AI chatbots for health information seeking among Chinese patients with precancerous ENT lesions: a descriptive qualitative study.

OBJECTIVE

To explore how Chinese patients with precancerous ear, nose and throat (ENT) lesions experience using artificial intelligence (AI)-driven chatbots for health-related information seeking, with particular attention to perceived benefits, challenges and influences on information-seeking practices.

DESIGN

Descriptive qualitative study.

SETTING

Department of Otolaryngology, West China Hospital, Sichuan University, China.

PARTICIPANTS

12 adult patients with clinically diagnosed precancerous ENT lesions who had used AI-driven chatbots at least three times in the previous 30 days to seek health-related information about their condition were purposively recruited. Face-to-face, semistructured interviews were conducted between 11 October 2024 and 10 November 2024.

RESULTS

Interviews were analysed using Colaizzi's method. Four themes were identified. First, participants described AI chatbots as an immediate and accessible source of health information, particularly when questions arose outside clinical encounters or during periods of uncertainty. Second, many reported moving away from conventional search engines towards conversational information seeking, valuing direct and synthesised responses over link-based retrieval. Third, participants emphasised that obtaining useful answers depended on learning to ask clear and specific questions, suggesting that effective prompting was an important user skill. Fourth, some participants perceived chatbot interaction as emotionally safer than asking healthcare professionals certain questions, particularly when they felt embarrassed, worried about asking repetitive questions or feared being judged.

CONCLUSIONS

Among this sample of Chinese patients with precancerous ENT lesions, AI-driven chatbots were perceived as a convenient and conversational supplementary source of health information. Participants valued their accessibility and interactional ease, but also indicated that their usefulness depended partly on users' ability to formulate effective prompts. Some participants additionally perceived chatbots as a more comfortable channel for asking sensitive or basic questions. The findings suggest that AI chatbots may have a complementary role in patient information support, but further research is needed to evaluate response accuracy, safety and appropriate integration into clinician-led care.