Developing an Artificial Intelligence Chatbot to Promote HIV Testing

开发人工智能聊天机器人以促进艾滋病毒检测

• 批准号: 10082768
• 负责人: Jeffrey Allen Wickersham
• 金额: $ 24.82万
• 依托单位: YALE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-06-16 至 2022-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10082768
• 关键词: AIDS prevention; Algorithms; Artificial Intelligence; Attention; Automation; Behavior Therapy; Behavioral; Behavioral Model; Cellular Phone; Charge; China; Clinic; Community Networks; Computer Systems; Continuity of Patient Care; Country; Data; Data Analyses; Decision Making; Disclosure; Discrimination; Early Diagnosis; Early treatment; Epidemic; Facebook; Funding; Future; Guidelines; HIV; Health Personnel; Health Services Accessibility; Human; Human Resources; Human immunodeficiency virus test; Hybrids; Income; Individual; Infection; Injecting drug user; Intelligence; Intervention; Learning; Machine Learning; Malaysia; Malaysian; Manuals; Massage; Measures; Medical; Methods; Motivation; Names; Output; Patient Self-Report; Patients; Pattern; Persons; Peru; Physicians; Pilot Projects; Police; Policies; Population; Prevalence; Prevention strategy; Process; Randomized Controlled Trials; Reporting; Research; Research Methodology; Research Personnel; Risk; Same-sex; Sauna; Sex Behavior; Sexual Partners; Sexual Transmission; Social Network; South Africa; Stigmatization; Surveys; Target Populations; Technology; Television; Testing; Time; Viral; Work; base; biobehavior; chatbot; clinical care; computer program; cost effective; criminal behavior; design; efficacy testing; experience; health management; high risk men; humiliation; implementation science; innovation; mHealth; machine learning algorithm; men; men who have sex with men; mobile application; model building; next generation; pre-exposure prophylaxis; prospective; response; same sex behavior; scale up; simulation; skills; smartphone Application; social; social stigma; sodomy; tailored messaging; theories; transmission process; treatment as usual; trial comparing

Title Developing an Artificial Intelligence Chatbot to Promote HIV Testing Abstract (30 Lines) HIV testing jumpstarts the HIV prevention and treatment care continuum. HIV testing levels in men who have sex with men (MSM) and in diverse settings like Malaysia are especially low. MSM increasingly contribute to heightened HIV transmission in the presence of high levels of stigma and discrimination. For high risk MSM, new guidelines recommend frequent HIV testing, ranging from every 3 to 6 months. Yet, HIV testing in MSM often occurs less frequently due to individual (e.g., heightened concerns about risk disclosure), clinic (e.g., confidentiality breaches, and discrimination from healthcare providers) and policy (criminalization of same-sex sexual behaviors) barriers. HIV prevalence in MSM has soared to 21.6% in Malaysia, exceeding 40.9% in Kuala Lumpur. While surveillance surveys of MSM in Malaysia who meet criteria for PrEP suggest that lifetime HIV testing is 70.3%, past-year testing is 40.9% and only 9.5% were tested more than once-yearly despite extraordinary levels of self-reported risk. Once tested, however, MSM with HIV in Malaysia are likely to be treated with ART and achieve viral suppression, making HIV testing a central focus for HIV prevention and treatment. Innovative strategies that motivate and provide guidance for testing among MSM in these settings are therefore urgently needed. Intervening using Information-Motivation-Behavioral Skills (IBM) model of behavioral change is ideally suited to overcome barriers to recommended HIV testing in MSM. Moreover, in settings like Malaysia where the HIV epidemic has transitioned from primarily concentrated in PWID to a volatile epidemic in MSM, theory-guided behavioral change strategies that inform, motivate and provide pragmatic skills to more fully engage in recommended HIV testing are poised to accelerate the HIV prevention and care continuum. Given the many individual, clinic and policy barriers to HIV testing, mobile health (mHealth) interventions that reduce “in person” contact and offer a menu of behavioral skills is ideally suited to increase access to MSM in highly stigmatized settings and promote recommended HIV testing. Recent studies in the U.S., China, South Africa, and Peru show that mHealth interventions using smartphones and apps have the potential to increase HIV testing while maintaining MSM’s confidentiality and providing real-time information, motivation and behavioral skills to overcome barriers. Such mHealth interventions are feasible and acceptable among MSM, including in Malaysia where most MSM find sexual partners using smartphone apps with similar interfaces and functionalities to the proposed intervention. Current mHealth strategies, however, are limited by their lack of automation and need for high-intensity and sustained human inputs, which restricts their scale-up. Artificial intelligence using machine learning (AI/ML) may overcome such limitations, but have yet to be applied to mHealth-based HIV testing algorithms. We therefore aim to develop and pilot test to assess acceptability and feasibility of an AI/ML-Chatbot for HIV testing relative to treatment as usual (control). Findings from this exploratory pilot study will inform a future prospective Type 1 Hybrid implementation science trial.

