Crowdsourcing App May Help Dieters Stay On Track

Brie Turner-McGrievy, Ph.D., M.S., R.D. Assistant Professor University of South Carolina Arnold School of Public Health Department of Health Promotion, Education, and Behavior Discovery Columbia, SC 29208MedicalResearch.com Interview with:
Brie Turner-McGrievy, Ph.D., M.S., R.D.
Assistant Professor, University of South Carolina
Arnold School of Public Health
Department of Health Promotion, Education, and Behavior Discovery
Columbia, SC 29208

 Medical Research: What are the main findings of the study?

Dr. Turner-McGrievy: This study assessed how closely crowdsourced ratings of foods and beverages contained in 450 pictures from the Eatery mobile app as rated by peer users using a simple “healthiness” scale were related to the ratings of the same pictures by trained observers. Our trained observers used a rating scale based on the U.S. Dietary Guidelines to assess the healthiness of the foods and beverages in each picture. Crowdsourcing uses the input of several users to provide feedback and information. We found that all three trained raters’ scores was highly correlated with the peer healthiness score for all the photos. In addition, we found that peer ratings were in the expected direction for both foods/beverages the Dietary Guidelines say to increase and ones to limit. Photos with fruit, vegetables, whole grains, and legumes, nuts, and seeds were all associated with higher peer healthiness scores and processed, food from fast food restaurants, refined grains, red meat, cheese, savory snacks, sweets/desserts, and sugar sweetened beverages were associated with lower peer healthiness scores.

Medical Research: Were any of the findings unexpected?

Dr. Turner-McGrievy: It was surprising that untrained users of the Eatery app did such a good job assessing the healthiness of the foods and beverages in the photos. They did this without any training.

Medical Research: What should clinicians and patients take away from your report?

Dr. Turner-McGrievy: We know that self-monitoring the diet is a key component to weight loss but that adherence to self-monitoring tends to decline over time. It can be difficult and burdensome to enter every food you eat or beverage you drink. Taking a picture and letting other users provide you with feedback is one way to decrease the burden, and maybe also add some fun to the process as well.

Medical Research: What recommendations do you have for future research as a result of this study?

Dr. Turner-McGrievy: The findings suggest that crowdsourcing holds potential to provide basic feedback on overall diet quality to users utilizing a low burden approach. Future research may wish to explore this as a potential strategy to reduce the burden associated with dietary self-monitoring.

Citation:

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

Gabrielle M Turner-McGrievy,Elina E Helander,Kirsikka Kaipainen,Jose Maria Perez-Macias,Ilkka Korhonen

J Am Med Inform Assoc amiajnl-2014-002636Published Online First: 4 August 2014 doi:10.1136/amiajnl-2014-002636

 

 

Last Updated on August 8, 2014 by Marie Benz MD FAAD