Evaluation of the Tobbstop Mobile App for Smoking Cessation: Cluster Randomized Controlled Clinical Trial

The Digital Therapeutics Real-World Evidence Framework: An Approach for Guiding Evidence-Based Digital Therapeutics Design, Development, Testing, and Monitoring

Digital therapeutics (DTx) are a promising way to provide safe, effective, accessible, sustainable, scalable, and equitable approaches to advance individual and population health. However, developing and deploying DTx is inherently complex in that DTx includes multiple interacting components, such as tools to support activities like medication adherence, health behavior goal-setting or self-monitoring, and algorithms that adapt the provision of these according to individual needs that may change over time. While myriad frameworks exist for different phases of DTx development, no single framework exists to guide evidence production for DTx across its full life cycle, from initial DTx development to long-term use. To fill this gap, we propose the DTx real-world evidence (RWE) framework as a pragmatic, iterative, milestone-driven approach for developing DTx. The DTx RWE framework is derived from the 4-phase development model used for behavioral interventions, but it includes key adaptations that are specific to the unique characteristics of DTx. To ensure the highest level of fidelity to the needs of users, the framework also incorporates real-world data (RWD) across the entire life cycle of DTx development and use. The DTx RWE framework is intended for any group interested in developing and deploying DTx in real-world contexts, including those in industry, health care, public health, and academia. Moreover, entities that fund research that supports the development of DTx and agencies that regulate DTx might find the DTx RWE framework useful as they endeavor to improve how DTxcan advance individual and population health.

Baseline characteristics and the factors influencing successful smoking cessation: A comparison between a WeChat smoking cessation mini-program and an offline smoking cessation clinic

INTRODUCTION

Smoking cessation (SC) clinics are a professional SC services in China. However, studies comparing the characteristics and SC rates of smoking populations in SC clinics with those using mobile SC programs are limited. We compared smokers' characteristics, 3-month SC rates, and the factors influencing 3-month SC success, between a large hospital SC clinic and a WeChat SC mini-program.

METHODS

Between January and November 2021, 384 participants voluntarily enrolled in either the hospital SC clinic (Group A: n=243) or the WeChat SC mini-program (Group B: n=141). Both groups underwent a 3-month SC intervention, and their SC status was monitored at 24 hours, 1 week, 1 month, and 3 months after quitting. SC rate was defined as the self-reported rate of continuous SC.

RESULTS

The 3-month SC rate was higher in Group A (42.4%) than in Group B (24.8%). Participants with middle school education had a lower likelihood of SC success than those with primary school or lower (p=0.014). Employees in the enterprise/business/services industries were more likely to have SC success than farmers (p=0.013). Participants with SC difficulty scores of 0-60 were more successful than those with scores >60 (p=0.001, p=0.000, respectively). Participants who quit smoking due to their illness, or other reasons, had a higher likelihood of SC success than those who quit due to concerns about their own and their family's health (p=0.006, p=0.098, respectively). While the likelihood of SC success was lower in those who quit because of the influence of their environment than in those who quit due to concerns about their own and their family's health (p=0.057).

CONCLUSIONS

Both SC clinics and WeChat SC mini-programs achieved satisfactory SC rates. The high accessibility of mobile SC platforms, which save time spent on transportation and medical visits, renders them worth promoting and publicizing as additional SC options for smokers, particularly young smokers.

Developing a Game (Inner Dragon) Within a Leading Smartphone App for Smoking Cessation: Design and Feasibility Evaluation Study

BACKGROUND

Several stand-alone smartphone apps have used serious games to provide an engaging approach to quitting smoking. So far, the uptake of these games has been modest, and the evidence base for their efficacy in promoting smoking cessation is still evolving. The feasibility of integrating a game into a popular smoking cessation app is unclear.

OBJECTIVE

The aim of this paper was to describe the design and iterative development of the Inner Dragon game within Smoke Free, a smartphone app with proven efficacy, and the results of a single-arm feasibility trial as part of a broad program that seeks to assess the effectiveness of the gamified app for smoking cessation.

