The use of crowdsourcing for dietary self-monitoring: crowdsourced ratings of food pictures are comparable to ratings by trained observers

Turner‐McGrievy, Gabrielle; Helander, Elina; Kaipainen, Kirsikka; Perez-Macias, Jose Maria; Korhonen, Ilkka

doi:10.1136/amiajnl-2014-002636

Cited by 25 publications

(18 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Turner-McGrievy et al’s “EateryApp” had the crowd rating the healthiness of photos of food after 1.5 hours of training. The authors also compared their ratings to those of experts and found a strong correlation between the ratings (r = 0.88, P < 0.001) [ 47 ]. Moorhead also used photos to have a crowd estimate the calories in food, but also developed personalised messages for prevention and management of obesity.…”

Section: Resultsmentioning

confidence: 99%

“…Crowdsourcing was found to be useful to predict poor sanitary conditions and foodborne illnesses based on Yelp reviews [ 43 , 44 ], to assess whether meals were healthy, irrelevant of whether the crowd was formed of experts or laypeople [ 46 , 47 ] and to identify predictors of obesity in statistical models for childhood and adulthood obesity [ 49 , 50 ]. Applications to help people make healthy choices based on where and what they eat are important.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Applications of crowdsourcing in health: an overview

Wazny

2018

Journal of Global Health

115

View full text Add to dashboard Cite

BackgroundCrowdsourcing is a nascent phenomenon that has grown exponentially since it was coined in 2006. It involves a large group of people solving a problem or completing a task for an individual or, more commonly, for an organisation. While the field of crowdsourcing has developed more quickly in information technology, it has great promise in health applications. This review examines uses of crowdsourcing in global health and health, broadly.MethodsSemantic searches were run in Google Scholar for “crowdsourcing,” “crowdsourcing and health,” and similar terms. 996 articles were retrieved and all abstracts were scanned. 285 articles related to health. This review provides a narrative overview of the articles identified.ResultsEight areas where crowdsourcing has been used in health were identified: diagnosis; surveillance; nutrition; public health and environment; education; genetics; psychology; and, general medicine/other. Many studies reported crowdsourcing being used in a diagnostic or surveillance capacity. Crowdsourcing has been widely used across medical disciplines; however, it is important for future work using crowdsourcing to consider the appropriateness of the crowd being used to ensure the crowd is capable and has the adequate knowledge for the task at hand. Gamification of tasks seems to improve accuracy; other innovative methods of analysis including introducing thresholds and measures of trustworthiness should be considered.ConclusionCrowdsourcing is a new field that has been widely used and is innovative and adaptable. With the exception of surveillance applications that are used in emergency and disaster situations, most uses of crowdsourcing have only been used as pilots. These exceptions demonstrate that it is possible to take crowdsourcing applications to scale. Crowdsourcing has the potential to provide more accessible health care to more communities and individuals rapidly and to lower costs of care.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Applications of crowdsourcing in health: an overview

Wazny

2018

Journal of Global Health

115

View full text Add to dashboard Cite

show abstract

“…A previous study, however, found that untrained users of a crowdsourcing photo app could rate foods as "healthy" or "not healthy" with similar accuracy to trained raters. 24 Some of the mobile apps examined offered professional feedback from an RDN (eg, Meal Logger) for a fee or offered a professional version of their app to RDNs for use with their clients. Another popular app (Rise) requires a monthly subscription fee and includes a tailored diet plan with feedback from a coach.…”

Section: Discussionmentioning

confidence: 99%

“…Crowdsourcing, which includes soliciting information provided by several sources as a low-burden approach to garnering feedback, has been used in the past to rate dietary quality of foods self-monitored via photo using a mobile app. 24 A crowdsourcing approach could potentially be used to provide feedback and social support to users regarding diet quality of foods photographed via mobile app to promote weight loss in a cost effective manner to diverse populations.…”

mentioning

confidence: 99%

Is a Picture Worth a Thousand Words? Few Evidence-Based Features of Dietary Interventions Included in Photo Diet Tracking Mobile Apps for Weight Loss

