Development and feasibility of computer based fidelity monitoring for MI

基于计算机的 MI 保真度监控的开发和可行性

• 批准号: 8427196
• 负责人: Zachary E. Imel
• 金额: $ 25.38万
• 依托单位: UNIVERSITY OF UTAH
• 依托单位国家: 美国
• 财政年份: 2013
• 资助国家: 美国
• 起止时间: 2013-07-01 至 2016-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8427196
• 关键词: Acoustics; Adopted; Agreement; Back; Basic Science; Behavior; Behavior Therapy; Behavioral; Clinical; Code; Cognitive Science; Communities; Compassion; Computers; Data; Development; Discrimination; Distal; Drug Addiction; Drug abuse; Educational workshop; Empathy; Engineering; Evaluation; Evidence based treatment; Feasibility Studies; Feedback; Grant; Human; International; Intervention; Knowledge; Learning; Linguistics; Measures; Methods; Modeling; Monitor; NIH Program Announcements; National Institute of Drug Abuse; Outcome; Patients; Performance; Pharmaceutical Preparations; Positioning Attribute; Privacy; Process; Protocols documentation; Provider; Psychotherapy; Quality Control; Reporting; Research; Running; Semantics; Solutions; Specific qualifier value; Speech; Staging; Supervision; Surveys; System; Technology; Testing; Time; Training; addiction; base; community setting; computer science; computerized data processing; cost; effective therapy; evidence base; experience; graduate student; improved; innovation; member; motivational enhancement therapy; predictive modeling; programs; psychologic; public health relevance; response; satisfaction; scale up; skills; speech recognition; therapy development; tool; treatment as usual; treatment program

DESCRIPTION (provided by applicant): Why is there such a gap between the evidence base for effective drug treatment and its dissemination in the community? Among behavioral interventions, Motivational Interviewing (MI) should be well positioned for high-impact dissemination: There is an international organization devoted to the training and dissemination of MI (The Motivational Interviewing Network of Trainers [MINT]), and MI developers have been at the forefront of research on dissemination. In addition, MI mechanisms are well specified and many are considered basic building blocks of behavioral interventions (e.g., empathy, use of reflections and open questions).1 Empathy, a central MI component, has a strong research tradition in basic science and is among the most consistent predictors of positive outcome in psychotherapy across treatments and disorders.2 At present, quality control in MI relies on ongoing supervision and feedback to therapists in the community. However, measuring therapist behavior is synonymous with behavioral coding by humans, which is not feasible in community settings3. Accordingly, there is no feasible mechanism for evaluating the practice of evidenced based treatments in clinical settings. Advances in linguistic processing have brought a technology for behavioral coding within reach. Specifically, in the basic science and engineering fields, there are tools that combine acoustic and semantic information into predictive models of human-defined knowledge (e.g., empathy codes).4-8 The current proposal brings together a highly interdisciplinary team to produce a viable technology for generating feedback on therapist empathy without human intervention. This technology may eventually be packaged and disseminated in the community. As an initial step, we will apply a sequence of linguistic processing approaches to develop a process for predicting therapist empathy from audio files obtained from MI sessions (AIM 1).9 Next, we will run a feasibility study to determine the performance of the coding technology with new data obtained from MI sessions conducted by novice and experienced therapists (AIM 2). During this evaluation we will troubleshoot issues related to audio quality and speech recognition as well as the process of feedback. In addition, we will evaluate the agreement of computer-based codes with human coding of new sessions. Drug abuse and dependence represents an incredible societal burden. The current research will develop an innovative process for enhancing the ability disseminate and maintain quality control in the behavioral treatment of addictions.

描述（由申请人提供）：为什么有效药物治疗的证据基础与在社区中的传播之间存在这样的差距？在行为干预中，动机性访谈（MI）应该处于高影响力传播的有利地位：有一个国际组织专门从事动机性访谈的培训和传播（the motivation interview Network of Trainers [MINT]），而动机性访谈的开发者一直处于传播研究的前沿。此外，MI机制被很好地指定，并且许多被认为是行为干预的基本组成部分（例如，移情，使用反思和开放式问题）共情是MI的核心组成部分，在基础科学中有着很强的研究传统，并且是跨治疗和障碍的心理治疗中最一致的积极结果预测因素之一目前，MI的质量控制依赖于持续的监督和对社区治疗师的反馈。然而，测量治疗师的行为等同于人类的行为编码，这在社区环境中是不可行的。因此，尚无可行的机制来评估临床环境中循证治疗的实践。语言处理的进步使行为编码技术触手可及。具体来说，在基础科学和工程领域，有一些工具可以将声学和语义信息结合到人类定义的知识（例如，移情代码）的预测模型中。目前的提议汇集了一个高度跨学科的团队，以开发一种可行的技术，在没有人为干预的情况下产生关于治疗师共情的反馈。这项技术最终可能被打包并在社区中传播。作为第一步，我们将应用一系列的语言处理方法来开发一个从MI会话中获得的音频文件中预测治疗师共情的过程（AIM 1）接下来，我们将进行一项可行性研究，以确定编码技术的性能，这些数据来自由新手和经验丰富的治疗师进行的MI会话（AIM 2）。在此评估期间，我们将解决与音频质量和语音识别以及反馈过程有关的问题。此外，我们将评估基于计算机的编码与新会话的人工编码的一致性。药物滥用和依赖是一种难以置信的社会负担。本研究将为提高成瘾行为治疗中质量控制的传播和维持能力提供一个创新的过程。