METHODS

In phase 1, the study team undertook a multistep process to design and develop the game, including web-based focus group discussions with end users (n=15). In phase 2, a single-arm study of Smoke Free users who were trying to quit (n=30) was conducted to assess the feasibility and acceptability of the integrated game and to establish the feasibility of the planned procedures for a randomized pilot trial.

RESULTS

Phase 1 led to the final design of Inner Dragon, informed by principles from psychology and behavioral economics and incorporating several game mechanics designed to increase user engagement and retention. Inner Dragon users maintain an evolving pet dragon that serves as a virtual avatar for the users' progress in quitting. The phase-2 study established the feasibility of the study methods. The mean number of app sessions completed per user was 13.8 (SD 13.1; median 8; range 1-46), with a mean duration per session of 5.8 (median 1.1; range 0-81.1) minutes. Overall, three-fourths (18/24, 75%) of the participants entered the Inner Dragon game at least once and had a mean of 2.4 (SD 2.4) sessions of game use. The use of Inner Dragon was positively associated with the total number of app sessions (correlation 0.57). The mean satisfaction score of participants who provided ratings (11/24, 46%) was 4.2 (SD 0.6) on a 5-point scale; however, satisfaction ratings for Inner Dragon were only completed by 13% (3/24) of the participants.

CONCLUSIONS

Findings supported further development and evaluation of Inner Dragon as a beneficial feature of Smoke Free. The next step of this study is to conduct a randomized pilot trial to determine whether the gamified version of the app increases user engagement over a standard version of the app.

Effectiveness of eHealth Smoking Cessation Interventions: Systematic Review and Meta-Analysis

BACKGROUND

Rapid advancements in eHealth and mobile health (mHealth) technologies have driven researchers to design and evaluate numerous technology-based interventions to promote smoking cessation. The evolving nature of cessation interventions emphasizes a strong need for knowledge synthesis.

OBJECTIVE

This systematic review and meta-analysis aimed to summarize recent evidence from randomized controlled trials regarding the effectiveness of eHealth-based smoking cessation interventions in promoting abstinence and assess nonabstinence outcome indicators, such as cigarette consumption and user satisfaction, via narrative synthesis.

METHODS

We searched for studies published in English between 2017 and June 30, 2022, in 4 databases: PubMed (including MEDLINE), PsycINFO, Embase, and Cochrane Library. Two independent reviewers performed study screening, data extraction, and quality assessment based on the GRADE (Grading of Recommendations, Assessment, Development, and Evaluations) framework. We pooled comparable studies based on the population, follow-up time, intervention, and control characteristics. Two researchers performed an independent meta-analysis on smoking abstinence using the Sidik-Jonkman random-effects model and log risk ratio (RR) as the effect measurement. For studies not included in the meta-analysis, the outcomes were narratively synthesized.

RESULTS

A total of 464 studies were identified through an initial database search after removing duplicates. Following screening and full-text assessments, we deemed 39 studies (n=37,341 participants) eligible for this review. Of these, 28 studies were shortlisted for meta-analysis. According to the meta-analysis, SMS or app text messaging can significantly increase both short-term (3 months) abstinence (log RR=0.50, 95% CI 0.25-0.75; I2=0.72%) and long-term (6 months) abstinence (log RR=0.77, 95% CI 0.49-1.04; I2=8.65%), relative to minimal cessation support. The frequency of texting did not significantly influence treatment outcomes. mHealth apps may significantly increase abstinence in the short term (log RR=0.76, 95% CI 0.09-1.42; I2=88.02%) but not in the long term (log RR=0.15, 95% CI -0.18 to 0.48; I2=80.06%), in contrast to less intensive cessation support. In addition, personalized or interactive interventions showed a moderate increase in cessation for both the short term (log RR=0.62, 95% CI 0.30-0.94; I2=66.50%) and long term (log RR=0.28, 95% CI 0.04-0.53; I2=73.42%). In contrast, studies without any personalized or interactive features had no significant impact. Finally, the treatment effect was similar between trials that used biochemically verified or self-reported abstinence. Among studies reporting outcomes besides abstinence (n=20), a total of 11 studies reported significantly improved nonabstinence outcomes in cigarette consumption (3/14, 21%) or user satisfaction (8/19, 42%).

