Effect of an artificial intelligence-assisted tool on non-valvular atrial fibrillation anticoagulation management in primary care: protocol for a cluster randomized controlled trial

Abstract Background Atrial fibrillation (AF) is one of the most common cardiac arrhythmia diseases. Thromboembolic prophylaxis plays an essential role in AF therapy, but at present, general practitioners (GPs) are presumed to lack the knowledge and enthusiasm for AF management. Clinical decision support systems (CDSS), assisted by artificial intelligence, help primary care providers (PCPs) make quick, individualized, and correct clinical decisions. This primary aim of the study is to identify whether the promotion of the CDSS would improve the primary care provided to patients with AF. The secondary objectives are mainly to assess the health-economic and clinical benefits from using the CDSS, and the improvement of GPs’ AF management capability. Methods This study will be a prospective cluster randomized controlled trial, conducted among 14 community health centers in Shanghai which were randomized as the intervention group and control group in a ratio of 1:1. The intervention group will use the CDSS in the consultation of patients with AF and the control group will maintain their usual care. The trial will include 498 patients with AF and the follow-up period will be 12 months. The primary outcome is set as the proportion of antithrombotic treatment prescriptions in agreement with recommendations in the latest China’s AF-related guidelines. The secondary outcomes are the frequency of consultation, the compliance rate of international normalized ratio (INR) in patients with warfarin, stroke morbidity, treatment compliance, medication satisfaction, and the cost-benefit analysis. Per-protocol (PP) analysis and the intention-to-treat (ITT) analysis will be conducted. Discussion This study aims to identify whether the application of CDSS to manage patients with AF in China’s community health centers would bring benefits for patients, physicians, and health economics. Trial registration Registry name: 非瓣膜性房颤社区AI辅助管理工具研发及推广效果研究 (Development and promotion of an AI-assisted tool for NVAF management in primary care); registry number: ChiCTR2100052307; registration date: Nov. 22nd, 2021; http://www.chictr.org.cn/showproj.aspx?proj=133849 .