Leslie Kernisan MD MPH:

In general, the ePrognosis story illustrates a common challenge in improving healthcare quality: the problems that experts see at the population level (excess cancer screening in frail elders) are experienced very differently by the clinicians and patients on the ground...Although expert guidelines and advice do have an important role to play, it’s usually not nearly enough to counter the habits and attitudes of the people in the trenches.

This is an interesting tale of creating a smartphone app to put evidence-based information in physicians' hands at the point of care (something I've tried to do myself). What I think Dr Kernisan is trying to get at in the quote above is that it's very difficult to persuade experienced clinicians to not rely on their training and experience, to instead use a digital tool for clinical decision support. One reason for this, I believe, is that we overestimate our performance. Decision-support tools are created because there is some population-based evidence for poor performance on some measure (at least that's the general idea). To make their usefulness 'real' for ordinary physicians, they need to see their own performance on those measures and the clinical impact of better performance.