ChatGPT应答的沟通特征与日本梅毒就医意向:一项对照对话实验
Communication features of ChatGPT responses and care-seeking intention for syphilis in Japan: a controlled dialogue experiment.
Communication features of ChatGPT responses and care-seeking intention for syphilis in Japan: a controlled dialogue experiment.
梅毒是一种重要的再发传染病,在获得保密诊疗服务受限、污名化可能延误求助的农村和偏远地区,就诊前支持可能尤为重要。我们在日本一个模拟的梅毒相关焦虑情境中,考察了ChatGPT生成回复中的沟通特征如何影响感知的咨询满意度和寻求专业诊疗的意向。我们开展了一项日语对照对话实验,采用模拟的担忧感染梅毒的患者与ChatGPT(GPT-4o mini)之间的标准化互动。在48次三轮会话中,人工智能(AI)回复根据所要求的沟通立场和个人信息披露情况而有所不同。对支持性沟通特征、立场一致性、个性化一致性、可读性(jReadability)和信息量(字符数)进行了编码。三名卫生专业人员评估者使用咨询与关系共情量表(CARE)评定咨询满意度,并使用准备度标尺评定就医意向。CARE评分显示中等程度的评估者间信度,而意向评分显示较低的一致性。两条AI回复包含医学错误信息。在分层回归分析中,较长的回复和较高的可读性与更高的满意度相关,而在支持性沟通行为中,赞扬表达与满意度独立相关。满意度与就医意向强烈相关(β=0.80,<0.001)。在日语模拟梅毒咨询中,信息量、可读性和赞扬表达与更高的感知咨询满意度相关,而后者又与更强的寻求专业诊疗意向相关。这些发现提示,对话式AI可作为低门槛、匿名的就诊前支持工具,鼓励及时求助,尤其是在保密获得性健康服务受限的农村和偏远环境中。意向评分的评估者间一致性较低以及错误信息的存在,凸显了稳健结局测量和安全保障措施的必要性。
Syphilis is a major re-emerging infectious disease, and pre-consultation support may be particularly important in rural and remote areas where access to confidential care is limited and stigma can delay help-seeking. We examined how communication features in ChatGPT-generated responses influence perceived consultation satisfaction and intention to seek professional care in a simulated syphilis-related anxiety scenario in Japan. We conducted a controlled dialogue experiment in Japanese using standardized interactions between a simulated patient concerned about syphilis and ChatGPT (GPT-4o mini). Across 48 three-turn sessions, artificial intelligence (AI) responses varied by requested communication stance and personal information disclosure. Supportive communication features, stance alignment, personalization consistency, readability (jReadability), and information volume (character count) were coded. Three health professional evaluators rated consultation satisfaction using the Consultation and Relational Empathy (CARE) Measure and rated care-seeking intention using a Readiness Ruler. CARE scores showed moderate inter-rater reliability, whereas intention ratings showed low agreement. Two AI responses contained medical misinformation. In hierarchical regression analyses, longer responses and higher readability were associated with higher satisfaction, and among supportive communication behaviors, praise expressions independently associated with satisfaction. Satisfaction was strongly associated with care-seeking intention (β=0.80, <0.001). In Japanese-language simulated syphilis consultations, information volume, readability, and praise expressions were associated with higher perceived consultation satisfaction, which in turn was associated with greater intention to seek professional care. These findings suggest that conversational AI may serve as a low-threshold, anonymous pre-consultation support tool to encourage timely help-seeking, particularly in rural and remote settings where confidential access to sexual health services is limited. Low inter-rater agreement for intention ratings and the presence of misinformation underscore the need for robust outcome measurement and safety safeguards.
Fuka Nagano, Emi Furukawa, Shinya Ito. Communication features of ChatGPT responses and care-seeking intention for syphilis in Japan: a controlled dialogue experiment.. Journal of rural medicine : JRM. 2026; doi:10.2185/jrm.2025-079.
Fuka Nagano, Emi Furukawa, Shinya Ito (2026). Communication features of ChatGPT responses and care-seeking intention for syphilis in Japan: a controlled dialogue experiment.. Journal of rural medicine : JRM. https://doi.org/10.2185/jrm.2025-079
Fuka Nagano, Emi Furukawa, Shinya Ito. Communication features of ChatGPT responses and care-seeking intention for syphilis in Japan: a controlled dialogue experiment.[J]. Journal of rural medicine : JRM, 2026 doi:10.2185/jrm.2025-079.
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出