Effect of a Machine Learning Recommender System and Viral Peer Marketing Intervention on Smoking Cessation: A Randomized Clinical Trial.

Importance: Novel data science and marketing methods of smoking-cessation intervention have not been adequately evaluated. Objective: To compare machine learning recommender (ML recommender) computer tailoring of motivational text messages vs a standard motivational text-based intervention (standard messaging) and a viral peer-recruitment tool kit (viral tool kit) for recruiting friends and family vs no tool kit in a smoking-cessation intervention. Design, Setting, and Participants: This 2 ×2 factorial randomized clinical trial with partial allocation, conducted between July 2017 and September 2019 within an online tobacco intervention, recruited current smokers aged 18 years and older who spoke English from the US via the internet and peer referral. Data were analyzed from March through May 2022. Interventions: Participants registering for the online intervention were randomly assigned to the ML recommender or standard messaging groups followed by partially random allocation to access to viral tool kit or no viral tool kit groups. The ML recommender provided ongoing refinement of message selection based on user feedback and comparison with a growing database of other users, while the standard system selected messages based on participant baseline readiness to quit. Main Outcomes and Measures: Our primary outcome was self-reported 7-day point prevalence smoking cessation at 6 months. Results: Of 1487 participants who smoked (444 aged 19-34 years [29.9%], 508 aged 35-54 years [34.1%], 535 aged ≥55 years [36.0%]; 1101 [74.0%] females; 189 Black [12.7%] and 1101 White [78.5%]; 106 Hispanic [7.1%]), 741 individuals were randomly assigned to the ML recommender group and 746 individuals to the standard messaging group; viral tool kit access was provided to 745 participants, and 742 participants received no such access. There was no significant difference in 6-month smoking cessation between ML recommender (146 of 412 participants [35.4%] with outcome data) and standard messaging (156 of 389 participants [40.1%] with outcome data) groups (adjusted odds ratio, 0.81; 95% CI, 0.61-1.08). Smoking cessation was significantly higher in viral tool kit (177 of 395 participants [44.8%] with outcome data) vs no viral tool kit (125 of 406 participants [30.8%] with outcome data) groups (adjusted odds ratio, 1.48; 95% CI, 1.11-1.98). Conclusions and Relevance: In this study, machine learning-based selection did not improve performance compared with standard message selection, while viral marketing did improve cessation outcomes. These results suggest that in addition to increasing dissemination, viral recruitment may have important implications for improving effectiveness of smoking-cessation interventions. Trial Registration: ClinicalTrials.gov Identifier: NCT03224520.

Characterizing Pandemic-Related Changes in Smoking Over Time in a Cohort of Current and Former Smokers.

INTRODUCTION: We used a longitudinal cohort of US adults who were current or former smokers to explore how three participant-reported factors-general stress, coronavirus disease of 2019 (COVID-19) distress, and perceived risk of complications from COVID-19 related to smoking-were associated with changes in smoking status. METHODS: Smoking status was assessed at three time points. Timepoint 1 status was assessed at a prior study completion (2018-2020). Timepoint 2 (start of the pandemic), and Timepoint 3 (early phase of the pandemic) statuses were assessed using an additional survey in 2020. After classifying participants into eight groups per these time points, we compared the means of participant-reported factors and used a linear regression model to adjust for covariates. RESULTS: Participants (n = 392) were mostly female (73.9%) and non-Hispanic White (70.1%). Between Timepoints 2 and 3, abstinence rates decreased by 11%, and 40% of participants reported a smoking status change. Among those reporting a change and the highest general stress levels, newly abstinent participants had higher perceived risk of complications from COVID-19 related to smoking than those who relapsed during pandemic (mean (SD): 14.2 (3.3) vs. 12.6 (3.8)). Compared to participants who sustained smoking, those who sustained abstinence, on average, scored 1.94 less on the general stress scale (ßeta Coefficient (ß): -1.94, p-value < .01) and 1.37 more on the perceived risk of complications from COVID-19 related to smoking scale (ß: 1.37, p-value .02). CONCLUSIONS: Decreased abstinence rates are concerning. Patterns of reported factors were as expected for individuals who sustained their smoking behavior but not for those who changed. IMPLICATIONS: We observed an increase in smoking rates during the COVID-19 pandemic. In exploring how combinations of general stress levels, COVID-19 distress levels, and perceived risk of complications from COVID-19 related to smoking were associated with changes in smoking, we observed expected patterns of these factors among individuals who sustained abstinence or smoking. Among individuals who changed smoking status and reported high stress levels, those who reported a higher perceived risk of complications from COVID-19 related to smoking abstained from smoking. In contrast, those who reported a lower perceived risk of complications from COVID-19 related to smoking, started smoking. An intersectional perspective may be needed to understand smokers' pandemic-related behavior changes.

