Leveraging social determinants via artificial intelligence and peer coaching to address racial disparities in primary care among people who use opioids

项目摘要 使用阿片类药物（PWUO）的黑人和拉丁裔人承受着阿片类药物过量死亡的不成比例的负担。 黑人和拉丁裔PWUO所面临的经济负担也因与过剩相关的成本而上升 死亡率和高成本医疗保健服务的使用。与白色PWUO、黑色和拉丁裔PWUO相比 不太可能在急诊科（艾德）开始使用丁丙诺啡， 阿片类药物使用障碍（OUD）的治疗。初级保健中的PWUO种族差异 由健康的社会决定因素（SDH;例如，缺乏同伴支持或健康保险），并可能部分 通过采用创新的移动的保健和同侪辅导战略来解决这一问题。在NIH的支持下， 验证了一个理论驱动的，人工智能（AI）驱动的文本工具，使用自然语言处理， 促进对患者查询的实时文本响应，结合自动文本，促进接收 丁丙诺啡在基于办公室的阿片类药物治疗（OBOT）和社会服务中的应用， 卫生部。这个开源短信工具提供被动提醒，信息内容和交互式的两个- 方式响应算法，无需个人工作人员接触。此外，我们还采用了有效的文化和 为PRC提供结构性谦逊培训，超越SDH，同时解决减少污名化、歧视 健康习惯，以及病人导航，以提高基层护理和社会服务的PWUO。使用 一个三臂，比较有效性试验设计，我们的具体目标是：（1）评估PRC的疗效- 支持基于文本的护理/服务协调与PWUO + AI驱动的SDH增强文本消息 （干预组-1）vs.仅AI驱动的SDH增强文本消息（干预组-2）vs. TAU或打印 社会/医疗服务转介（对照），以加强在ED登记的OBOT中接受丁丙诺啡 黑人/拉丁裔PWUO（N=252）;（2）评价多模式干预（第1组）的实施， RE-AIM和CFIR框架使用3个利益相关者群体的深入访谈：（1）一线提供者 （n=10）;（2）管理员（n=10）;和（3）来自多模式的黑人和拉丁裔PWUO子集 干预组-1（n=30）;（3）确定资源并估计实施的相关成本， 维持多模式干预，并将此信息纳入可定制的预防影响工具 并进行综合经济评价以计算相对经济价值（例如，以每 质量调整生命年，每OUD治疗日的成本），来自医疗保健部门的每个研究组，州- 政策制定者和社会观点，这也将为RE-AIM框架内的实施提供信息。我们的团队是 鉴于为同龄人设计的新型文化和结构谦逊培训的专业知识，准备进行这项研究， 在开源AI驱动的移动的健康创新中， 为在初级保健中使用丁丙诺啡的患者提供远程医疗解决方案。如果成功， 随后将进行有效性-实施混合1型试验。 .

PROJECT SUMMARY Black and Latinx people who use opioids (PWUO) bear a disproportionate burden of opioid overdose deaths. The economic burden faced by Black and Latinx PWUO has also risen due to costs associated with excess mortality and utilization of high-cost healthcare services. Compared to White PWUO, Black and Latinx PWUO are less likely to be initiated on buprenorphine in emergency department (ED) settings and establish care in primary care for the treatment of opioid use disorder (OUD). Racial disparities among PWUO in primary care are driven by social determinants of health (SDH; e.g., lack of peer support or health insurance) and may be partially addressed by adopting innovative mobile health and peer coaching strategies. With NIH support, we have validated a theory-driven, artificial intelligence (AI)-driven texting tool using natural language processing to facilitate real-time text responses to patient queries combined with automated texts facilitating receipt of buprenorphine in office-based opioid treatment (OBOT) and social services that address social determinants of health (SDH). This open source texting tool offers passive reminders, informational content, and interactive two- way response algorithms without personal staff contact. In addition, we have adapted an efficacious cultural and structural humility training for PRCs that goes beyond SDH to also address stigma reduction, discrimination, health habitus, and patient navigation to enhance uptake of primary care and social services for PWUO. Using a three-arm, comparative effectiveness trial design, our specific aims are to: (1) Assess the efficacy of PRC- supported text-based care/services coordination with PWUO + AI-driven SDH-enhanced text messaging (intervention arm-1) vs. AI-driven SDH-enhanced text messaging only (intervention arm-2) vs. TAU or printed social/medical services referrals (control) to enhance the receipt of buprenorphine in OBOT among ED-enrolled Black / Latinx PWUO (N=252); (2) Evaluate the implementation of the multimodal intervention (arm-1) guided by the RE-AIM and CFIR frameworks using in-depth interviews among 3 stakeholder groups: (1) frontline providers (n=10); (2) administrators (n=10); and (3) a subset of the Black and Latinx PWUO from the multimodal intervention arm-1 (n=30); and (3) Identify the resources and estimate the associated cost of implementing and sustaining the multimodal intervention and incorporate this information into a customizable budget-impact tool and conduct a comprehensive economic evaluation to calculate the relative economic value (e.g., cost-per quality-adjusted life years, cost-per OUD treatment days) of each study arm from the healthcare sector, state- policymaker, and societal perspectives which will also inform implementation framed by RE-AIM. Our team is poised to conduct this study given expertise in novel Cultural & Structural Humility Training designed for peers, in open source AI-driven mobile health innovations, and was instrumental in integrating mHealth and telemedicine solutions for patients initiating buprenorphine in primary care. If successful, a multisite effectiveness-implementation hybrid type 1 trial will follow. .