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

Health recommender systems to facilitate collaborative decision-making in chronic disease management: A scoping review

Objective

Health recommender systems (HRSs) are increasingly used to complement existing clinical decision-making processes, but their use for chronic diseases remains underexplored. Recognizing the importance of collaborative decision making (CDM) and patient engagement in chronic disease treatment, this review explored how HRSs support patients in managing their illness.

Methods

A scoping review was conducted using the framework proposed by Arksey and O'Malley, advanced by Levac et al., in line with the PRISMA-ScR checklist. Quantitative (descriptive numerical summary) and qualitative (inductive content analysis) methods wered used to synthesize the data.

Results

Forty-five articles were included in the final review, most commonly covering diabetes (9/45, 20%), mental health (9/45, 20.0%), and tobacco dependence (7/45, 15.6%). Behavior change theories (10/45, 22.2%) and authoritative sources (10/45, 22.2%) were the most commonly referenced sources for design and development work. From the thematic analysis, we conclude: (a) the main goal of HRSs is to induce behavior change, but limited research investigates their effectiveness in achieving this aim; (b) studies acknowledge that theories, models, frameworks, and/or guidelines help design HRSs to elicit specific behavior change, but they do not implement them; (c) connections between CDM and HRS purpose should be more explicit; and (d) HRSs can often offer other self-management services, such as progress tracking and chatbots.

Conclusions

We recommend a greater emphasis on evaluation outcomes beyond algorithmic performance to determine HRS effectiveness and the creation of an evidence-driven, methodological approach to creating HRSs to optimize their use in enhancing patient care.

Lay summary

Our work aims to provide a summary of the current landscape of health recommender system (HRS) use for chronic disease management. HRSs are digital tools designed to help people manage their health by providing personalized recommendations based on their health history, behaviors, and preferences, enabling them to make more informed health decisions. Given the increased use of these tools for personalized care, and especially with advancements in generative artificial intelligence, understanding the current methods and evaluation processes used is integral to optimizing their effectiveness. Our findings show that HRSs are most used for diabetes, mental health, and tobacco dependence, but only a small percentage of publications directly reference and/or use relevant frameworks to help guide their design and evaluation processes. Furthermore, the goal for most of these HRSs is to induce behavior change, but there is limited research investigating how effective they are in accomplishing this. Given these findings, we recommend that evaluations shift their focus from algorithms to more holistic approaches and to be more intentional about the processes used when designing the tool to support an evidence-driven approach and ultimately create more effective and useful HRSs for chronic disease management.

Stopping use of E-cigarettes and smoking combustible cigarettes: findings from a large longitudinal digital smoking cessation intervention study in the United States

OBJECTIVE

Digital interventions have been widely implemented to promote tobacco cessation. However, implementations of these interventions have not yet considered how participants' e-cigarette use may influence their quitting outcomes. We explored the association of e-cigarette use and quitting smoking within the context of a study testing a digital tobacco cessation intervention among individuals in the United States who were 18 years and older, smoked combustible cigarettes, and enrolled in the intervention between August 2017 and March 2019.

RESULTS

We identified four e-cigarette user groups (n = 990) based on the participants' baseline and six-month e-cigarette use (non-users, n = 621; recently started users, n = 60; sustained users, n = 187; recently stopped users, n = 122). A multiple logistic regression was used to estimate the adjusted odds ratios (AOR) of six-month quit outcome and the e-cigarette user groups. Compared to e-cigarette non-users, the odds of quitting smoking were significantly higher among recently stopped users (AOR = 1.68, 95% CI [1.06, 2.67], p = 0.03). Participants who were most successful at quitting combustible cigarettes also stopped using e-cigarettes at follow-up, although many sustained using both products. Findings suggest that digital tobacco cessation interventions may carefully consider how to promote e-cigarette use cessation among participants who successfully quit smoking.

TRIAL REGISTRATION

ClinicalTrials.gov identifier NCT03224520 (July 21, 2017).

A systematic review on eHealth technology personalization approaches

Despite the widespread use of personalization of eHealth technologies, there is a lack of comprehensive understanding regarding its application. This systematic review aims to bridge this gap by identifying and clustering different personalization approaches based on the type of variables used for user segmentation and the adaptations to the eHealth technology and examining the role of computational methods in the literature. From the 412 included reports, we identified 13 clusters of personalization approaches, such as behavior + channeling and environment + recommendations. Within these clusters, 10 computational methods were utilized to match segments with technology adaptations, such as classification-based methods and reinforcement learning. Several gaps were identified in the literature, such as the limited exploration of technology-related variables, the limited focus on user interaction reminders, and a frequent reliance on a single type of variable for personalization. Future research should explore leveraging technology-specific features to attain individualistic segmentation approaches.

Developing Mood-Based Computer-Tailored Health Communication for Smoking Cessation: Feasibility Randomized Controlled Trial

BACKGROUND

Computer-tailored health communication (CTHC), a widely used strategy to increase the effectiveness of smoking cessation interventions, is focused on selecting the best messages for an individual. More recently, CTHC interventions have been tested using contextual information such as participants' current stress or location to adapt message selection. However, mood has not yet been used in CTCH interventions and may increase their effectiveness.

OBJECTIVE

This study aims to examine the association of mood and smoking cessation message effectiveness among adults who currently smoke cigarettes.

METHODS

In January 2022, we recruited a web-based convenience sample of adults who smoke cigarettes (N=615; mean age 41.13 y). Participants were randomized to 1 of 3 mood conditions (positive, negative, or neutral) and viewed pictures selected from the International Affective Picture System to induce an emotional state within the assigned condition. Participants then viewed smoking cessation messages with topics covering five themes: (1) financial costs or rewards, (2) health, (3) quality of life, (4) challenges of quitting, and (5) motivation or reasons to quit. Following each message, participants completed questions on 3 constructs: message receptivity, perceived relevance, and their motivation to quit. The process was repeated 30 times. We used 1-way ANOVA to estimate the association of the mood condition on these constructs, controlling for demographics, cigarettes per day, and motivation to quit measured during the pretest. We also estimated the association between mood and outcomes for each of the 5 smoking message theme categories.

RESULTS

There was an overall statistically significant effect of the mood condition on the motivation to quit outcome (P=.02) but not on the message receptivity (P=.16) and perceived relevance (P=.86) outcomes. Participants in the positive mood condition reported significantly greater motivation to quit compared with those in the negative mood condition (P=.005). Participants in the positive mood condition reported higher motivation to quit after viewing smoking cessation messages in the financial (P=.03), health (P=.01), quality of life (P=.04), and challenges of quitting (P=.03) theme categories. We also compared each mood condition and found that participants in the positive mood condition reported significantly greater motivation to quit after seeing messages in the financial (P=.01), health (P=.003), quality of life (P=.01), and challenges of quitting (P=.01) theme categories than those in the negative mood condition.

CONCLUSIONS

Our findings suggest that considering mood may be important for future CTHC interventions. Because those in the positive mood state at the time of message exposure were more likely to have greater quitting motivations, smoking cessation CTHC interventions may consider strategies to help improve participants' mood when delivering these messages. For those in neutral and negative mood states, focusing on certain message themes (health and motivation to quit) may be more effective than other message themes.