CONCLUSIONS

Our review of 39 randomized controlled trials found that recent eHealth interventions might promote smoking cessation, with mHealth being the dominant approach. Despite their success, the effectiveness of such interventions may diminish with time. The design of more personalized interventions could potentially benefit future studies.

TRIAL REGISTRATION

PROSPERO CRD42022347104; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=347104.

SweetMama: Usability Assessment of a Novel Mobile Application Among Low-Income Pregnant People to Assist With Diabetes Management and Support

Background

Mobile health tools may be effective strategies to improve engagement, education, and diabetes-related health during pregnancy. We developed SweetMama, a patient-centered, interactive mobile application (app) designed to support and educate low-income pregnant people with diabetes. Our objective was to evaluate the SweetMama user experience and acceptability.

Methods

SweetMama is a mobile app with static and dynamic features. Static features include a customized homepage and resource library. Dynamic features include delivery of a theory-driven diabetes-specific curriculum via 1) motivational, tip, and goal-setting messages aligning with treatment and gestational age; 2) appointment reminders; and 3) ability to mark content as "favorite." In this usability assessment, low-income pregnant people with gestational or type 2 diabetes used SweetMama for 2 weeks. Participants provided qualitative feedback (via interviews) and quantitative feedback (via validated usability/satisfaction measures) on their experience. User analytic data detailed the duration and type of interactions users had with SweetMama.

Results

Of 24 individuals enrolled, 23 used SweetMama and 22 completed exit interviews. Participants were mostly non-Hispanic Black (46%) or Hispanic (38%) individuals. Over the 14-day period, users accessed SweetMama frequently (median number of log-ins 8 [interquartile range 6-10]), for a median of 20.5 total minutes, and engaged all features. A majority (66.7%) rated SweetMama as having moderate or high usability. Participants emphasized design and technical strengths and beneficial effects on diabetes self-management and also identified limitations of the user experience.

Conclusion

Pregnant people with diabetes found SweetMama to be user-friendly, informative, and engaging. Future work must study its feasibility for use throughout pregnancy and its efficacy to improve perinatal outcomes.

Evaluation of the smoking cessation effects of QuitAction, a smartphone WeChat platform

INTRODUCTION

Many smokers in China desire to quit, though the success rate among adults is low. This study evaluated the effects of QuitAction, a WeChat smoking cessation platform, summarized the intervention experience of the smoking cessation platform, identified aspects of the platform that necessitated improvement, and provided references for further optimization of the smoking cessation platform.

METHODS

This single-arm study was conducted in Hunan, China, from September 2020 to October 2021. Regular smokers, who were aged ≥15 years and willing to quit smoking using QuitAction, were recruited. An in-application questionnaire evaluated participants' baseline smoking status and intention to quit smoking. The QuitAction program included questionnaires regarding the participants' ongoing smoking cessation status at 24 hours, one week, one month and three months after quitting. The smoking cessation procedure was discontinued if the participant had no intention of continuing. The smoking cessation rate, influencing success factors, frequency of use satisfaction, and helpfulness of QuitAction were recorded.

RESULTS

A total of 303 participants registered and logged into the QuitAction program, including 59 with incomplete information and 64 with no intention of quitting. The study finally included 180 participants. The smoking cessation rate was 33.9% at 24 hours, 27.2% at one week, 26.1% at one month, and 25.0% at three months. QuitAction was reported as helpful by 94.9% of participants and 95.7% were satisfied with the program. Participants with a quitting difficulty score of 80-100 were less likely to quit smoking than participants with a difficulty score of 0-60 (OR=0.28; 95% CI: 0.10-0.78; p=0.015). Participants using the platform ≥5 times were more likely to quit smoking than those who used the platform <5 times (OR=3.59; 95% CI: 1.51-8.52; p=0.004).

CONCLUSIONS

The QuitAction platform provides smoking cessation services that can improve smokers' success rate and improve user experience satisfaction.

Effectiveness of an App for tobacco cessation in pregnant smokers (TOBBGEST): study protocol

BACKGROUND

Tobacco consumption during pregnancy is one of the most modifiable causes of morbidity and mortality for both pregnant smokers and their foetus. Even though pregnant smokers are conscious about the negative effects of tobacco consumption, they also had barriers for smoking cessation and most of them continue smoking, being a major public health problem. The aim of this study is to determine the effectiveness of an application (App) for mobile devices, designed with a gamification strategy, in order to help pregnant smokers to quit smoking during pregnancy and in the long term.

