基于聊天机器人的进食障碍预防的有效性：一项随机临床试验。

Effectiveness of a chatbot for eating disorders prevention: A randomized clinical trial.

机构信息

Department of Psychiatry, Washington University School of Medicine, St. Louis, Missouri, USA.

Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, California, USA.

出版信息

Int J Eat Disord. 2022 Mar;55(3):343-353. doi: 10.1002/eat.23662. Epub 2021 Dec 28.

DOI:10.1002/eat.23662

PMID:35274362

Abstract

OBJECTIVE

Prevention of eating disorders (EDs) is of high importance. However, digital programs with human moderation are unlikely to be disseminated widely. The aim of this study was to test whether a chatbot (i.e., computer program simulating human conversation) would significantly reduce ED risk factors (i.e., weight/shape concerns, thin-ideal internalization) in women at high risk for an ED, compared to waitlist control, as well as whether it would significantly reduce overall ED psychopathology, depression, and anxiety and prevent ED onset.

METHOD

Women who screened as high risk for an ED were randomized (N = 700) to (1) chatbot based on the StudentBodies© program; or (2) waitlist control. Participants were followed for 6 months.

RESULTS

For weight/shape concerns, there was a significantly greater reduction in intervention versus control at 3- (d = -0.20; p = .03) and 6-m-follow-up (d = -0.19; p = .04). There were no differences in change in thin-ideal internalization. The intervention was associated with significantly greater reductions than control in overall ED psychopathology at 3- (d = -0.29; p = .003) but not 6-month follow-up. There were no differences in change in depression or anxiety. The odds of remaining nonclinical for EDs were significantly higher in intervention versus control at both 3- (OR = 2.37, 95% CI [1.37, 4.11]) and 6-month follow-ups (OR = 2.13, 95% CI [1.26, 3.59]).

DISCUSSION

Findings provide support for the use of a chatbot-based EDs prevention program in reducing weight/shape concerns through 6-month follow-up, as well as in reducing overall ED psychopathology, at least in the shorter-term. Results also suggest the intervention may reduce ED onset.

PUBLIC SIGNIFICANCE

We found that a chatbot, or a computer program simulating human conversation, based on an established, cognitive-behavioral therapy-based eating disorders prevention program, was successful in reducing women's concerns about weight and shape through 6-month follow-up and that it may actually reduce eating disorder onset. These findings are important because this intervention, which uses a rather simple text-based approach, can easily be disseminated in order to prevent these deadly illnesses.

TRIAL REGISTRATION

OSF Registries; https://osf.io/7zmbv.

摘要

目的

饮食失调（ED）的预防非常重要。然而，带有人工 moderation 的数字程序不太可能被广泛传播。本研究的目的是测试与候补名单对照组相比，一种聊天机器人（即模拟人类对话的计算机程序）是否会显著降低 ED 高危女性的 ED 风险因素（即体重/体型担忧、瘦理想内化），以及是否会显著降低整体 ED 精神病理学、抑郁和焦虑，并预防 ED 发作。

方法

筛选出 ED 高危的女性被随机分配（N=700）至（1）基于 StudentBodies© 计划的聊天机器人；或（2）候补名单对照组。参与者随访 6 个月。

结果

在 3-（d=-0.20；p=0.03）和 6-个月随访时（d=-0.19；p=0.04），干预组的体重/体型担忧较对照组有显著减少。在瘦理想内化方面，干预组与对照组之间没有差异。与对照组相比，干预组在 3-（d=-0.29；p=0.003）但不是 6 个月随访时的整体 ED 精神病理学有显著更大的降低。在抑郁或焦虑方面没有差异。在 3-（OR=2.37，95%CI[1.37，4.11]）和 6-个月随访时（OR=2.13，95%CI[1.26，3.59]），干预组的 ED 非临床发生率明显高于对照组。

讨论

研究结果为使用基于聊天机器人的 ED 预防计划提供了支持，该计划通过 6 个月的随访减少了体重/体型的担忧，并且至少在短期内减少了整体 ED 精神病理学。结果还表明，该干预措施可能会降低 ED 发病风险。

公众意义

我们发现，一种基于既定的认知行为治疗为基础的饮食失调预防计划的聊天机器人，或者模拟人类对话的计算机程序，在 6 个月的随访中成功地减少了女性对体重和体型的担忧，并且实际上可能降低了饮食失调的发作。这些发现很重要，因为这种干预措施，使用了一种相当简单的基于文本的方法，可以很容易地传播，以预防这些致命的疾病。