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

Abstract

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.

Digital Smoking Cessation Intervention for Cancer Survivors: Analysis of Predictors and Moderators of Engagement and Outcome Alongside a Randomized Controlled Trial

“…The analyses on the association between intervention engagement (ie, the number of logins, self-monitoring registrations, and exercises) and the outcome did not yield any significant effects. This study showed the overall prevailing pattern of the majority of participants quitting the use of the intervention in the first few days and a smaller group that uses the intervention for a longer period [ 40 ]. However, other studies on digital SC interventions have shown a dose-response relationship between intervention engagement and outcome [ 9 , 10 , 41 ], with higher engagement predicting greater SC rates, although this is sometimes limited to certain engagement measures [ 34 ] or with low quality of the evidence due to low follow-up rates [ 9 ].…”

Predictors of smoking cessation outcomes identified by machine learning: A systematic review

“…Sadasivam et al, (2016) examined a “hybrid machine learning recommender system that selects and sends motivational messages using algorithms that learn from message ratings”, finding that compared to standard computer-tailored health communication (CTHC), the recommender system outperformed CTHC on measures related to self-perceived influence to quit, yet did not result in improved smoking cessation rates [ 46 ]. Similarly, Chen et al (2021) analyzed smoking cessation using a recommender-based motivational messaging intervention and found high user engagement predicted 6-month smoking cessation [ 47 ]. However, these studies were excluded from the present review for their study design because they did not utilize machine learning to evaluate smoking cessation outcomes, rather the intervention utilized machine learning.…”

Data-Driven Approaches to Smoking Cessation Unraveling Predictors of Quitting through Machine Learning

“…In the cognitive-behavioral model of relapse prevention, for instance, affective states and cognitive processes like self-efficacy and motivation have long been identified as drivers of relapse in substance use disorders [31][32][33][34]. Delay discounting is also strongly associated with smoking outcomes, differentiating smokers from controls [35][36][37][38][39][40], forecasting the intensity of use [36,[41][42][43], and predicting treatment outcomes [44,45]. While several biomarkers for quitting smoking (such as cotinine and carbon monoxide) [22] have been discovered using non-machine learning techniques, machine learning has helped to uncover a brand-new biomarker in fMRI resting-state activity [10].…”