METHODS

This study is a multicentre randomized community intervention trial. It will recruit pregnant smokers (200 participants/group), aged more than 18 years, with sporadically or daily smoking habit in the last 30 days and who follow-up their pregnancy in the Sexual and Reproductive Health Care Services of the Camp de Tarragona and Central Catalonia Primary Care Departments. All the participants will have the usual clinical practice intervention for smoking cessation, whereas the intervention group will also have access to the App. The outcome measure will be prolonged abstinence at 12 months after the intervention, as confirmed by expired-carbon monoxide and urinary cotinine tests. Results will be analysed based on intention to treat. Prolonged abstinence rates will be compared, and the determining factors will be evaluated using multivariate statistical analysis.

DISCUSSION

The results of this study will offer evidence about the effectiveness of an intervention using a mobile App in smoking cessation for pregnant smokers, to decrease comorbidity associated with long-term smoking. If this technology is proven effective, it could be readily incorporated into primary care intervention for all pregnant smokers.

TRIAL REGISTRATION

Clinicaltrials.gov ID NCT05222958 . Trial registered 3 February 2022.

The effectiveness of smartphone application-based interventions for assisting smoking cessation: A systematic review and meta-analysis (Preprint)

BACKGROUND

Smoking is a leading cause of premature death globally. Quitting smoking reduces the risk of all-cause mortality by 11%-34%. Smartphone app-based smoking cessation (SASC) interventions have been developed and are widely used. However, the evidence for the effectiveness of smartphone-based interventions for smoking cessation is currently equivocal.

OBJECTIVE

The purpose of this study was to synthesize the evidence for the effectiveness of smartphone app-based interventions for smoking cessation.

METHODS

We conducted a systematic review and meta-analysis of the effectiveness of smartphone interventions for smoking cessation based on the Cochrane methodology. An electronic literature search was performed using the Cochrane Library, Web of Science, PubMed, Embase, PsycINFO, China National Knowledge Infrastructure, and Wanfang databases to identify published papers in English or Chinese (there was no time limit regarding the publication date). The outcome was the smoking abstinence rate, which was either a 7-day point prevalence abstinence rate or a continuous abstinence rate.

RESULTS

A total of 9 randomized controlled trials involving 12,967 adults were selected for the final analysis. The selected studies from 6 countries (the United States, Spain, France, Switzerland, Canada, and Japan) were included in the meta-analysis between 2018 and 2022. Pooled effect sizes (across all follow-up time points) revealed no difference between the smartphone app group and the comparators (standard care, SMS text messaging intervention, web-based intervention, smoking cessation counseling, or apps as placebos without real function; odds ratio [OR] 1.25, 95% CI 0.99-1.56, P=.06, I²=73.6%). Based on the subanalyses, 6 trials comparing smartphone app interventions to comparator interventions reported no significant differences in effectiveness (OR 1.03, 95% CI 0.85-1.26, P=.74, I²=57.1%). However, the 3 trials that evaluated the combination of smartphone interventions combined with pharmacotherapy compared to pharmacotherapy alone found higher smoking abstinence rates in the combined intervention (OR 1.79, 95% CI 1.38-2.33, P=.74, I²=7.4%). All SASC interventions with higher levels of adherence were significantly more effective (OR 1.48, 95% CI 1.20-1.84, P<.001, I²=24.5%).

CONCLUSIONS

This systematic review and meta-analysis did not support the effectiveness of delivering smartphone-based interventions alone to achieve higher smoking abstinence rates. However, the efficacy of smartphone-based interventions increased when combined with pharmacotherapy-based smoking cessation approaches.

TRIAL REGISTRATION

PROSPERO CRD42021267615; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=267615.

The current evidence for substance use disorder apps

PURPOSE OF REVIEW

New mHealth (smartphone) apps for substance use disorders (SUD) are emerging at an accelerated rate, with consumer choice typically guided by app-store user ratings rather than their effectiveness. The expansive reach, low-cost and accessibility of mHealth apps have driven their popularity and appeal as alternatives to traditional treatment; as such, rigorously establishing their effectiveness is of paramount importance.

