Truong Anh T L, Tan Shi-Bei, Wang Golda Z, Yip Alexander W J, Egermark Mathias, Yeung Wesley, Lee V Vien, Chan Mark Y, Kumar Kirthika S, Tan Lester W J, Vijayakumar Smrithi, Blasiak Agata, Wang Laureen Y T, Ho Dean
The N.1 Institute for Health (N.1), National University of Singapore, 28 Medical Drive, Singapore 117456, Singapore.
Department of Biomedical Engineering, College of Design and Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore 117583, Singapore.
Eur Heart J Digit Health. 2023 Oct 24;5(1):41-49. doi: 10.1093/ehjdh/ztad063. eCollection 2024 Jan.
Artificial intelligence-driven small data platforms such as CURATE.AI hold potential for personalized hypertension care by assisting physicians in identifying personalized anti-hypertensive doses for titration. This trial aims to assess the feasibility of a larger randomized controlled trial (RCT), evaluating the efficacy of CURATE.AI-assisted dose titration intervention. We will also collect preliminary efficacy and safety data and explore stakeholder feedback in the early design process.
In this open-label, randomized, pilot feasibility trial, we aim to recruit 45 participants with primary hypertension. Participants will be randomized in 1:1:1 ratio into control (no intervention), home blood pressure monitoring (active control; HBPM), or CURATE.AI arms (intervention; HBPM and CURATE.AI-assisted dose titration). The home treatments include 1 month of two-drug anti-hypertensive regimens. Primary endpoints assess the logistical (e.g. dose adherence) and scientific (e.g. percentage of participants for which CURATE.AI profiles can be generated) feasibility, and define the progression criteria for the RCT in a 'traffic light system'. Secondary endpoints assess preliminary efficacy [e.g. mean change in office blood pressures (BPs)] and safety (e.g. hospitalization events) associated with each treatment protocol. Participants with both baseline and post-treatment BP measurements will form the intent-to-treat analysis. Following their involvement with the CURATE.AI intervention, feedback from CURATE.AI participants and healthcare providers will be collected via exit survey and interviews.
Findings from this study will inform about potential refinements of the current treatment protocols before proceeding with a larger RCT, or potential expansion to collect additional information. Positive results may suggest the potential efficacy of CURATE.AI to improve BP control.
NCT05376683.
诸如CURATE.AI这样的人工智能驱动的小数据平台,通过协助医生确定个性化的抗高血压滴定剂量,在个性化高血压护理方面具有潜力。本试验旨在评估一项更大规模随机对照试验(RCT)的可行性,评估CURATE.AI辅助剂量滴定干预的疗效。我们还将收集初步的疗效和安全性数据,并在早期设计过程中探索利益相关者的反馈。
在这项开放标签、随机、试点可行性试验中,我们旨在招募45名原发性高血压患者。参与者将按1:1:1的比例随机分为对照组(无干预)、家庭血压监测组(积极对照组;HBPM)或CURATE.AI组(干预组;HBPM和CURATE.AI辅助剂量滴定)。家庭治疗包括1个月的两药联合抗高血压方案。主要终点评估后勤方面(如剂量依从性)和科学方面(如可生成CURATE.AI档案的参与者百分比)的可行性,并在“交通灯系统”中定义RCT的进展标准。次要终点评估与每个治疗方案相关的初步疗效[如诊室血压(BP)的平均变化]和安全性(如住院事件)。有基线和治疗后血压测量值的参与者将构成意向性分析。在参与CURATE.AI干预后,将通过退出调查和访谈收集CURATE.AI参与者和医疗服务提供者的反馈。
本研究的结果将为在进行更大规模的RCT之前对当前治疗方案的潜在改进提供信息, 或为收集更多信息的潜在扩展提供信息。阳性结果可能表明CURATE.AI在改善血压控制方面的潜在疗效。
NCT05376683。