Dermatology pictures posted on some social networks, like Twitter and MedPics, could help in the diagnosis of dermatologic lesions in teledermatology as well as standard clinical practice, according to study findings published in Annals of Family Medicine.

In this retrospective, observational study, a total of 270 health professionals evaluated 60 images on Twitter and MedPics published by general practitioners in 2016. These health professionals were asked to diagnose the disorder based on the images, and these diagnoses were compared with diagnoses obtained from telemedicine in standard teledermatology services.

The investigators examined the agreement between the number of correct diagnoses obtained using telemedicine and standard teledermatology services with diagnoses made by an expert committee.

Continue Reading

According to the experts, the primary diagnoses included purpura (8.3%), eczema (6.7%), mycosis (6.7%), and viral infections (6.7%). There was a moderate diagnostic agreement found between telemedicine on social networks and standard teledermatology services for the entire image set (κ=0.55; 95% CI, 0.42-0.68). Agreement was considered good for images with dermatologist responses (κ=0.63; 95% CI, 0.45-0.85).

For all images, there was no statistically significant difference between telemedicine on social networks and standard teledermatology services in terms of the number of correct diagnoses (60% vs 55%; P =.28). In contrast, there was a higher number of correct diagnoses on social networks per dermatologists’ responses (65% vs 55%; P <.01).

Limitations of this study included its retrospective nature as well as the lack of follow up and direct monitoring of patients.

The investigators agreed that the findings from “this study show that some social networks could provide good diagnoses for dermatological lesions in general practice.”


Serhrouchni S, Malmartel A. Diagnostic agreement between telemedicine on social networks and teledermatology centers. Ann Fam Med. 2021;19(1):24-29. doi:10.1370/afm.2608