Dataset Information

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

ABSTRACT: 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.

SUBMITTER: Faro JM

PROVIDER: S-EPMC7215495 | biostudies-literature | 2020 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Faro Jamie M JM Nagawa Catherine S CS Allison Jeroan A JA Lemon Stephenie C SC Mazor Kathleen M KM Houston Thomas K TK Sadasivam Rajani S RS

JMIR mHealth and uHealth 20200427 4

<h4>Background</h4>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.<h4>Objective</ ...[more]

PMID: 32338619

Similar Datasets

Project description:BackgroundOutside health care, content tailoring is driven algorithmically using machine learning compared to the rule-based approach used in current implementations of computer-tailored health communication (CTHC) systems. A special class of machine learning systems ("recommender systems") are used to select messages by combining the collective intelligence of their users (ie, the observed and inferred preferences of users as they interact with the system) and their user profiles. However, this approach has not been adequately tested for CTHC.ObjectiveOur aim was to compare, in a randomized experiment, a standard, evidence-based, rule-based CTHC (standard CTHC) to a novel machine learning CTHC: Patient Experience Recommender System for Persuasive Communication Tailoring (PERSPeCT). We hypothesized that PERSPeCT will select messages of higher influence than our standard CTHC system. This standard CTHC was proven effective in motivating smoking cessation in a prior randomized trial of 900 smokers (OR 1.70, 95% CI 1.03-2.81).MethodsPERSPeCT is an innovative hybrid machine learning recommender system that selects and sends motivational messages using algorithms that learn from message ratings from 846 previous participants (explicit feedback), and the prior explicit ratings of each individual participant. Current smokers (N=120) aged 18 years or older, English speaking, with Internet access were eligible to participate. These smokers were randomized to receive either PERSPeCT (intervention, n=74) or standard CTHC tailored messages (n=46). The study was conducted between October 2014 and January 2015. By randomization, we compared daily message ratings (mean of smoker ratings each day). At 30 days, we assessed the intervention's perceived influence, 30-day cessation, and changes in readiness to quit from baseline.ResultsThe proportion of days when smokers agreed/strongly agreed (daily rating ≥4) that the messages influenced them to quit was significantly higher for PERSPeCT (73%, 23/30) than standard CTHC (44%, 14/30, P=.02). Among less educated smokers (n=49), this difference was even more pronounced for days strongly agree (intervention: 77%, 23/30; comparison: 23%, 7/30, P<.001). There was no significant difference in the frequency which PERSPeCT randomized smokers agreed or strongly agreed that the intervention influenced them to quit smoking (P=.07) and use nicotine replacement therapy (P=.09). Among those who completed follow-up, 36% (20/55) of PERSPeCT smokers and 32% (11/34) of the standard CTHC group stopped smoking for one day or longer (P=.70).ConclusionsCompared to standard CTHC with proven effectiveness, PERSPeCT outperformed in terms of influence ratings and resulted in similar cessation rates.ClinicaltrialClinicaltrials.gov NCT02200432; https://clinicaltrials.gov/ct2/show/NCT02200432 (Archived by WebCite at http://www.webcitation.org/6lEJY1KEd).

