Department of Computer Science, College of Engineering, Wayne State University, Detroit, MI, United States.
Department of Family Medicine and Public Health Sciences, School of Medicine, Wayne State University, Detroit, MI, United States.
JMIR Res Protoc. 2024 Sep 20;13:e60361. doi: 10.2196/60361.
Obesity is a common, serious and costly chronic disease. Current clinical practice guidelines recommend that providers augment the longitudinal care of people living with obesity with consistent support for the development of self-efficacy and motivation to modify their lifestyle behaviors. Lifestyle behavior change aligns with the goals of motivational interviewing (MI), a client-centered yet directive counseling modality. However, training health care providers to be proficient in MI is expensive and time-consuming, resulting in a lack of trained counselors and limiting the widespread adoption of MI in clinical practice. Artificial intelligence (AI) counselors accessible via the internet can help circumvent these barriers.
The primary objective is to explore the feasibility of conducting unscripted MI-consistent counseling using Neural Agent for Obesity Motivational Interviewing (NAOMI), a large language model (LLM)-based web app for weight loss counseling. The secondary objectives are to test the acceptability and usability of NAOMI's counseling and examine its ability to shift motivational precursors in a sample of patients with overweight and obesity recruited from primary care clinics.
NAOMI will be developed based on recent advances in deep learning in four stages. In stages 1 and 2, NAOMI will be implemented using an open-source foundation LLM and (1) few-shot learning based on a prompt with task-specific instructions and (2) domain adaptation strategy based on fine-tuning LLM using a large corpus of general psychotherapy and MI treatment transcripts. In stages 3 and 4, we will refine the best of these 2 approaches. Each NAOMI version will be evaluated using a mixed methods approach in which 10 adults (18-65 years) meeting the criteria for overweight or obesity (25.0≥BMI≤39.9) interact with NAOMI and provide feedback. NAOMI's fidelity to the MI framework will be assessed using the Motivational Interviewing Treatment Integrity scale. Participants' general perceptions of AI conversational agents and NAOMI specifically will be assessed via Pre- and Post-Interaction Questionnaires. Motivational precursors, such as participants' confidence, importance, and readiness for changing lifestyle behaviors (eg, diet and activity), will be measured before and after the interaction, and 1 week later. A qualitative analysis of changes in the measures of perceptions of AI agents and counselors and motivational precursors will be performed. Participants will rate NAOMI's usability and empathic skills post interaction via questionnaire-based assessments along with providing feedback about their experience with NAOMI via a qualitative interview.
NAOMI (version 1.0) has been developed. Participant recruitment will commence in September 2024. Data collection activities are expected to conclude in May 2025.
If proven effective, LLM-based counseling agents can become a cost-effective approach for addressing the obesity epidemic at a public health level. They can also have a broad, transformative impact on the delivery of MI and other psychotherapeutic treatment modalities extending their reach and broadening access.
INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/60361.
肥胖是一种常见的、严重的、代价高昂的慢性疾病。目前的临床实践指南建议，医疗服务提供者应通过持续支持自我效能和改变生活方式行为的动机，来增强对肥胖患者的纵向护理。生活方式行为的改变与动机访谈（MI）的目标一致，MI 是一种以患者为中心但又具有指导意义的咨询模式。然而，培训医疗保健提供者熟练掌握 MI 既昂贵又耗时，导致熟练咨询师的短缺，并限制了 MI 在临床实践中的广泛应用。通过互联网提供的人工智能（AI）咨询师可以帮助克服这些障碍。
本研究的主要目的是探索使用基于大型语言模型（LLM）的肥胖动机访谈神经网络代理（NAOMI）进行非脚本化 MI 一致性咨询的可行性，NAOMI 是一款用于体重管理咨询的 LLM 网络应用程序。次要目标是测试 NAOMI 咨询的可接受性和可用性，并检查其在从初级保健诊所招募的超重和肥胖患者样本中改变动机前体的能力。
NAOMI 将基于深度学习的最新进展分四个阶段开发。在第 1 阶段和第 2 阶段，NAOMI 将使用开源基础 LLM 并（1）基于带有特定任务指令的提示的少样本学习，以及（2）基于使用大型一般心理治疗和 MI 治疗转录本微调 LLM 的领域适应策略来实现。在第 3 阶段和第 4 阶段，我们将完善这两种方法中的最佳方法。每个 NAOMI 版本都将通过混合方法进行评估，其中 10 名符合超重或肥胖标准（25.0≥BMI≤39.9）的成年人（18-65 岁）与 NAOMI 互动并提供反馈。使用动机访谈治疗完整性量表评估 NAOMI 对 MI 框架的忠实度。通过预交互和后交互问卷评估参与者对 AI 对话代理和 NAOMI 的一般看法。在交互之前、之后以及 1 周后，将测量生活方式行为（如饮食和活动）改变的动机前体，例如参与者的信心、重要性和准备情况。将对感知 AI 代理和顾问以及动机前体的变化进行定性分析。参与者将在交互后通过基于问卷的评估来评估 NAOMI 的可用性和同理心技能，并通过定性访谈提供有关他们与 NAOMI 体验的反馈。
已经开发了 NAOMI（版本 1.0）。参与者招募将于 2024 年 9 月开始。预计数据收集活动将于 2025 年 5 月结束。
如果被证明有效，基于 LLM 的咨询代理可以成为一种具有成本效益的方法，用于解决公共卫生层面的肥胖问题。它们还可以对 MI 和其他心理治疗治疗模式的提供产生广泛、变革性的影响，扩大其覆盖面并拓宽获取途径。
国际注册报告标识符（IRRID）：PRR1-10.2196/60361。