标题 开发人工智能聊天机器人以促进艾滋病毒检测 摘要（30 行） HIV 检测启动了 HIV 预防和治疗护理的连续性。男性的艾滋病毒检测水平 在马来西亚等不同环境中，男男性行为（MSM）的比例尤其低。 MSM 的贡献越来越大 在存在高度耻辱和歧视的情况下加剧艾滋病毒传播。对于高风险 MSM， 新指南建议频繁进行 HIV 检测，每 3 至 6 个月一次。然而，MSM 中的 HIV 检测 由于个人（例如，对风险披露的高度关注）、诊所（例如， 违反保密规定以及来自医疗保健提供者的歧视）和政策（对同性进行刑事定罪） 性行为）障碍。马来西亚男男性接触者的艾滋病毒感染率飙升至21.6%，超过瓜拉的40.9% 吉隆坡。虽然对马来西亚符合 PrEP 标准的 MSM 进行的监测调查表明，终生 HIV 感染者 测试率为 70.3%，去年测试率为 40.9%，尽管情况非常好，但只有 9.5% 每年测试一次以上 自我报告的风险水平。然而，一旦检测完毕，马来西亚感染艾滋病毒的男男性行为者可能会接受抗逆转录病毒治疗 并实现病毒抑制，使艾滋病毒检测成为艾滋病毒预防和治疗的核心焦点。 在这些环境中激励 MSM 进行测试并提供指导的创新策略是 因此迫切需要。使用信息-动机-行为技能 (IBM) 模型进行干预 行为改变非常适合克服 MSM 推荐的 HIV 检测的障碍。此外，在 在马来西亚等国家，艾滋病毒流行已从主要集中在吸毒者转变为 MSM 中不稳定的流行病，理论指导的行为改变策略，提供信息、激励和提供 更充分地参与建议的艾滋病毒检测的实用技能将加速艾滋病毒的预防 和护理连续体。鉴于艾滋病毒检测、移动医疗（mHealth）方面存在许多个人、诊所和政策障碍 减少“面对面”接触并提供一系列行为技能的干预措施非常适合增加 在高度污名化的环境中获得男男性接触者的机会，并促进推荐的艾滋病毒检测。最近在美国的研究， 中国、南非和秘鲁表明，使用智能手机和应用程序进行移动医疗干预具有潜力 增加 HIV 检测，同时维护 MSM 的机密性并提供实时信息， 克服障碍的动机和行为技能。这种移动医疗干预措施是可行且可接受的 在 MSM 中，包括在马来西亚，大多数 MSM 使用具有类似功能的智能手机应用程序寻找性伴侣 拟议干预的界面和功能。然而，当前的移动医疗策略受到以下因素的限制： 它们缺乏自动化，需要高强度和持续的人力投入，这限制了它们的规模化。 使用机器学习（AI/ML）的人工智能可能会克服这些限制，但尚未得到应用 基于移动医疗的 HIV 检测算法。因此，我们的目标是开发和试点测试来评估可接受性和 相对于常规治疗（对照），AI/ML 聊天机器人进行 HIV 检测的可行性。由此得出的结论 探索性试点研究将为未来的前瞻性 1 型混合实施科学试验提供信息。