Pattern Recognition: Stick with the “Ugly Duckling” Rule?

By Guest Blogger Abrar Qureshi, MD, MPH
Brigham and Women’s Hospital, Boston, MA

In their recent study, Wazaefi at al asked dermatologists and non-dermatologists to cluster images of pigmented lesions from a series of patients and found that dermatologists did a better job at pattern recognition.  Boy, does that makes all dermatologists feel good!  We should be able to spot the difference between a black-capped chickadee and a white breasted nut-hatch in flight!  Maybe training our residents to recognize nature’s patterns outside the clinic will further embellish their clinical skills, with outings such as ‘astronomy night’ or ‘bird watching in the marshes’.

White breasted nut hatch by Mdf, via a creative commons attribution share-alike license on Wikipedia
White breasted nut hatch by Mdf, via a creative commons attribution share-alike license on Wikipedia

There are more layers to all this talk of ‘patterns’ – for example, are we looking too closely at pigmented lesions nowadays?  In the era of cross-polarization and spectroscopic gizmos, fortunately there are still some dermatologists who walk around clinic with a jeweler’s loupe in-hand.  Even more basic, there are other clinicians who use naked-eye inspections to examine their patients:  no loupes, forget fancy dermoscopes.  Is there a rationale to this variation among dermatologists when faced with a questionable pigmented lesion?  Are we looking for the ugly duckling through a scope?  Does the approach matter when seeing the whole patient versus looking at images of specific pigmented lesions?  Could the results of this study be different if dermatologists and non-dermatologists were asked to actually examine patients rather than work with images?



Wazaefi Y, Gaudy-Marqueste C, Avril M-F et al.  (2013) Evidence of a Limited Intra-Individual Diversity of Nevi: Intuitive Perception of Dominant Clusters Is a Crucial Step in the Analysis of Nevi by Dermatologists.  J Invest Dermatol doi:10.1038/jid.2013.183

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s