A Chatbot Utilizing Machine Learning and Natural Language Processing to Implement the Brief Negotiation Interview to Improve Engagement in Buprenorphine Treatment among Justice-Involved Individuals

项目总结/摘要 本行政补充建议由中心的3人小组参与， Progressive Recovery，LLC（CPR）in the Innovation Corps（I-Corps™），这是一个为期8周的密集计划， 为受资助的技术驱动型初创企业制定成功的商业化计划和商业模式 通过NIH的SBIR第一阶段机制。该方案将包括培训、结构和问责制 与主要利益攸关方和其他人进行了100次访谈，他们的专业知识将为 公司的计划。SBIR第一阶段授予CPR（小企业关注，SBC），该应用程序 预测解决的问题是，最有可能死于阿片类药物过量的人是 最不可能得到救命药的人从监狱出来的参与司法的人 过量死亡的风险（比一般人群高8倍），但这些人中只有1/20接受 丁丙诺啡（bup），一种安全，有效的药物，已被证明可以降低一个人的死亡风险， 一半过量。有一个迫切需要促进增加bup治疗参与其中 个体这一人群接受bup的两个最大障碍是1）系统水平障碍和2）低 个人动机的水平。我们将打破系统级的障碍， 缓刑制度，是污名化，并减少了机会，一个bup转介与人工智能 基于AI的聊天机器人。这将是唯一的工具需要接受转介到一个bup提供者。我们还将 通过对聊天机器人进行编程以提供有效的简短谈判， 面试（BNI），而不需要训练有素的人。我们的目标是：目标1：设计和开发原型 聊天机器人来激励BUP参与。里程碑：（a）以人为本的设计（HCD）采访关键人物 利益相关者;以及（B）使用机器学习（ML）和自然语言处理创建聊天机器人 (NLP)与移动的应用程序集成;目标2：对60名缓刑犯进行为期4周的试点研究 随机分配给BNI聊天机器人或数字资源（即，数字递送OUD和丁丙诺啡 教育和转介资源）。以下3人团队在开发和 将数字健康解决方案推向市场，并致力于追求I-Corps的独特优势 程序.所有3个都能够满足培训计划的时间密集型要求：1）迈克尔V。 Pantalon博士，CEO; 2）Marianne S. Pantalon博士，PI和3）托马斯惠勒，行业专家和首席技术官。 有了这个复杂的计划，CPR将处于更好的位置，以确保SBIR第二阶段的资金。

Project Summary/Abstract This Administrative Supplement proposes the participation of a 3-member team from the Center for Progressive Recovery, LLC (CPR) in the Innovation Corps (I-Corps™), an intensive, 8-week program focused on developing a successful commercialization plan and business model for technology-driven start-ups funded by NIH’s SBIR Phase I mechanism. The program would entail training, as well as structure and accountability around conducting 100 interviews with key stakeholders and others whose expertise would inform the company’s plans. The SBIR Phase I award to CPR (the small business concern, SBC) that this application is predicated on addresses the problem that the people at the greatest risk of dying from an opioid overdose are the least likely to get life-saving medication. Justice- involved individuals coming out of prison have the highest risk of death by overdose (8x greater than the general population), yet only 1 in 20 of these individuals receive buprenorphine (bup), a safe, effective medication that has been shown to reduce a person’s risk of death by overdose by half. There is an urgent need to facilitate an increase in bup treatment engagement among these individuals. Two of the top barriers to receiving bup for this population are 1) system level barriers and, 2) low levels of individual motivation. We will disrupt system level barriers by circumventing the pieces of the probation system that are stigmatizing and reduce the chances of a bup referral with an artificial intelligence (AI)-based chatbot. This will be the only tool needed to receive a referral to a bup provider. We will also address low individual motivation with the chatbot by programming it to deliver the efficacious Brief Negotiation Interview (BNI) without the need for a trained human. Our aims are: Aim 1: Design and develop a prototype chatbot to motivate bup engagement. Milestones: (a) human-centered design (HCD) interviews with key stakeholders; and (b) creation of a chatbot using machine learning (ML) and natural language processing (NLP) that is integrated with a mobile application; Aim 2: Conduct a 4-week pilot study with 60 probationers randomly assigned to the BNI Chatbot or Digital Resources (i.e., Digitally-delivered OUD and buprenorphine education and referral resources). The following 3-member team has deep expertise in developing and bringing to market digital health solutions and was formed to pursue the unique benefits of the I-Corps program. All 3 are able to meet the time-intensive requirements of the training program: 1) Michael V. Pantalon, Ph.D., CEO; 2) Marianne S. Pantalon, Ph.D., PI, and 3) Thomas Wheeler, Industry Expert and CTO. With this sophisticated program, CPR would be in a much better position to secure SBIR Phase II funding.