Evaluating the use of a recommender system for selecting optimal messages for smoking cessation: patterns and effects of user-system engagement.

BACKGROUND: Motivational messaging is a frequently used digital intervention to promote positive health behavior changes, including smoking cessation. Typically, motivational messaging systems have not actively sought feedback on each message, preventing a closer examination of the user-system engagement. This study assessed the granular user-system engagement around a recommender system (a new system that actively sought user feedback on each message to improve message selection) for promoting smoking cessation and the impact of engagement on cessation outcome. METHODS: We prospectively followed a cohort of current smokers enrolled to use the recommender system for 6 months. The system sent participants motivational messages to support smoking cessation every 3 days and used machine learning to incorporate user feedback (i.e., user's rating on the perceived influence of each message, collected on a 5-point Likert scale with 1 indicating strong disagreement and 5 indicating strong agreement on perceiving the influence on quitting smoking) to improve the selection of the following message. We assessed user-system engagement by various metrics, including user response rate (i.e., the percent of times a user rated the messages) and the perceived influence of messages. We compared retention rates across different levels of user-system engagement and assessed the association between engagement and the 7-day point prevalence abstinence (missing outcome = smoking) by using multiple logistic regression. RESULTS: We analyzed data from 731 participants (13% Black; 73% women). The user response rate was 0.24 (SD = 0.34) and user-perceived influence was 3.76 (SD = 0.84). The retention rate positively increased with the user response rate (trend test P < 0.001). Compared with non-response, six-month cessation increased with the levels of response rates: low response rate (odds ratio [OR] = 1.86, 95% confidence interval [CI]: 1.07-3.23), moderate response rate (OR = 2.30, 95% CI: 1.36-3.88), high response rate (OR = 2.69, 95% CI: 1.58-4.58). The association between perceived message influence and the outcome showed a similar pattern. CONCLUSIONS: High user-system engagement was positively associated with both high retention rate and smoking cessation, suggesting that investigation of methods to increase engagement may be crucial to increase the impact of the recommender system for smoking cessation. TRIAL REGISTRATION: Registration Identifier: NCT03224520 . Registration date: July 21, 2017.

Comparing recruitment strategies for a digital smoking cessation intervention: Technology-assisted peer recruitment, social media, ResearchMatch, and smokefree.gov.

BACKGROUND: Choosing the right recruitment strategy has implications for the successful conduct of a trial. Our objective was to compare a novel peer recruitment strategy to four other recruitment strategies for a large randomized trial testing a digital tobacco intervention. METHODS: We compared enrollment rates, demographic and baseline smoking characteristics, and odds of completing the 6-month study by recruitment strategy. Cost of recruitment strategies per retained participant was calculated using staff personnel time and advertisement costs. FINDINGS: We enrolled 1487 participants between August 2017 and March 2019 from: Peer recruitment n = 273 (18.4%), Facebook Ads n = 505 (34%), Google Ads = 200 (13.4%), ResearchMatch n = 356 (23.9%) and Smokefree.govn = 153 (10.3%). Mean enrollment rate per active recruitment month: 1) Peer recruitment, n = 13.9, 2) Facebook ads, n = 25.3, 3) Google ads, n = 10.51, 4) Research Match, n = 59.3, and 5) Smokefree.gov, n = 13.9. Peer recruitment recruited the greatest number of males (n = 110, 40.3%), young adults (n = 41, 14.7%), participants with a high school degree or less (n = 24, 12.5%) and smokers within one's social network. Compared to peer recruitment (retention rate = 57%), participants from Facebook were less likely (OR 0.46, p < 0.01, retention rate = 40%), and those from ResearchMatch were more likely to complete the study (OR 1.90, p < 0.01, retention rate = 70%). Peer recruitment was moderate in cost per retained participant ($47.18) and substantially less costly than Facebook ($173.60). CONCLUSIONS: Though peer recruitment had lower enrollment than other strategies, it may provide greater access to harder to reach populations and possibly others who smoke within one's social network while being moderately cost-effective. ClinicalTrials.gov: NCT03224520.

