Scholarlink

Purpose <p>Large language models (LLMs) offer promising applications in healthcare communication, including the provision of medical information and simulation of empathetic responses. However, the extent to which patients perceive such interactions as empathetic remains unclear. This study explores urological patients’ perceptions of empathy and compassion in interactions with an LLM-powered chatbot, as well as their willingness to disclose personal information.</p> Methods <p>A total of 292 patients scheduled for urological counselling interacted with a GPT-4-powered chatbot to ask questions related to their medical condition. Participants subsequently completed a survey evaluating human-likeness, perceived empathy and compassion. Comparisons were drawn between chatbot and physician interactions regarding empathy, perceived prejudice and willingness to disclose sensitive information.</p> Results <p>Of 292 patients 63% (184/292) reported enjoying the chatbot interaction, with 77% (225/292) expressing satisfaction with the conversational flow, and 67% (196/292) describing its responses as human-like. Despite these positive impressions, 56% (164/292) disagreed that the chatbot made them feel cared for and 40% (117/292) found it lacked empathy. Additionally, 61% (178/292) disagreed that the chatbot was as empathetic as human physicians. Regarding self-disclosure, 77% (225/292) expressed a preference for sharing sensitive information with a human physician. Regression analysis revealed that patients with higher educational levels were more sceptical of the suitability of the chatbot for self-disclosure and empathy.</p> Conclusions <p>While urological patients valued the accessibility and conversational flow of the LLM-powered chatbot, they overwhelmingly preferred urologists for empathetic communication and personal disclosures. These findings suggest that AI systems must either be refined for empathetic interactions or be used only in settings where empathy is less essential.</p> Trial registration number <p>DRKS-ID:00034906, registered on 16th of August 2024.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Patient insights into empathy, compassion and self-disclosure in medical large language models: results from the IPALLM III study

  • 期刊论文

  • 发表日期：

    2025年8月14日

查看全文
  • Nicolas Carl,
  • Sarah Haggenmüller,
  • Jana Theres Winterstein,
  • Lisa Nguyen,
  • Christoph Wies,
  • Martin Joachim Hetz,
  • Maurin Helen Mangold,
  • Britta Grüne,
  • Maurice Stephan Michel,
  • Titus Josef Brinker,
  • Frederik Wessels

摘要

Purpose

Large language models (LLMs) offer promising applications in healthcare communication, including the provision of medical information and simulation of empathetic responses. However, the extent to which patients perceive such interactions as empathetic remains unclear. This study explores urological patients’ perceptions of empathy and compassion in interactions with an LLM-powered chatbot, as well as their willingness to disclose personal information.

Methods

A total of 292 patients scheduled for urological counselling interacted with a GPT-4-powered chatbot to ask questions related to their medical condition. Participants subsequently completed a survey evaluating human-likeness, perceived empathy and compassion. Comparisons were drawn between chatbot and physician interactions regarding empathy, perceived prejudice and willingness to disclose sensitive information.

Results

Of 292 patients 63% (184/292) reported enjoying the chatbot interaction, with 77% (225/292) expressing satisfaction with the conversational flow, and 67% (196/292) describing its responses as human-like. Despite these positive impressions, 56% (164/292) disagreed that the chatbot made them feel cared for and 40% (117/292) found it lacked empathy. Additionally, 61% (178/292) disagreed that the chatbot was as empathetic as human physicians. Regarding self-disclosure, 77% (225/292) expressed a preference for sharing sensitive information with a human physician. Regression analysis revealed that patients with higher educational levels were more sceptical of the suitability of the chatbot for self-disclosure and empathy.

Conclusions

While urological patients valued the accessibility and conversational flow of the LLM-powered chatbot, they overwhelmingly preferred urologists for empathetic communication and personal disclosures. These findings suggest that AI systems must either be refined for empathetic interactions or be used only in settings where empathy is less essential.

Trial registration number

DRKS-ID:00034906, registered on 16th of August 2024.