RECENT FINDINGS

Several systematic reviews conclude that the evidence-base for mHealth SUD apps is weak, inconclusive and hampered by substantial heterogeneity in study designs. However, there have been a number of interesting and novel developments in this area in recent years, which have not been synthesised to date.

SUMMARY

Most mHealth apps deliver either multiple-component behaviour change techniques, discrete psychological interventions or cognitive training interventions, or are designed to act as adjuncts to facilitate the delivery of clinical or continuing care. There are promising signals of their feasibility, acceptability and preliminary effectiveness in numerous open-label pilot studies of mHealth apps targeting alcohol and smoking. However, only a handful of sufficiently-powered, well-designed randomised controlled trials have been conducted to date with mixed findings. Furthermore, there has been limited recent attention on mHealth apps aiming to improve outcomes for individuals using other drugs.

Development, validation and transfer to clinical practice of a mobile application for the treatment of smoking

OBJECTIVE

The main objective is to transfer to clinical practice a new smoking cessation application ("Vive sin Tabaco" a) in all health centers of the public Basque Health Service.

DESIGN

An implementation study of a smoking cessation program previously validated. After implementation, a retrospective study has been carried out to evaluate its use under normal conditions. SITE: The process of transfer to clinical practice has been held in several phases; first a pilotage in four health centers of Alava and subsequently, when all reported incidents were resolved, it was extended to all health centers of the Basque Health Service.

INTERVENTION AND MAIN MEASUREMENT

Development of "Vive sin Tabaco"; a corporate tool for smoking cessation, and its transfer to clinical practice. All interested health care workers received training on how to use the application. User manuals for both patients and professionals were developed. Smoking cessation rates at 12 months during implementation were also collected.

RESULTS

The percentage of patients of post pilot phase who quit smoking at 12 months was 14.1%.

CONCLUSIONS

The conception of "Vive sin tabaco" as a corporate tool for smoking cessation, available in all health centers of Basque Health Service, has been long and arduous, and has required the participation of health professionals and patients as end-users in order to obtain a tool that adapts to their expectations and guarantees greater usability and satisfaction. This application is being effective as an adjuvant tool to health advice.

Effectiveness of a Conversational Chatbot (Dejal@bot) for the Adult Population to Quit Smoking: Pragmatic, Multicenter, Controlled, Randomized Clinical Trial in Primary Care

Background

Tobacco addiction is the leading cause of preventable morbidity and mortality worldwide, but only 1 in 20 cessation attempts is supervised by a health professional. The potential advantages of mobile health (mHealth) can circumvent this problem and facilitate tobacco cessation interventions for public health systems. Given its easy scalability to large populations and great potential, chatbots are a potentially useful complement to usual treatment.

Objective

This study aims to assess the effectiveness of an evidence-based intervention to quit smoking via a chatbot in smartphones compared with usual clinical practice in primary care.

Methods

This is a pragmatic, multicenter, controlled, and randomized clinical trial involving 34 primary health care centers within the Madrid Health Service (Spain). Smokers over the age of 18 years who attended on-site consultation and accepted help to quit tobacco were recruited by their doctor or nurse and randomly allocated to receive usual care (control group [CG]) or an evidence-based chatbot intervention (intervention group [IG]). The interventions in both arms were based on the 5A’s (ie, Ask, Advise, Assess, Assist, and Arrange) in the US Clinical Practice Guideline, which combines behavioral and pharmacological treatments and is structured in several follow-up appointments. The primary outcome was continuous abstinence from smoking that was biochemically validated after 6 months by the collaborators. The outcome analysis was blinded to allocation of patients, although participants were unblinded to group assignment. An intention-to-treat analysis, using the baseline-observation-carried-forward approach for missing data, and logistic regression models with robust estimators were employed for assessing the primary outcomes.

