Hasei Joe, Hanzawa Mana, Nagano Akihito, Maeda Naoko, Yoshida Shinichirou, Endo Makoto, Yokoyama Nobuhiko, Ochi Motoharu, Ishida Hisashi, Katayama Hideki, Fujiwara Tomohiro, Nakata Eiji, Nakahara Ryuichi, Kunisada Toshiyuki, Tsukahara Hirokazu, Ozaki Toshifumi
Department of Medical Information and Assistive Technology Development, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan.
Department of Pediatrics, Okayama University Hospital, Okayama, Japan.
Front Digit Health. 2025 Feb 25;7:1543543. doi: 10.3389/fdgth.2025.1543543. eCollection 2025.
Pediatric and adolescent/young adult (AYA) cancer patients face profound psychological challenges, exacerbated by limited access to continuous mental health support. While conventional therapeutic interventions often follow structured protocols, the potential of generative artificial intelligence (AI) chatbots to provide continuous conversational support remains unexplored. This study evaluates the feasibility and impact of AI chatbots in alleviating psychological distress and enhancing treatment engagement in this vulnerable population.
Two age-appropriate AI chatbots, leveraging GPT-4, were developed to provide natural, empathetic conversations without structured therapeutic protocols. Five pediatric and AYA cancer patients participated in a two-week intervention, engaging with the chatbots via a messaging platform. Pre- and post-intervention anxiety and stress levels were self-reported, and usage patterns were analyzed to assess the chatbots' effectiveness.
Four out of five participants reported significant reductions in anxiety and stress levels post-intervention. Participants engaged with the chatbot every 2-3 days, with sessions lasting approximately 10 min. All participants noted improved treatment motivation, with 80% disclosing personal concerns to the chatbot they had not shared with healthcare providers. The 24/7 availability particularly benefited patients experiencing nighttime anxiety.
This pilot study demonstrates the potential of generative AI chatbots to complement traditional mental health services by addressing unmet psychological needs in pediatric and AYA cancer patients. The findings suggest these tools can serve as accessible, continuous support systems. Further large-scale studies are warranted to validate these promising results.
儿童及青少年/青年癌症患者面临着巨大的心理挑战,而持续获得心理健康支持的机会有限,这使情况更加恶化。虽然传统治疗干预通常遵循结构化方案,但生成式人工智能(AI)聊天机器人提供持续对话支持的潜力仍未得到探索。本研究评估了AI聊天机器人在减轻这一弱势群体的心理困扰和提高治疗参与度方面的可行性和影响。
开发了两个适合不同年龄段的AI聊天机器人,利用GPT-4提供自然、有同理心的对话,无需结构化治疗方案。五名儿童及青少年/青年癌症患者参与了为期两周的干预,通过消息平台与聊天机器人互动。干预前后的焦虑和压力水平由患者自我报告,并分析使用模式以评估聊天机器人的有效性。
五名参与者中有四名报告干预后焦虑和压力水平显著降低。参与者每2-3天与聊天机器人互动一次,每次会话持续约10分钟。所有参与者都指出治疗动机有所改善,80%的参与者向聊天机器人透露了他们未曾与医疗服务提供者分享的个人担忧。全天候可用对夜间焦虑的患者尤其有益。
这项初步研究表明,生成式AI聊天机器人有潜力通过满足儿童及青少年/青年癌症患者未得到满足的心理需求来补充传统心理健康服务。研究结果表明,这些工具可以作为易于获得的持续支持系统。有必要进行进一步的大规模研究来验证这些有前景的结果。