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

Sadasivam, Rajani S.; Cutrona, Sarah L.; Kinney, Rebecca L.; Marlin, Benjamin M.; Mazor, Kathleen M.; Lemon, Stephenie C.; Houston, Thomas K.

doi:10.2196/jmir.4448

Cited by 45 publications

(60 citation statements)

References 38 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, smokers wanted a highly personalized experience that included tracking (of smoking and smoking locations) and adaptively tailored content. In the future, tracking tools could couple self-monitoring [29] with passive sensing via wearable devices [56,57] and machine learning to predict smoking triggers and proactively intervene with real-time tailored recommendations [58]. This intelligent tracking should coincide with smokers’ cravings and deliver support when and where it is needed [59].…”

Section: Discussionmentioning

confidence: 99%

Prioritizing the mHealth Design Space: A Mixed-Methods Analysis of Smokers’ Perspectives

Hartzler¹,

BlueSpruce²,

Catz³

et al. 2016

JMIR Mhealth Uhealth

View full text Add to dashboard Cite

BackgroundSmoking remains the leading cause of preventable disease and death in the United States. Therefore, researchers are constantly exploring new ways to promote smoking cessation. Mobile health (mHealth) technologies could be effective cessation tools. Despite the availability of commercial quit-smoking apps, little research to date has examined smokers’ preferred treatment intervention components (ie, design features). Honoring these preferences is important for designing programs that are appealing to smokers and may be more likely to be adopted and used.ObjectiveThe aim of this study was to understand smokers’ preferred design features of mHealth quit-smoking tools.MethodsWe used a mixed-methods approach consisting of focus groups and written surveys to understand the design preferences of adult smokers who were interested in quitting smoking (N=40). Focus groups were stratified by age to allow differing perspectives to emerge between older (>40 years) and younger (<40 years) participants. Focus group discussion included a “blue-sky” brainstorming exercise followed by participant reactions to contrasting design options for communicating with smokers, providing social support, and incentivizing program use. Participants rated the importance of preselected design features on an exit survey. Qualitative analyses examined emergent discussion themes and quantitative analyses compared feature ratings to determine which were perceived as most important.ResultsParticipants preferred a highly personalized and adaptive mHealth experience. Their ideal mHealth quit-smoking tool would allow personalized tracking of their progress, adaptively tailored feedback, and real-time peer support to help manage smoking cravings. Based on qualitative analysis of focus group discussion, participants preferred pull messages (ie, delivered upon request) over push messages (ie, sent automatically) and preferred interaction with other smokers through closed social networks. Preferences for entertaining games or other rewarding incentives to encourage program use differed by age group. Based on quantitative analysis of surveys, participants rated the importance of select design features significantly differently (P<.001). Design features rated as most important included personalized content, the ability to track one’s progress, and features designed to help manage nicotine withdrawal and medication side effects. Design features rated least important were quit-smoking videos and posting on social media. Communicating with stop-smoking experts was rated more important than communicating with family and friends about quitting (P=.03). Perceived importance of various design features varied by age, experience with technology, and frequency of smoking.ConclusionsFuture mHealth cessation aids should be designed with an understanding of smokers’ needs and preferences for these tools. Doing so does not guarantee treatment effectiveness, but balancing user preferences with best-practice treatment considerations could enhance program adoption a...

show abstract

Section: Discussionmentioning

confidence: 99%

Prioritizing the mHealth Design Space: A Mixed-Methods Analysis of Smokers’ Perspectives

Hartzler¹,

BlueSpruce²,

Catz³

et al. 2016

JMIR Mhealth Uhealth

View full text Add to dashboard Cite

show abstract

“…Compared with an active control group that received no messages, this CTHC system significantly impacted 6-month cessation outcomes (OR 1.70, 95% CI 1.03-2.81) [10]. Current implementations of CTHC systems (hereafter referred to as “standard CTHC”) combine tailoring variables (what variables should be used to tailor) and if-then-else rules (how to select messages for the different tailoring variables) to select messages for a patient [1,11]. Experts (or study designers) specify these tailoring variables and develop the rules based on their knowledge of the targeted population, literature, and health behavior theories.…”

Section: Introductionmentioning

confidence: 99%

“…In recommender systems, machine learning algorithms select the messages. As published, recommender systems offer multiple potential advantages to CTHC including the ability to continually learn and adapt to user feedback; however, this approach has not been adequately tested for CTHC [11]. …”

Section: Introductionmentioning

confidence: 99%

Impact of a Collective Intelligence Tailored Messaging System on Smoking Cessation: The Perspect Randomized Experiment

et al. 2016

Self Cite

View full text Add to dashboard Cite

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)

show abstract

“…The limitations of Computer Tailored Health Communication (CTHC) systems and the advantages of incorporating Recommender Systems into CTHC and the challenges thereto were presented in [15]. They argue that CTHC has reached its natural limits although technological advances have enabled CTHC to be delivered on multiple platforms like websites, email, and mobile devices and to reach large populations.…”

Section: Literature Survey On Healthcare Recommender Systems (Hrs)mentioning

confidence: 99%

A Survey of Context-Aware Healthcare Recommender Systems

2017

IJSR

View full text Add to dashboard Cite

Abstract:The advent of social web has transformed users from sheer consumers to ardent producers of information. The rapid growth coupled with the reliance on the internet for information ranging from e-commerce, e-government and social networks has led to infobesity. Recommender Systems have become essential tool to aid users to overcome the problem of information overload and provide personalized relevant suggestions. The use of Recommender Systems have been successful in both industry and academia. Recommender systems have also found their way into the Healthcare domain with varied applications.Despite the growing practical demand, a few challenges are hindering the adoption ofRecommender Systems in the Healthcare.The purpose of this study is to understand the trend of Recommender Systems applications inHealthcareby examining the published literature, and to provide practitioners and researchers with insight and future direction.We conducted a focused literature review to identify research papers on Recommender Systems in the Healthcare in the last ten years. The key findings of this survey is that the application of Recommender Systems inHealthcare is evolving. The incorporation of contextual information is limited although it has been suggested as a key ingredient to improving the quality of the recommendations and the accuracy of the predications.It is important to point out that aside from the common filtering problems of sparsity, cold start and scalability, a socio-technical issue of privacy, security and trust is emerging.Collaborative Filtering technique is predominantly in use in Healthcare Recommender Systems. Incorporation of contextual information is limited.Privacy, security and trust concerns may hinder the widespread use and acceptance of the Healthcare Recommender Systems.

show abstract

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

Cited by 45 publications

References 38 publications

Prioritizing the mHealth Design Space: A Mixed-Methods Analysis of Smokers’ Perspectives

Prioritizing the mHealth Design Space: A Mixed-Methods Analysis of Smokers’ Perspectives

Impact of a Collective Intelligence Tailored Messaging System on Smoking Cessation: The Perspect Randomized Experiment

A Survey of Context-Aware Healthcare Recommender Systems

Contact Info

Product

Resources

About