Chatbot for Online Support Groups to Treat Tobacco Addiction

Официальное название

Intelligent Chatbot for Online Support Groups to Treat Tobacco Addiction

Обзор

Investigators will conduct a pilot RCT to test the efficacy of an intelligent chatbot to aid small, private, quit-smoking peer support groups. Participants will be randomized to an intervention arm (chatbot-enhanced support group), or a control arm (support group only). In the intervention arm (N=60), each support group will be connected to an intelligent chatbot running on a secure local server as a trained LLM (large language model). The intelligent chatbot will function as an additional member of the GroupMe support group, but a member that only responds if no human does so. In the control arm (N=60), the support groups will be connected to an automated message-posting bot running on a secure local server. This automated message-posting bot will lack the response capabilities of the intelligent chatbot. But both the intelligent chatbot and the automated message-posting bot will post a pre-written daily discussion topic to encourage participants to discuss issues known to facilitate tobacco cessation or group bonding.

Подробное описание

Investigators will conduct a pilot RCT to test the efficacy of an intelligent chatbot to aid small, private, quit-smoking peer support groups. For this pilot RCT, investigators will use a 2-armed parallel group trial design with an active treatment concurrent control. Participants will be randomized to the intervention arm (chatbot-enhanced support group), or the control arm (support group only). All groups will run on GroupMe, a free group chat platform. Investigators will recruit cohorts of 30 smokers, in 4 waves (N=120). After recruitment is complete, a statistician will randomly assign 15 participants to the intervention arm and 15 participants to the control arm. Investigators will place 15 people in each support group arm to ensure a critical mass even with the expected participant attrition. After randomization, each participant will stay in their assigned arm for study duration. Prior to study start, each participant will receive 8 weeks of combination NRT, including nicotine patch and gum or lozenges (their choice), consistent with clinical practice guidelines for tobacco cessation. In the intervention arm (N=60), each support group will be connected to the intelligent chatbot running on a secure local server as a trained LLM (large language model). This chatbot will monitor all posts in the group and seek to comprehend these posts using the training it has been provided. If a group member makes a post and no one responds with about 10 seconds, the chatbot will respond using one of its 25 response libraries created from knowledge bases, which contain over 1k responses in total. In effect, the intelligent chatbot will function as an additional member of the GroupMe support group, but a member that only responds if no human does so. Furthermore, every day at 5 PM Pacific, 8 PM Eastern, the chatbot will post a pre-written daily discussion topic, to encourage participants to discuss issues known to facilitate tobacco cessation or group bonding. In the control arm (N=60), the support groups will be connected to an automated message-posting bot running on a secure local server. This automated message-posting bot will lack the response capabilities of the intelligent chatbot; it will not respond to posts if no human group member does but, instead, remain silent. However, it will post the same daily discussion topic, and at the same time of day, as the intelligent chatbot. Each night, investigators will download each group's past 24-hour posts. These downloads will show each post verbatim along with the datetime stamp and poster username (including posts by the chatbot and automated message-posting bot). Using these downloaded posts, investigators will measure the primary outcome: the total number of posts made by each human participant, excluding the chatbot or bot. In addition, investigators will measure participants' bio-confirmed smoking abstinence and their NRT usage at 1-month and at 3-month intervention end. Trained research staff who are blind to study arm will contact participants via email, text and phone. They will ask participants the following 4 questions: Over the past 7 days, how many cigarettes have they smoked? Over the past 7 days, how many times have they vaped or use e-cigarettes with nicotine? Over the past 7 days, how many times have they used tobacco products other than cigarettes, e.g., cigars, pipe, snuff, chew, snus, or hookah? Over the past 7 days, how many times have they used Nicotine Replacement Therapy or NRT, e.g., patches, gum or lozenges? At 3-month intervention end, investigators will seek to bioconfirm self-reported smoking abstinence. If a participant reports no use of tobacco and no NRT use over the past 7 days, or refuses to answer, investigators will mail out a cotinine saliva test and set up a video (e.g., zoom or FaceTime) appointment at a convenient time for them to take it. Each participant's saliva test will be observed by trained research staff blind to study arm. If a participant recently used NRT, the saliva test will pick up that NRT, and so the test will not be a valid indicator of their smoking status. Therefore, investigators will not give a saliva test current NRT users and instead record them as NRT users. Investigators will incentivize participants to take the saliva test with gift cards.