Project description:BACKGROUND:There is a need to deliver smoking cessation support at a population level, both in developed and developing countries. Studies on internet-based and mobile phone-based smoking cessation interventions have shown that these methods can be as effective as other methods of support, and they can have a wider reach at a lower cost. OBJECTIVE:This randomized controlled trial (RCT) aimed to compare, on a population level, the efficacy of an identical, tailored smoking cessation intervention delivered by mobile text messaging versus email. METHODS:We conducted a nationwide 2-arm, double-blinded, fully automated RCT, close to a real-world setting, in Norway. We did not offer incentives to increase participation and adherence or to decrease loss to follow-up. We recruited users of the website, slutta.no, an open, free, multi-component Norwegian internet-based smoking cessation program, from May 2010 until October 2012. Enrolled smokers were considered as having completed a time point regardless of their response status if it was 1, 3, 6, or 12 months post cessation. We assessed 7315 participants using the following inclusion criteria: knowledge of the Norwegian language, age 16 years or older, ownership of a Norwegian cell phone, having an email account, current cigarette smoker, willingness to set a cessation date within 14 days (mandatory), and completion of a baseline questionnaire for tailoring algorithms. Altogether, 6137 participants were eligible for the study and 4378 participants (71.33%) provided informed consent to participate in the smoking cessation trial. We calculated the response rates for participants at the completed 1, 3, 6, and 12 months post cessation. For each arm, we conducted an intention-to-treat (ITT) analysis for each completed time point. The main outcome was 7-day self-reported point prevalence abstinence (PPA) at the completed 6 months post cessation. We calculated effect size of the 7-day self-reported PPA in the text message arm compared with the email arm as odds ratios (ORs) with 95% CIs for the 4 time points post cessation. RESULTS:At 6 months follow-up, 21.06% (384/1823) of participants in the text message arm and 18.62% (333/1788) in the email arm responded (P=.07) to the surveys. In the ITT analysis, 11.46% (209/1823) of participants in the text message arm compared with 10.96% (196/1788) in the email arm (OR 1.05, 95% CI 0.86-1.30) reported to have achieved 7 days PPA. CONCLUSIONS:This nationwide, double-blinded, large, fully automated RCT found that 1 in 9 enrolled smokers reported 7-day PPA in both arms, 6 months post cessation. Our study found that identical smoking cessation interventions delivered by mobile text messaging and email may be equally successful at a population level. TRIAL REGISTRATION:ClinicalTrials.gov NCT01103427; https://clinicaltrials.gov/ct2/show/NCT01103427.

Project description:BACKGROUND:China has the highest global prevalence of cigarette smokers, accounting for more than 40% of the total cigarette consumption in the world. Considering the shortage of smoking cessation services in China, and the acceptability, feasibility, and efficacy of mobile-phone-based text messaging interventions for quitting smoking in other countries, we conducted a mobile-phone-based smoking cessation study in China. METHODS AND FINDINGS:We conducted a randomized controlled trial in China across 30 cities and provinces from August 17, 2016, to May 27, 2017. Adult smokers aged 18 years and older with the intention to quit smoking were recruited and randomized to a 12-week high-frequency messaging (HFM) or low-frequency messaging (LFM) intervention ("Happy Quit") or to a control group in a 5:2:3 ratio. The control group received only text messages unrelated to quitting. The primary outcome was biochemically verified continuous smoking abstinence at 24 weeks. Secondary outcomes included (1) self-reported 7-day point prevalence of abstinence (i.e., not even a puff of smoke, for the last 7 days) at 1, 4, 8, 12, 16, 20, and 24 weeks; (2) self-reported continuous abstinence at 4, 12, and 24 weeks; and (3) self-reported average number of cigarettes smoked per day. A total of 1,369 participants received 12 weeks of intervention or control text messages with continued follow-up for 12 weeks. The baseline characteristics of participants among the HFM (n = 674), LFM (n = 284), and control (n = 411) groups were similar. The study sample included 1,295 (94.6%) men; participants had a mean age of 38.1 (SD 9.79) years and smoked an average of 20.1 (SD 9.19) cigarettes per day. We included the participants in an intention-to-treat analysis. Biochemically verified continuous smoking abstinence at 24 weeks occurred in 44/674 participants in the HFM group (6.5%), 17/284 participants in the LFM group (6.0%), and 8/411 participants (1.9%) in the control group; participants in both the HFM (odds ratio [OR] = 3.51, 95% CI 1.64-7.55, p < 0.001) and the LFM (OR = 3.21, 95% CI 1.36-7.54], p = 0.002) intervention groups were more likely to quit smoking than those in the control group. However, there was no difference in quit rate between the HFM and LFM interventions. We also found that the 7-day point quit rate from week 1 to week 24 ranged from approximately 10% to more than 26% with the intervention and from less than 4% to nearly 12% without the intervention. Those who continued as smokers in the HFM group smoked 1 to 3 fewer cigarettes per day than those in the LFM group over the 24 weeks of trial. Among study limitations, the participants were able to use other smoking cessation services (although very few participants reported using them), cotinine tests can only detect smoking status for a few days, and the proportion of quitters was small. CONCLUSIONS:Our findings demonstrate that a mobile-phone-based text messaging intervention (Happy Quit), with either high- or low-frequency messaging, led to smoking cessation in the present study, albeit in a low proportion of smokers, and can therefore be considered for use in large-scale intervention efforts in China. Mobile-phone-based interventions could be paired with other smoking cessation services for treatment-seeking smokers in China. TRIAL REGISTRATION:ClinicalTrials.gov NCT02693626.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets