Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Globally 1.1 billion people, 15 years or older are smokers. About 80% of them live in low and middle-income countries. Annually, five million of them die from tobacco use with more than 20% of all deaths of men and 5% of women. This death rate is estimated to increase about 10% by 2020 with more than 70% of it occurring in developing countries. If not controlled, such hasty escalation of smoking will cause annual tobacco-related deaths to increase from seven to eight million by 2030 in developing countries. China has a huge smoking population in the world with 356 million first hand and 740 million second-hand smokers; making 80% of its population affected by smoking, leaving hundreds of thousands of health problems and deaths behind. Continuity in smoking escalation will cause China to face nearly two million tobacco-related deaths by 2020. Only effective and largely applied tobacco control strategies can prevent about 50 million deaths in developing countries like China Objective: Quick response code (QRC) intervention using health belief model (HBM) constructs aims to increase smokers’ knowledge of health beliefs (HBs) regarding cigarette smoking (CS), explains the causal relationship of HBM constructs with smokers’ CS, estimates smokers’ CS based on change in their HBs, and proposes its viability to curb the tobacco epidemic in China. Methods: The data were collected from 492 volunteers using a questionnaire and mobile phone app, and collected data were analyzed using SPSS and AMOS v.23. The Wilcoxon signed rank test was used to measure the difference of pre-and-post intervention in smokers’ HBs and CS. Structural equation modeling (SEM) technique was used to measure the direct, indirect, and mediating effects of research variables. Finally, the probability estimation model was developed using binary logistic regression to predict smokers’ CS based on their HBs. Results: The Wilcoxon signed rank test indicates positive change observed in smokers’ knowledge of PTOS (md=0.84, z -10.903, p<.001), perceived barriers to non-smoking (PBTNS) (-0.68, z -9.491, p<.001), perceived benefits of non-smoking (PBONS) (md=1.22, z -9.807, p<.001), and CS (md=1.665, z -14.439, p<.001). SEM indicates positive mediations of PTOS (β=.212, p<.001), PBTNS (β=.118, p<.001), and PBONS (β=.313, p<.001) between QRC intervention and CS. Probability estimation model predicts PTOS (β=-1.291, Exp(β)=.275, df 1, p<.001), PBTNS (β=1.085, Exp(β)=2.959, df 1, p<.001), and PBONS (β=-1.276, Exp(β)=.279, df 1, p<.001) for CS. Conclusions: This study is viable to observe, amend and predict smokers’ HBs and their CS, and to prevent the tobacco-related deaths in China. Clinical Trial: NA