofrequency wire reduced total procedural time by 27% (21.5 vs 29.5 minutes; P=.008) and fluoroscopy and contrast use without increasing complications. One ischemic stroke occurred during 360-day follow-up unrelated to the device. The multipurpose radiofrequency system streamlines LAAC workflow and is a safe, efficient alternative to mechanical puncture. Larger randomized trials are warranted to confirm these benefits.