Results

The trial was conducted between October 1, 2018, and March 31, 2019. The sample included 513 patients (242 in the IG and 271 in the CG), with an average age of 49.8 (SD 10.82) years and gender ratio of 59.3% (304/513) women and 40.7% (209/513) men. Of them, 232 patients (45.2%) completed the follow-up, 104/242 (42.9%) in the IG and 128/271 (47.2%) in the CG. In the intention-to-treat analysis, the biochemically validated abstinence rate at 6 months was higher in the IG (63/242, 26%) compared with that in the CG (51/271, 18.8%; odds ratio 1.52, 95% CI 1.00-2.31; P=.05). After adjusting for basal CO-oximetry and bupropion intake, no substantial changes were observed (odds ratio 1.52, 95% CI 0.99-2.33; P=.05; pseudo-R²=0.045). In the IG, 61.2% (148/242) of users accessed the chatbot, average chatbot-patient interaction time was 121 (95% CI 121.1-140.0) minutes, and average number of contacts was 45.56 (SD 36.32).

Conclusions

A treatment including a chatbot for helping with tobacco cessation was more effective than usual clinical practice in primary care. However, this outcome was at the limit of statistical significance, and therefore these promising results must be interpreted with caution.

Trial Registration

Clinicaltrials.gov NCT 03445507; https://tinyurl.com/mrnfcmtd

International Registered Report Identifier (IRRID)

RR2-10.1186/s12911-019-0972-z

Factors Influencing Adherence to mHealth Apps for Prevention or Management of Noncommunicable Diseases: Systematic Review

Background

Mobile health (mHealth) apps show vast potential in supporting patients and health care systems with the increasing prevalence and economic costs of noncommunicable diseases (NCDs) worldwide. However, despite the availability of evidence-based mHealth apps, a substantial proportion of users do not adhere to them as intended and may consequently not receive treatment. Therefore, understanding the factors that act as barriers to or facilitators of adherence is a fundamental concern in preventing intervention dropouts and increasing the effectiveness of digital health interventions.

Objective

This review aimed to help stakeholders develop more effective digital health interventions by identifying factors influencing the continued use of mHealth apps targeting NCDs. We further derived quantified adherence scores for various health domains to validate the qualitative findings and explore adherence benchmarks.

Methods

A comprehensive systematic literature search (January 2007 to December 2020) was conducted on MEDLINE, Embase, Web of Science, Scopus, and ACM Digital Library. Data on intended use, actual use, and factors influencing adherence were extracted. Intervention-related and patient-related factors with a positive or negative influence on adherence are presented separately for the health domains of NCD self-management, mental health, substance use, nutrition, physical activity, weight loss, multicomponent lifestyle interventions, mindfulness, and other NCDs. Quantified adherence measures, calculated as the ratio between the estimated intended use and actual use, were derived for each study and compared with the qualitative findings.

Results

The literature search yielded 2862 potentially relevant articles, of which 99 (3.46%) were included as part of the inclusion criteria. A total of 4 intervention-related factors indicated positive effects on adherence across all health domains: personalization or tailoring of the content of mHealth apps to the individual needs of the user, reminders in the form of individualized push notifications, user-friendly and technically stable app design, and personal support complementary to the digital intervention. Social and gamification features were also identified as drivers of app adherence across several health domains. A wide variety of patient-related factors such as user characteristics or recruitment channels further affects adherence. The derived adherence scores of the included mHealth apps averaged 56.0% (SD 24.4%).

Conclusions

This study contributes to the scarce scientific evidence on factors that positively or negatively influence adherence to mHealth apps and is the first to quantitatively compare adherence relative to the intended use of various health domains. As underlying studies mostly have a pilot character with short study durations, research on factors influencing adherence to mHealth apps is still limited. To facilitate future research on mHealth app adherence, researchers should clearly outline and justify the app’s intended use; report objective data on actual use relative to the intended use; and, ideally, provide long-term use and retention data.

Smoking Prevalence among Physicians: A Systematic Review and Meta-Analysis

BACKGROUND

Smoking is a major public health problem. Although physicians have a key role in the fight against smoking, some of them are still smoking. Thus, we aimed to conduct a systematic review and meta-analysis on the prevalence of smoking among physicians.

METHODS

PubMed, Cochrane, and Embase databases were searched. The prevalence of smoking among physicians was estimated and stratified, where possible, by specialties, continents, and periods of time. Then, meta-regressions were performed regarding putative influencing factors such as age and sex.

