National Institute for Health Innovation, University of Auckland, Auckland, New Zealand.
Waitemata District Health Board, Auckland, New Zealand.
J Med Internet Res. 2022 Sep 26;24(9):e35556. doi: 10.2196/35556.
Despite significant progress in reducing tobacco use over the past 2 decades, tobacco still kills over 8 million people every year. Digital interventions, such as text messaging, have been found to help people quit smoking. Chatbots, or conversational agents, are new digital tools that mimic instantaneous human conversation and therefore could extend the effectiveness of text messaging.
This scoping review aims to assess the extent of research in the chatbot literature for smoking cessation and provide recommendations for future research in this area.
Relevant studies were identified through searches conducted in Embase, MEDLINE, APA PsycINFO, Google Scholar, and Scopus, as well as additional searches on JMIR, Cochrane Library, Lancet Digital Health, and Digital Medicine. Studies were considered if they were conducted with tobacco smokers, were conducted between 2000 and 2021, were available in English, and included a chatbot intervention.
Of 323 studies identified, 10 studies were included in the review (3 framework articles, 1 study protocol, 2 pilot studies, 2 trials, and 2 randomized controlled trials). Most studies noted some benefits related to smoking cessation and participant engagement; however, outcome measures varied considerably. The quality of the studies overall was low, with methodological issues and low follow-up rates.
More research is needed to make a firm conclusion about the efficacy of chatbots for smoking cessation. Researchers need to provide more in-depth descriptions of chatbot functionality, mode of delivery, and theoretical underpinnings. Consistency in language and terminology would also assist in reviews of what approaches work across the field.
尽管在过去的 20 年中，在减少烟草使用方面取得了重大进展，但烟草每年仍导致超过 800 万人死亡。数字干预措施，如短信，已被发现有助于人们戒烟。聊天机器人或会话代理是新的数字工具，可模拟即时的人类对话，因此可以提高短信的效果。
本范围综述旨在评估聊天机器人文献中关于戒烟的研究程度，并为该领域的未来研究提供建议。
通过在 Embase、MEDLINE、APA PsycINFO、Google Scholar 和 Scopus 中进行搜索，并在 JMIR、Cochrane 图书馆、柳叶刀数字健康和数字医学上进行额外搜索，确定了相关研究。如果研究对象是吸烟者，在 2000 年至 2021 年之间进行，以英文发表，并且包括聊天机器人干预，则认为该研究符合条件。
在 323 项研究中，有 10 项研究被纳入综述（3 篇框架文章、1 项研究方案、2 项试点研究、2 项试验和 2 项随机对照试验）。大多数研究都注意到了与戒烟和参与者参与有关的一些好处；然而，结果测量差异很大。总体而言，研究的质量较低，存在方法学问题和低随访率。
需要更多的研究来确定聊天机器人在戒烟方面的疗效。研究人员需要更详细地描述聊天机器人的功能、传递模式和理论基础。语言和术语的一致性也将有助于审查该领域的有效方法。
