Using Technology to Scale Up the Evaluation of Motivational Interviewing

 描述：数以百万计的美国人正在接受有问题的酒精使用的行为干预。2010年，药物滥用和精神健康服务管理局记录了超过180万次药物和酒精问题的治疗，其中许多涉及集体或个人心理治疗。这些干预措施的质量如何？事实上，我们对此一无所知。为了评估心理治疗等行为干预的质量，研究人员依赖于通过行为编码进行的人类评估，这是大规模实施高质量的酒精滥用干预措施的主要障碍。人类对行为干预的评估是一个速度限制因素，需要一种结合了人类专业知识但不依赖人类判断作为评估工具的技术解决方案。目前的K02职业发展建议建立在跨学科研究的基础上，重点是自动评估酒精和药物使用障碍的动机面试(MI)保真度。这项合作研究将来自工程的语音信号处理专家和来自计算机科学的统计文本挖掘专家与MI专家培训人员和研究人员聚集在一起。这项工作目前得到了R01(AA018673)方法开发拨款和R34(DA034860)可行性试验的支持。职业发展活动将包括三个领域的额外培训、经验和合作：1)技术工具和方法(语音信号处理、统计文本挖掘和机器学习)；2)MI的临床过程和变化机制；3)大规模实施。一个高级导师小组将监督职业发展活动，他们是三个核心领域中每个领域的国内和国际公认的专家。这些活动旨在深化关键主题的知识(课程工作、定向阅读)，发展应用技能(语音信号处理、统计文本挖掘和机器学习的实践工作)，促进技术与临床过程的整合(从计算工具和MI临床理论的角度共同审查MI会议)，并为大规模实施自动MI保真度编码和反馈做准备(通过心理健康研究网络吸引大型医疗系统中的关键利益相关者)。K02期间进行的研究将：a)系统地探索需要多少MI会话以及哪些部分(S)才能进行准确的保真度评估；b)开展创新的流程研究，研究口语的语调和韵律如何调节客户改变谈话与患者结局的关联；以及c)在为MI治疗师开发自动化保真度反馈报告时采用尖端视觉设计。这一职业发展奖将支持、加强和推进开发自动化临床支持工具的研究，以向心肌梗死治疗师提供快速反馈。最终目标是为所有与酒精问题作斗争的美国人提高行为干预的质量。

 DESCRIPTION: Millions of Americans are receiving behavioral interventions for problematic alcohol use. In 2010, the Substance Abuse and Mental Health Services Administration documented over 1.8 million treatment episodes for drug and alcohol problems, many involving group or individual psychotherapy. What is the quality of these interventions? In truth, we have no idea. To evaluate the quality of behavioral interventions such as psychotherapy researchers rely on human evaluation through behavioral coding, which is a major impediment to scaling up and sustaining high-quality interventions for alcohol abuse in large-scale implementation. Human evaluation of behavioral interventions is a rate-limiting factor, and a technological solution is needed that incorporates human expertise but does not rely on human judgment as the evaluation tool. The current K02 career development proposal builds on interdisciplinary research focused on automating the evaluation of motivational interviewing (MI) fidelity for alcohol and substance use disorders. This collaborative research brings together speech signal processing experts from engineering and statistical text- mining experts from computer science with MI expert trainers and researchers. The work is currently supported by an R01 (AA018673) methods development grant and an R34 (DA034860) feasibility trial. Career development activities will encompass additional training, experience, and collaboration in three areas: 1) technical tools and methods (speech signal processing, statistical text-mining, and machine learning), 2) clinical process and change mechanisms of MI, and 3) large-scale implementation. A team of senior mentors, who are nationally and internationally recognized experts in each of the three core areas, will oversee the career development activities. These activities have been designed to deepen knowledge in key topics (course work, directed reading), develop applied skills (hands-on work with speech signal processing, statistical text-mining, and machine learning), advance integration of technology with clinical process (co- reviewing MI sessions from the view of computational tools and MI clinical theory), and prepare for large-scale implementation of automated MI fidelity coding and feedback (engage key stakeholders in large healthcare systems via the mental health research network). Research conducted during the K02 will: a) systematically explore how much and which portion(s) of MI sessions are needed for accurate fidelity assessment; b) conduct innovative process research on how tone and prosody of spoken language moderate the association of client change talk with patient outcome; and, c) incorporate cutting-edge visual design in developing an automated fidelity feedback report for MI therapists. This career development award will support, enhance, and move forward research developing automated clinical support tools to provide rapid feedback to MI therapists. The ultimate goal is to improve the quality of behavioral interventions for all Americans struggling with alcohol problems.