They say a picture speaks a thousand words. Marry that phrase with technology and you have the basis of this fascinating study on losing weight!

Behavioural weight loss interventions are an effective way to help people lose weight. But diet self monitoring requires feedback, support and persistence to be effective. Typical monitoring has meant keeping a journal.

The smart phone has become a camera,  making immediate food recording possible. This could reduce the participant burden, as the authors of a fascinating study point out. The next part would be how to provide feedback.

One approach that is suggested is the concept of crowdsourcing which uses the input from several users to provide feedback and information. One app (theEatery) has users taking pictures with the Eatery app, rate their meals with a sliding scale from fit healthy to fat unhealthy. Users receive peer feedback as an average healthiness score for their own food and beverages.

The potential is that Health technology could reduce the burden of self monitoring but the question is- how valid is crowdsourced monitoring?  And would these raters -untrained -  compare to trained raters and would they rate appropriately foods that should be increased and those that should be decreased?

In this study crowsourced ratings of some 450 pictures from the Mobile Eatery app were rated by 5,006 peers on a simple scale of 'healthiness' compared to trained raters.  In addition the food and beverages in each picture were categorized and the impact on the peer rating scale was examined.  

The trained raters' scores were all very closely correlated to the peer healthiness score for all photos.

Researchers say that consistent and frequent monitoring is more important than accuracy for weight loss. This study demonstrates the potential of apps and crowdsourcing for weight loss