RESULTS

Among 246 studies and 497,081 physicians, the smoking prevalence among physicians was 21% (95CI 20 to 23%). Prevalence of smoking was 25% in medical students, 24% in family practitioners, 18% in surgical specialties, 17% in psychiatrists, 16% in medical specialties, 11% in anesthesiologists, 9% in radiologists, and 8% in pediatricians. Physicians in Europe and Asia had a higher smoking prevalence than in Oceania. The smoking prevalence among physicians has decreased over time. Male physicians had a higher smoking prevalence. Age did not influence smoking prevalence.

CONCLUSION

Prevalence of smoking among physicians is high, around 21%. Family practitioners and medical students have the highest percentage of smokers. All physicians should benefit from targeted preventive strategies.

Prediction of Smoking Risk From Repeated Sampling of Environmental Images: Model Validation

Background

Viewing their habitual smoking environments increases smokers’ craving and smoking behaviors in laboratory settings. A deep learning approach can differentiate between habitual smoking versus nonsmoking environments, suggesting that it may be possible to predict environment-associated smoking risk from continuously acquired images of smokers’ daily environments.

Objective

In this study, we aim to predict environment-associated risk from continuously acquired images of smokers’ daily environments. We also aim to understand how model performance varies by location type, as reported by participants.

Methods

Smokers from Durham, North Carolina and surrounding areas completed ecological momentary assessments both immediately after smoking and at randomly selected times throughout the day for 2 weeks. At each assessment, participants took a picture of their current environment and completed a questionnaire on smoking, craving, and the environmental setting. A convolutional neural network–based model was trained to predict smoking, craving, whether smoking was permitted in the current environment and whether the participant was outside based on images of participants’ daily environments, the time since their last cigarette, and baseline data on daily smoking habits. Prediction performance, quantified using the area under the receiver operating characteristic curve (AUC) and average precision (AP), was assessed for out-of-sample prediction as well as personalized models trained on images from days 1 to 10. The models were optimized for mobile devices and implemented as a smartphone app.

Results

A total of 48 participants completed the study, and 8008 images were acquired. The personalized models were highly effective in predicting smoking risk (AUC=0.827; AP=0.882), craving (AUC=0.837; AP=0.798), whether smoking was permitted in the current environment (AUC=0.932; AP=0.981), and whether the participant was outside (AUC=0.977; AP=0.956). The out-of-sample models were also effective in predicting smoking risk (AUC=0.723; AP=0.785), whether smoking was permitted in the current environment (AUC=0.815; AP=0.937), and whether the participant was outside (AUC=0.949; AP=0.922); however, they were not effective in predicting craving (AUC=0.522; AP=0.427). Omitting image features reduced AUC by over 0.1 when predicting all outcomes except craving. Prediction of smoking was more effective for participants whose self-reported location type was more variable (Spearman ρ=0.48; P=.001).

Conclusions

Images of daily environments can be used to effectively predict smoking risk. Model personalization, achieved by incorporating information about daily smoking habits and training on participant-specific images, further improves prediction performance. Environment-associated smoking risk can be assessed in real time on a mobile device and can be incorporated into device-based smoking cessation interventions.

Methods Used in Smoking Cessation and Reduction Attempts: Findings from Help-Seeking Smokers

In addition to traditional smoking cessation methods like nicotine replacement therapy (NRT), new methods such as mobile applications and e-cigarettes have been added to the toolbox. The purpose of this study was to examine which methods smokers currently use in quit or reduction attempts and map characteristics of users of the various methods. In this study, participants were smokers who visited a website or called a quit line for smoking cessation and who were currently in quit or reduction attempts (N = 740). Data were collected in Norway in 2013-2017 through a web survey. Most smokers were currently trying to quit, and the most frequently used methods were a smoking cessation app for mobile phones, nicotine replacement therapies (NRTs), and e-cigarettes. Logistic regression analyses identified older daily smokers with high cigarette consumption as NRT users, while the users of a cessation app were younger females. The use of e-cigarettes was associated with older, low educated smokers with low cigarette consumption. The use of the mobile phone app was associated with having made several recent quit attempts. The study provides insight into help-seeking smokers' preferences for smoking cessation methods and user characteristics. This knowledge is relevant for further work in smoking cessation planning and policies.