Вмешательства

• Поведенческое online quit-smoking support group with intelligent chatbot
  In the intervention arm (N=60), each quit-smoking peer support group will be connected to an intelligent chatbot running on a secure local server as a trained LLM (large language model). This chatbot will monitor all posts in the group and seek to comprehend these posts using the training it has been provided. If a group member makes a post and no one responds with about 10 seconds, the chatbot will respond using one of its 25 response libraries created from knowledge bases, which contain over 1
• Поведенческое online quit-smoking support group with unintelligent bot
  In the control arm (N=60), the support groups will be connected to our original automated message-posting bot running on our secure local server. This automated message-posting bot will lack the response capabilities of the intelligent chatbot; it will not respond to posts if no human group member does but, instead, remain silent. However, it will post the same daily discussion topic, and at the same time of day, as the intelligent chatbot.

Первичные конечные точки

• Overall posts per participant [Срок оценки: End of 90-day intervention]

Вторичные конечные точки (3)

• Bio-confirmed smoking abstinence [Срок оценки: End of 90-day intervention]
• NRT use at 1-month [Срок оценки: 30 days after intervention start]
• nrt use at intervention end [Срок оценки: End of 90-day intervention]

Критерии участия

Критерии включения

• Cigarette smokers (can also use e-cigarettes)
• Ages 18-75 years
• English speaking
• Smart phone with unlimited data
• 100 cigarettes lifetime
• Prepared to quit smoking within 10 days of study start
• Active text and email
• Use of social media or group messaging
• Home address provided
• Contact information for a collateral provided
• Setup of a GroupMe account for study

Критерии исключения

• No NRT health contraindications
• 5+ cigarettes per day
• Not an illicit drug user
• Not a daily marijuana/cannabis user

Критерии приведены из реестра в оригинале (на английском). Окончательную оценку соответствия проводит исследовательский центр.

Здоровые добровольцы: Да

Дизайн исследования

Распределение

Рандомизированное

Модель

Параллельные группы

Маскирование

Открытое

Основная цель

Лечение

Центры проведения

Список центров уточняется — проверьте первичный протокол.

Публикации

• Giyahchi T, Singh S, Harris I, Pechmann C. Customized training of pretrained language models to detect post intents in online health support groups. In: Shaban-Nejad A, Michalowski M, Bianco S, eds. Multimodal AI in Healthcare Studies in Computational Intelligence. Springer Nature; 2023:59-76:chap 14.
• Prochaska JJ, Vogel EA, Chieng A, Kendra M, Baiocchi M, Pajarito S, Robinson A. A Therapeutic Relational Agent for Reducing Problematic Substance Use (Woebot): Development and Usability Study. J Med Internet Res. 2021 Mar 23;23(3):e24850. doi: 10.2196/24850. PMID 33755028
• Phillips C, Pechmann C, Calder D, Prochaska JJ. Understanding Hesitation to Use Nicotine Replacement Therapy: A Content Analysis of Posts in Online Tobacco-Cessation Support Groups. Am J Health Promot. 2023 Jan;37(1):30-38. doi: 10.1177/08901171221113835. Epub 2022 Jul 11. PMID 35817548
• Pechmann CC, Yoon KE, Trapido D, Prochaska JJ. Perceived Costs versus Actual Benefits of Demographic Self-Disclosure in Online Support Groups. J Consum Psychol. 2021 Jul;31(3):450-477. doi: 10.1002/jcpy.1200. Epub 2020 Oct 19. PMID 36276230
• Pechmann C, Pan L, Delucchi K, Lakon CM, Prochaska JJ. Development of a Twitter-based intervention for smoking cessation that encourages high-quality social media interactions via automessages. J Med Internet Res. 2015 Feb 23;17(2):e50. doi: 10.2196/jmir.3772. PMID 25707037
• Pechmann C, Delucchi K, Lakon CM, Prochaska JJ. Randomised controlled trial evaluation of Tweet2Quit: a social network quit-smoking intervention. Tob Control. 2017 Mar;26(2):188-194. doi: 10.1136/tobaccocontrol-2015-052768. Epub 2016 Feb 29. PMID 26928205
• Lakon CM, Pechmann C, Wang C, Pan L, Delucchi K, Prochaska JJ. Mapping Engagement in Twitter-Based Support Networks for Adult Smoking Cessation. Am J Public Health. 2016 Aug;106(8):1374-80. doi: 10.2105/AJPH.2016.303256. Epub 2016 Jun 16. PMID 27310342
• Esmaeeli A, Pechmann CC, Prochaska JJ. Buddies as In-Group Influencers in Online Support Groups: A Social Network Analysis of Processes and Outcomes. J Interact Market. 2022 May;57(2):198-211. doi: 10.1177/10949968221076144. Epub 2022 Apr 26. PMID 35656556

Идентификаторы

NCT: NCT06952725 · 919

Первоисточники (государственные реестры)

• ClinicalTrials.gov (NIH, США)

Открыть это исследование на ClinicalTrials.gov ↗