NCT06914492

Real-time Smoking Cessation Instant Messaging Support Using a Large Language Model (LLM)-Based Chatbot Via "Quit to Win" 2025 (QTW2025)

Building Capacity and Promoting Smoking Cessation in the Community Via "Quit to Win" Contest 2025: Real-time Smoking Cessation Instant Messaging Support Using a Large Language Model (LLM)-Based Chatbot

• Status: Active Not Recruiting
• Phase: N/A
• Study type: Interventional
• Enrollment: 1,094 (estimated)
• Sponsor: The University of Hong Kong · Academic / Other
• Sex: All
• Age: 18 Years
• Healthy volunteers: Not accepted

Summary

The goal of this trial is to learn if chatbot-based instant messaging works to help smoking cessation in general adult smokers. It will also learn about the experience, attitude, and perception of using an LLM-based chatbot. The main questions it aims to answer are: 1. Will LLM-based chatbot smoking cessation intervention have a higher validated abstinence rate than the control group? 2. Will LLM-based chatbot smoking cessation intervention have a higher self-reported abstinence rate, smoking reduction rate, and smoking cessation services use rate than the control group? Researchers will compare LLM-based chatbot smoking cessation intervention to a usual care group (brief advice based on AWARD and personalized active referral) to see if chatbot-based instant messaging support works to promote smoking cessation. Participants in the intervention group will receive: 1. AWARD advice 2. Personalized active referral 3. 12 weeks of chatbot-based instant messaging support (via WhatsApp)

Detailed description

Although smoking prevalence is decreasing in Hong Kong (1982: 23.3%; 2023: 9.1%), it accounts for over 7,000 deaths per year and a large amount of medical cost, long-term care and productivity loss of US$ 688 million (0.6% Hong Kong GDP). Quitting is difficult because nicotine is highly addictive. Long-term habitual tobacco smoking could foster a series of physical and psychological dependence on nicotine, and thus induce cravings and nicotine withdrawal symptoms when remaining abstinent. Tradition "one-intervention-for-all" approach cannot work optimally for overall smoking population because of the individual differences in the background characteristic and variations in response to the intervention. Intervention approaches that account for personalization and variation should be explored. Preliminary studies suggest that AI-based chatbots can deliver structured counseling to support tobacco cessation through personalised, empathetic, and authentic conversations, thus enhancing the effectiveness of smoking cessation interventions. When integrated into social media, AI chatbots can provide timely, targeted responses and connect users with a resources on widely used platforms. A 2023 meta-analysis involving 58,796 participants further highlighted the promise of chatbots for tobacco cessation (RR=1.29, 95%CI 1.13-1.46). In late 2022, the release of ChatGPT revolutionized AI and large language models by offering unprecedented reasoning and conversational capabilities, which enables the development of more sophisticated, human-like chatbots. Although ChatGPT (and the GenAI in general) was trained as a general-purpose virtual assistant, its tasks-specific performance can be significantly enhanced through prompt engineering. Leveraging this approach, we developed an LLM-based chatbot to autonomously deliver smoking cessation support via WhatsApp according to established protocols. Our previous rule-based chatbot effectively prevented smoking relapse, and a pilot trial with an LLM-based chatbot for youth smokers (n=154) showed feasibility, achieving an 80.2% retention rate. These findings support the implementation of GenAI chatbots as promising tools for brief smoking cessation interventions in adult smokers. Therefore, our study aims to test the effectiveness of a comprehensive intervention using brief cessation advice, personalized active referral, and chatbot-based instant messaging support compared with the control group on current smokers who join the Quit to Win Contest.

Conditions

• Smoking Cessation

Interventions

Type	Name	Description
BEHAVIORAL	AWARD advice	AWARD advice include Ask about smoking history, Warn about the high risk, Advise to quit, Refer smokers to smoking cessation services (with a referral card), and Do it again.
BEHAVIORAL	Brief leaflet on health warning and smoking cessation	The contents of the leaflet include (1) highlights of the absolute risk of death due to smoking; (2) the whole list of diseases caused by active and second-hand smoking; (3) ten horrible pictorial warnings of health consequences of smoking and second-hand smoking in one page to maximize the impacts; (4) benefits of SC and (5) simple messages to encourage participants to quit smoking.
BEHAVIORAL	Referral card	The contents consist of brief information and a highlight of existing smoking cessation services, contact methods, motivation information and strong supporting messages or slogans.
BEHAVIORAL	Self-help smoking cessation booklet	The contents include information about the benefits of quitting, smoking and diseases, methods to quit, how to handle withdrawal symptoms, declaration of quitting, etc.
BEHAVIORAL	Personalized active referral	Smokers will be introduced to various SC services in Hong Kong (using the referral card) and be motivated to use these services. Well-trained SC ambassadors will assist smoker to choose favourite/most convenient or preferred type of services. Research staff will assist participants in booking or re-booking the SC services at the 1- and 2-month follow-ups (after very brief questionnaire surveys). Participants' contact information will be forwarded to SC services providers within seven days, and providers are expected to contact the participants within 1-2 weeks. Research staff will also monitor SC services use of the participants at each follow-up (1-, 2-, 3- and 6- month) and assist participants to book or re-book the appointments if necessary at 1- and 2- month follow-up. We shall liaise with the existing service providers and seek their assistance in helping our smokers in helping our smokers in a timely manner.
BEHAVIORAL	12 weeks of chatbot-based instant messaging support	Participants in the intervention group will receive 12 weeks of instant messaging support delivered by the LLM-based chatbot accessible via WhatsApp platform. The chatbot, powered by GPT-4o model (or more advanced model available) using prompt-engineering and agent-based techniques, will deliver brief theory-based, structured SC intervention alongside freeform, on-demand support. The structured intervention session deploys the 5As model (Ask, Advise, Assess, Assist, and Arrange follow-up) and 5Rs model (Relevance, Risks, Rewards, Roadblocks, Repetition), as used in our previous telephone-counselling trials and recommended by WHO for brief SC intervention.
BEHAVIORAL	Reminder messages	WhatsApp messages on follow-up survey reminders.

Timeline

• Start date: 2025-06-21
• Primary completion: 2026-06-30
• Completion: 2027-06-30
• First posted: 2025-04-06
• Last updated: 2025-12-01

Locations

1 site across 1 country: Hong Kong