A conversational agent framework for mental health screening: design, implementation, and usability

While chatbots show promise for large-scale mental health screening, few offer interactive, free-text conversations, limiting their appeal for self-administered screening and impeding the timely detection of mental health issues. This study introduces an AI-based chatbot that allows users to respond to validated screening surveys for mental disorders (PHQ-9, GAD-7, and PCL-5) in a natural, free-text conversation manner with real-time feedback. The study's objectives include evaluating the chatbot's usability and reducing the frequency of response clarifications while accurately interpreting users’ responses. The system was assessed running in hybrid NLU mode (Phase 2; <i>N</i> = 587; Mage = 21.56, SD = 5.56, 67.8% women) after being trained on data collected while running in rule-based mode (Phase 1; <i>N</i> = 274; Mage = 21.86, SD = 5.50). During user-chatbot interactions, the chatbot required clarification only 4.64% of the time. Using the AI NLU model, the chatbot could understand user responses in 85.65% of cases and interpret free-text similarly to human annotators. In terms of usability, the chatbot in hybrid NLU mode was perceived as more engaging, friendly, and easier to use than in the rule-based NLU mode, which may be indirectly attributed to the enhanced autonomy provided by the AI NLU model.尽管聊天机器人在大规模心理健康筛查领域展现出应用潜力，但目前鲜有产品支持交互式自由文本对话，这限制了其在自助筛查场景中的适用性，也阻碍了心理健康问题的及时识别。本研究开发了一款基于人工智能的聊天机器人，支持用户以自然自由文本对话形式完成针对精神障碍的标准化筛查问卷（患者健康问卷9项版（PHQ-9）、广泛性焦虑障碍7项版（GAD-7）及创伤后应激障碍检查表5项版（PCL-5））作答，并提供实时反馈。本研究的目标包括评估该聊天机器人的易用性，降低响应澄清频次，同时实现对用户作答内容的精准解读。该系统先基于规则模式（阶段1；<i>N</i> = 274；平均年龄（Mage）=21.86，标准差（Standard Deviation, SD）=5.50；67.8%为女性）采集的数据完成训练，随后在混合式自然语言理解（Natural Language Understanding, NLU）模式下开展评估（阶段2；<i>N</i> = 587；平均年龄（Mage）=21.56，标准差（SD）=5.56；67.8%为女性）。在用户与聊天机器人的交互过程中，该机器人仅需在4.64%的场景下发起澄清请求。借助人工智能NLU模型，该聊天机器人可在85.65%的场景中准确理解用户作答，其对自由文本的解读水平与人工标注者相当。在易用性方面，相较于规则模式，混合式NLU模式下的聊天机器人被认为更具吸引力、更友好且更易于使用，这一差异可间接归因于人工智能NLU模型所赋予的更高自主性。