Hales

Dunn

Wilcox

et al. 2016

J Diabetes Sci Technol

View full text Add to dashboard Cite

Background: Apps using digital photos to track dietary intake and provide feedback are common, but currently there has been no research examining what evidence-based strategies are included in these apps. Methods: A content analysis of mobile apps for photo diet tracking was conducted, including whether effective techniques for interventions promoting behavior change, including self-regulation, for healthy eating (HE) are targeted. An initial search of app stores yielded 34 apps (n = 8 Android and Apple; n = 11 Android; n = 15 Apple). One app was removed (unable to download), and other apps (n = 4) were unable to be rated (no longer available). Remaining apps (n = 29) were downloaded, reviewed, and coded by 2 independent reviewers to determine the number of known effective self-regulation and other behavior change techniques included. The raters met to compare their coding of the apps, calculate interrater agreement, resolve any discrepancies, and come to a consensus. Results: Six apps (21%) did not utilize any of the behavior change techniques examined. Three apps (10%) provided feedback to users via crowdsourcing or collective feedback from other users and professionals, 7 apps (24%) used crowdsourcing or collective feedback, 1 app (3%) used professionals, and 18 apps (62%) did not provide any dietary feedback to users. Conclusion: Few photo diet-tracking apps include evidence-based strategies to improve dietary intake. Use of photos to self-monitor dietary intake and receive feedback has the potential to reduce user burden for self-monitoring, yet photo diet tracking apps need to incorporate known effective behavior strategies for HE, including self-regulation.

show abstract

“…The estimation of food intake and its nutritional information is helpful to our health [ 37 ] as it provides detailed records of our dietary history. Previous work mainly conducted the analysis by leveraging the crowd [ 37 , 53 ] and computer vision algorithms [ 6 , 35 ].…”

Section: Related Workmentioning

confidence: 99%

Yum-Me

Yang

Hsieh

Yang

et al. 2017

ACM Trans. Inf. Syst.

119

View full text Add to dashboard Cite

Nutrient-based meal recommendations have the potential to help individuals prevent or manage conditions such as diabetes and obesity. However, learning people’s food preferences and making recommendations that simultaneously appeal to their palate and satisfy nutritional expectations are challenging. Existing approaches either only learn high-level preferences or require a prolonged learning period. We propose Yum-me, a personalized nutrient-based meal recommender system designed to meet individuals’ nutritional expectations, dietary restrictions, and fine-grained food preferences. Yum-me enables a simple and accurate food preference profiling procedure via a visual quiz-based user interface and projects the learned profile into the domain of nutritionally appropriate food options to find ones that will appeal to the user. We present the design and implementation of Yum-me and further describe and evaluate two innovative contributions. The first contriution is an open source state-of-the-art food image analysis model, named FoodDist. We demonstrate FoodDist’s superior performance through careful benchmarking and discuss its applicability across a wide array of dietary applications. The second contribution is a novel online learning framework that learns food preference from itemwise and pairwise image comparisons. We evaluate the framework in a field study of 227 anonymous users and demonstrate that it outperforms other baselines by a significant margin. We further conducted an end-to-end validation of the feasibility and effectiveness of Yum-me through a 60-person user study, in which Yum-me improves the recommendation acceptance rate by 42.63%.

show abstract

The use of crowdsourcing for dietary self-monitoring: crowdsourced ratings of food pictures are comparable to ratings by trained observers

Abstract: The findings suggest that crowdsourcing holds potential to provide basic feedback on overall diet quality to users utilizing a low burden approach.

Cited by 25 publications

References 24 publications

Applications of crowdsourcing in health: an overview

Applications of crowdsourcing in health: an overview

Is a Picture Worth a Thousand Words? Few Evidence-Based Features of Dietary Interventions Included in Photo Diet Tracking Mobile Apps for Weight Loss

Yum-Me

Contact Info

Product

Resources

About