医学
临床终点
心肌梗塞
观察研究
冲程(发动机)
内科学
心脏病学
外科
临床试验
机械工程
工程类
作者
Marta Herrero Brocal,Raquel Samper,Jorge Riquelme,Javier Pineda,Pascual Bordes,Fernando Torres‐Mezcua,José Valencia,Francisco Torres-Saura,María González Manso,Raquel Ajo,Juan Arenas,Eloísa Feliu,Juan Gabriel Martínez,Juan M. Ruiz-Nodar
标识
DOI:10.1093/ehjdh/ztae089
摘要
Abstract Aims Evidence regarding the safety of early discharge following transcatheter aortic valve implantation (TAVI) is limited. The aim of this study was to evaluate the safety of very early (<24) and early discharge (24–48 h) as compared to standard discharge (>48 h), supported by the implementation of a voice-based virtual assistant using artificial intelligence (AI) and natural language processing. Methods and results Single-arm prospective observational study that included consecutive patients who underwent TAVI in a tertiary hospital in 2023 and were discharged under an AI follow-up programme. Primary endpoint was a composite of death, pacemaker implantation, readmission for heart failure, stroke, acute myocardial infarction, major vascular complications, or major bleeding, at 30-day follow-up. A total of 274 patients were included. 110 (40.1%) patients were discharged very early (<24 h), 90 (32.9%) early (24–48 h), and 74 (27.0%) were discharged after 48 h. At 30-day follow-up, no significant differences were found among patients discharged very early, early, and those discharged after 48 h for the primary endpoint (very early 9.1% vs. early 11.1% vs. standard 9.5%; P = 0.88). The AI platform detected complications that could be effectively addressed. The implementation of this follow-up system was simple and satisfactory for TAVI patients. Conclusion Early and very early discharge in patients undergoing TAVI, supported by close follow-up using AI, were shown to be safe. Patients with early and very early discharge had similar 30-day event rates compared to those with longer hospital stays. The AI system contributed to the early detection and resolution of complications.
科研通智能强力驱动
Strongly Powered by AbleSci AI