Effectiveness of Computer-Tailored Health Communication in Increasing Physical Activity in People With or at Risk of Long-Term Conditions: Systematic Review and Meta-Analysis.

BACKGROUND: Regular physical activity (PA) is beneficial for enhancing and sustaining both physical and mental well-being as well as for the management of preexisting conditions. Computer-tailored health communication (CTHC) has been shown to be effective in increasing PA and many other health behavior changes in the general population. However, individuals with or at risk of long-term conditions face unique barriers that may limit the applicability of CTHC interventions to this population. Few studies have focused on this cohort, providing limited evidence for the effectiveness of CTHC in promoting PA. OBJECTIVE: This systematic review and meta-analysis aims to assess the effectiveness of CTHC in increasing PA in individuals with or at risk of long-term conditions. METHODS: A systematic review and meta-analysis were conducted to evaluate the effect of CTHC in increasing PA in people with or at risk of long-term conditions. Hedges g was used to calculate the mean effect size. The total effect size was pooled and weighted using inverse variance. When possible, potential moderator variables were synthesized, and their effectiveness was evaluated by subgroups analysis with Q test for between-group heterogeneity Qb. Potential moderator variables included behavior change theories and models providing the fundamental logic for CTHC design, behavior change techniques and tailoring strategies to compose messages, and computer algorithms to achieve tailoring. Several methods were used to examine potential publication bias in the results, including the funnel plot, Egger test, Begg test, fail-safe N test, and trim-and-fill method. RESULTS: In total, 24 studies were included in the systematic review for qualitative analysis and 18 studies were included in the meta-analysis. Significant small to medium effect size values were found when comparing CTHC to general health information (Hedges g=0.16; P<.001) and to no information sent to participants (Hedges g=0.29; P<.001). Half of the included studies had a low to moderate risk of bias, and the remaining studies had a moderate to high risk of bias. Although the results of the meta-analysis indicated no evidence of publication bias, caution is required when drawing definitive conclusions due to the limited number of studies in each subgroup (N≤10). Message-tailoring strategies, implementation strategies, behavior change theories and models, and behavior change techniques were synthesized from the 24 studies. No strong evidence was found from subgroup analyses on the effectiveness of using particular behavior change theories and models or from using particular message-tailoring and implementation strategies. CONCLUSIONS: This study demonstrates that CTHC is effective in increasing PA for people with or at risk of long-term conditions, with significant small to medium effects compared with general health information or no information. Further studies are needed to guide design decisions for maximizing the effectiveness of CTHC.

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.

Collective-Intelligence Recommender Systems: Advancing Computer Tailoring for Health Behavior Change Into the 21st Century.

BACKGROUND: What is the next frontier for computer-tailored health communication (CTHC) research? In current CTHC systems, study designers who have expertise in behavioral theory and mapping theory into CTHC systems select the variables and develop the rules that specify how the content should be tailored, based on their knowledge of the targeted population, the literature, and health behavior theories. In collective-intelligence recommender systems (hereafter recommender systems) used by Web 2.0 companies (eg, Netflix and Amazon), machine learning algorithms combine user profiles and continuous feedback ratings of content (from themselves and other users) to empirically tailor content. Augmenting current theory-based CTHC with empirical recommender systems could be evaluated as the next frontier for CTHC. OBJECTIVE: The objective of our study was to uncover barriers and challenges to using recommender systems in health promotion. METHODS: We conducted a focused literature review, interviewed subject experts (n=8), and synthesized the results. RESULTS: We describe (1) limitations of current CTHC systems, (2) advantages of incorporating recommender systems to move CTHC forward, and (3) challenges to incorporating recommender systems into CTHC. Based on the evidence presented, we propose a future research agenda for CTHC systems. CONCLUSIONS: We promote discussion of ways to move CTHC into the 21st century by incorporation of recommender systems.

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.

Comparison of a Collective Intelligence Tailored Messaging System on Smoking Cessation Between African American and White People Who Smoke: Quasi-Experimental Design.

BACKGROUND: The Patient Experience Recommender System for Persuasive Communication Tailoring (PERSPeCT) is a machine learning recommender system with a database of messages to motivate smoking cessation. PERSPeCT uses the collective intelligence of users (ie, preferences and feedback) and demographic and smoking profiles to select motivating messages. PERSPeCT may be more beneficial for tailoring content to minority groups influenced by complex, personally relevant factors. OBJECTIVE: The objective of this study was to describe and evaluate the use of PERSPeCT in African American people who smoke compared with white people who smoke. METHODS: Using a quasi-experimental design, we compared African American people who smoke with a historical cohort of white people who smoke, who both received up to 30 emailed tailored messages over 65 days. People who smoke rated the daily message in terms of perceived influence on quitting smoking for 30 days. Our primary analysis compared daily message ratings between the two groups using a t test. We used a logistic model to compare 30-day cessation between the two groups and adjusted for covariates. RESULTS: The study included 119 people who smoke (African Americans, 55/119; whites, 64/119). At baseline, African American people who smoke were significantly more likely to report allowing smoking in the home (P=.002); all other characteristics were not significantly different between groups. Daily mean ratings were higher for African American than white people who smoke on 26 of the 30 days (P<.001). Odds of quitting as measured by 30-day cessation were significantly higher for African Americans (odds ratio 2.3, 95% CI 1.04-5.53; P=.03) and did not change after adjusting for allowing smoking at home. CONCLUSIONS: Our study highlighted the potential of using a recommender system to personalize for African American people who smoke. TRIAL REGISTRATION: ClinicalTrials.gov NCT02200432; https://clinicaltrials.gov/ct2/show/NCT02200432. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/jmir.6465.