Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: Jan 22, 2026
Date Accepted: Aug 3, 2026

The final, peer-reviewed published version of this preprint can be found here:

Behavior Change Techniques Associated With Abstinence in a Chat-Based Smoking Cessation Intervention: Secondary Analysis of a Randomized Clinical Trial Using Machine Learning

Li Y, Su X, Cheung YTD, Zhao S, Lam TH, Wang MP, Luk TT

Behavior Change Techniques Associated With Abstinence in a Chat-Based Smoking Cessation Intervention: Secondary Analysis of a Randomized Clinical Trial Using Machine Learning

J Med Internet Res 2026;28:e91943

DOI: 10.2196/91943

PMID: 43043646

Behavior change techniques associated with abstinence in a chat-based smoking cessation intervention: secondary analysis of a randomized clinical trial using machine learning

  • Yajie Li; 
  • Xiaoyu Su; 
  • Yee Tak Derek Cheung; 
  • Shengzhi Zhao; 
  • Tai Hing Lam; 
  • Man Ping Wang; 
  • Tzu Tsun Luk

ABSTRACT

Background:

Isolating the “active ingredients” that drive the success of digital behavioral interventions is crucial for understanding the intervention mechanisms and optimizing future interventions.

Objective:

This study aims to identify effective behavior change techniques (BCTs) delivered in a chat-based smoking cessation intervention and determine their independent associations with biochemically validated abstinence.

Methods:

This study is a secondary analysis of a pragmatic, cluster-randomized clinical trial conducted in Hong Kong. From June 18 to September 30, 2017, 624 adult daily smokers were recruited from 34 community sites randomized to the intervention group. Participants received 3 months of personalized, real-time chat-based cessation support delivered by a live counselor via a mobile instant messaging app. Of these, 230 participants (73.9% male, mean age 43.0 years) who engaged with the chat support comprised the analytic sample. All chat dialogues during the real-time support were retrieved and systematically coded using an established BCT taxonomy for smoking cessation (BCTTsm). Four machine learning methods, LASSO regression, XGBoost, Boruta algorithm, and Recursive feature elimination, were employed to identify the BCTs that are the most predictive of biochemically validated tobacco abstinence outcomes at 3 and 6 months.

Results:

Systematic coding identified 35 distinct BCTs from the BCTTsm as having been delivered. Three BCTs were consistently selected by machine learning as the most predictive of both 3- and 6-month abstinence: provide rewards contingent on successfully stopping smoking [BM4], provide information on withdrawal symptoms [RC6], and provide information on consequences of smoking and smoking cessation [BM1]. In multivariable analyses, 6-month abstinence was significantly associated with BM4 (RR=7.9, 95% CI 4.2 to 14.6), RC6 (RR=3.3, 95% CI 1.6 to 6.5), and BM1 (RR=2.7, 95% CI 1.4 to 5.5), with consistent results for 3-month abstinence.

Conclusions:

Three BCTs, contingent rewards [BM4], information on withdrawal symptoms [RC6], and information on consequences [BM1], were identified as key active ingredients associated with success in a chat-based smoking cessation intervention. These findings provide empirical evidence for the mechanisms of effective digital interventions and offer specific, actionable guidance for optimizing their design to maximize impact. Clinical Trial: ClinicalTrials.gov Identifier: NCT03182790


 Citation

Please cite as:

Li Y, Su X, Cheung YTD, Zhao S, Lam TH, Wang MP, Luk TT

Behavior Change Techniques Associated With Abstinence in a Chat-Based Smoking Cessation Intervention: Secondary Analysis of a Randomized Clinical Trial Using Machine Learning

J Med Internet Res 2026;28:e91943

DOI: 10.2196/91943

PMID: 43043646

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.