Evaluation of AI-Based Chatbots for Improving Anxiety-Related Mental Health Literacy: A Randomized Controlled Trial
试验速览
- 阶段
- 不适用
- 状态
- 进行中（未招募）
- 发起方
- 入组人数
- 200
- 试验地点
- 1
- 主要终点
- Anxiety Literacy Scale (ALS)
研究概览
简要总结
The goal of this clinical trial is to examine whether AI-based chatbots can improve anxiety-related mental health literacy in adults with varying levels of anxiety. The study aims to learn whether interactive AI chatbots can improve understanding of anxiety, attitudes toward anxiety, help-seeking intentions, confidence in supporting others, and anxiety symptoms, compared with standard text-based educational materials.
The main questions it aims to answer are:
- Does an AI-based psychoeducation chatbot improve anxiety-related mental health literacy compared with text-based psychoeducation?
- Does adding interactive anxiety simulation conversations further improve mental health literacy and related outcomes compared with psychoeducation alone?
Researchers will compare participants who use an AI psychoeducation chatbot alone, participants who use an AI psychoeducation chatbot combined with anxiety simulation chatbots, and participants who receive text-based psychoeducation, to see whether the AI-based interventions lead to greater improvements in mental health literacy and related outcomes.
Participants will:
- Complete baseline questionnaires assessing anxiety-related knowledge, attitudes, and symptoms
- Be randomly assigned to one of three groups: AI psychoeducation chatbot, AI psychoeducation chatbot plus anxiety simulation chatbots, or text-based psychoeducation
- Use the assigned intervention over a one-week period
- Complete follow-up questionnaires immediately after the intervention and at later follow-up time points
研究设计
- 研究类型
- Interventional
- 分配方式
- Randomized
- 干预模型
- Parallel
- 主要目的
- Prevention
- 盲法
- None
入排标准
- 年龄范围
- 18 Years 至 65 Years（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 是
入选标准
- •Aged between 18 and 65 years.
- •Able to use digital devices (e.g., smartphone or computer) to complete AI-based conversations and questionnaires.
- •Willing to participate in a one-week online intervention.
- •Proficient in Chinese and able to understand study instructions and provide informed consent.
- •Participants with varying levels of anxiety symptoms are eligible.
排除标准
- •Self-reported history of severe psychiatric disorders (e.g., psychotic disorders, bipolar disorder).
- •Currently receiving psychological or psychiatric treatment.
- •Severe mental health symptoms requiring immediate clinical intervention.
- •Inability to use mobile or internet-enabled devices independently.
结局指标
主要结局
Anxiety Literacy Scale (ALS)
时间窗: pre-intervention, post-intervention (1-week), 4-week follow-up, 12-week follow-up
The Anxiety Literacy Scale is a 22-item questionnaire designed to assess individuals' knowledge about anxiety. Each statement is answered using a binary response format (true or false). For each item, participants are also asked to rate their certainty in their response on a 5-point Likert scale. Correct responses are summed to produce a total knowledge score, with higher scores indicating greater anxiety-related mental health literacy. Certainty ratings are used to assess participants' confidence in their knowledge and to examine the calibration between knowledge accuracy and subjective certainty.
Anxiety Stigma Scale
时间窗: pre-intervention, post-intervention (1-week), 4-week follow-up, 12-week follow-up
The Anxiety Stigma Scale is designed to measure stigma associated with Anxiety. It has two subscales which measure two different types of stigma: personal and perceived. The Personal Stigma Subscale measures stigma in the respondents own attitudes towards anxiety by asking them to indicate how strongly they personally agree with ten statements about anxiety. The Perceived Stigma Subscale measures the respondent's perception about the attitudes of others towards anxiety by asking them to indicate what they think most other people believe about the same ten statements. Responses to each item are measured on a five-point scale (ranging from zero 'strongly disagree' to four 'strongly agree'). Higher scores indicate higher levels of depression stigma.
Adapted General Help-Seeking Questionnaire
时间窗: pre-intervention, post-intervention (1-week), 4-week follow-up, 12-week follow-up
The General Help-Seeking Questionnaire (GHSQ) in this study is an adapted 17-item version designed to fit Chinese cultural contexts. It assesses an individual's intentions to seek help for personal or emotional problems from both formal sources (e.g., mental health professionals, doctors) and informal sources (e.g., family, friends). Each item is rated on a 7-point Likert scale, ranging from 1 ("Extremely Unlikely") to 7 ("Extremely Likely"), with higher scores indicating a greater likelihood of seeking help.
Confidence in Helping Others
时间窗: pre-intervention, post-intervention (1-week), 4-week follow-up, 12-week follow-up
The Confidence in Helping Others Scale is a self-developed, 13-item questionnaire designed to measure participants' confidence in providing support to individuals experiencing mental health issues. Each item is rated on a 5-point Likert scale, ranging from 1 ("Strongly Disagree") to 5 ("Strongly Agree"), with higher scores indicating greater confidence in recognizing symptoms, offering emotional support, and encouraging help-seeking.
Mental Health Self-efficacy Scale
时间窗: pre-intervention, post-intervention (1-week), 4-week follow-up, 12-week follow-up
The Mental Health Self-efficacy Scale is a 6-item questionnaire designed to measure participants' confidence in effectively manage stress, anxiety or depression about themself. Each item is rated on a 10-point Likert scale, ranging from 1 ("Not at all confident") to 10 ("Totally confident"), with higher scores indicating greater confidence in self-efficacy about mental health.
Bot Usability Scale
时间窗: post-intervention (1-week)
The Bot Usability Scale (BUS) in this study is an adapted 11-item version designed to assess the usability of AI-based chatbots. It evaluates participants' perceptions of the ease of use, effectiveness, efficiency, and overall user experience of the chatbots. The scale uses a 5-point Likert scale, ranging from 1 ("Strongly Disagree") to 5 ("Strongly Agree"), with higher scores indicating better perceived usability. Participants will complete the adapted BUS separately for both the AI Educator and the AI Anxiety Friend Simulators. The adapted BUS maintains the core usability assessment principles of the original scale while being tailored for AI-driven conversational agents.
次要结局
- General Anxiety Disorder (GAD-7)(pre-intervention, post-intervention (1-week), 4-week follow-up, 12-week follow-up)
- Patient Health Questionnaire (PHQ-9)(pre-intervention, post-intervention (1-week), 4-week follow-up, 12-week follow-up)
- Intolerance of Uncertainty Scale(pre-intervention, post-intervention (1-week), 4-week follow-up, 12-week follow-up)
- Negative Effects Scale, NES(post-intervention (1-week))
- Basic Empathy Scale in Adults (BES-A)(pre-intervention, post-intervention (1-week), 4-week follow-up, 12-week follow-up)
- Mental Health Behavior(pre-intervention, 4-week follow-up, 12-week follow-up)