Teamwork for smoking cessation: which smoker was willing to engage their partner? Results from a cross-sectional study.

OBJECTIVE: Smokers are greatly influenced by those living with them, but strategies that increase partner support for smoking cessation are lacking. Using a cross-sectional study design, we explored factors associated with willingness to engage a partner in smoking cessation in smokers registered on a web-assisted tobacco intervention trial. RESULTS: Study participants (n = 983) were recruited between July 2018 and March 2019. About 28% of smokers were willing to engage their partner in cessation efforts. The odds of willingness to engage a partner were more than two-fold for smokers reporting presence of other smokers in the immediate family (adjusted odds ratio (aOR): 2.18; 95% confidence interval (CI) 1.51-3.15 for 1-3 smokers; aOR, 3.12; 95% CI 1.95-4.98 for ≥ 4 smokers) compared to those with no smokers in the immediate family. Women had lower odds of willingness to engage (aOR; 0.82; 95% CI 0.58-1.16) than men, but this was not statistically significant. Use of e-cigarettes and visitation to a smoking cessation website prior to the intervention were both positively associated with willingness to engage partners in cessation. Future research should assess whether interventions tailored to smokers willing to engage partners or spouses could increase effectiveness of partner support during cessation.

Dissemination and Effectiveness of the Peer Marketing and Messaging of a Web-Assisted Tobacco Intervention: Protocol for a Hybrid Effectiveness Trial.

BACKGROUND: Smoking continues to be the leading preventable cause of death. Digital Interventions for Smoking Cessation (DISCs) are health communication programs accessible via the internet and smartphones and allow for greater reach and effectiveness of tobacco cessation programs. DISCs have led to increased 6-month cessation rates while also reaching vulnerable populations. Despite this, the impact of DISCs has been limited and new ways to increase access and effectiveness are needed. OBJECTIVE: We are conducting a hybrid effectiveness-dissemination study. We aim to evaluate the effectiveness of a machine learning-based approach (recommender system) for computer-tailored health communication (CTHC) over a standard CTHC system based on quit rates and risk reduction. In addition, this study will assess the dissemination of providing access to a peer recruitment toolset on recruitment rate and variability of the sample. METHODS: The Smoker-to-Smoker (S2S) study is a 6-month hybrid effectiveness dissemination trial conducted nationally among English-speaking, current smokers aged ≥18 years. All eligible participants will register for the DISC (Decide2quit) and be randomized to the recommender system CTHC or the standard CTHC, followed by allocation to a peer recruitment toolset group or control group. Primary outcomes will be 7-day point prevalence and risk reduction at the 6-month follow-up. Secondary outcomes include recruitment rate, website engagement, and patient-reported outcomes collected via the 6-month follow-up questionnaire. All primary analyses will be conducted on an intent-to-treat basis. RESULTS: The project is funded from 2017 to 2020 by the Patient Centered Outcomes Research Institute. Enrollment was completed in early 2019, and 6-month follow-ups will be completed by late 2019. Preliminary data analysis is currently underway. CONCLUSIONS: Conducting a hybrid study with both effectiveness and dissemination hypotheses raises some unique challenges in the study design and analysis. Our study addresses these challenges to test new innovations and increase the effectiveness and reach of DISCs. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/14814.