Recent technological advances suggest that smartphone photography may be a promising method for direct parent-to-clinician telemedicine, specifically for diagnosing skin conditions in pediatric patients. However, little information currently exists about diagnoses made via smartphone photographs.
To test this potential option further, Daniel M. O’Connor, MD, and colleagues assessed 40 patient-parent dyads at a pediatric dermatology clinic and the Children’s Hospital of Philadelphia from March 1, 2016, to September 30, 2016. In particular, the researchers assessed concordance between diagnoses made by an independent pediatric dermatologist via in-person examination vs diagnoses based solely on parent-provided photographs.
Furthermore, half of the patient-parent dyads were randomly assigned for a secondary analysis (intervention group), which provided parents with instructions on how to best take photographs with smartphones.
The main outcome was defined as concordance between in-person and photograph-based diagnoses in the intervention group vs controls, as quantified by Cohen κ.
Results of the study showed that overall concordance between the 2 methods of diagnosis was 83% (κ = 0.81). In a subgroup of 37 participants with photographs that were considered high-quality, diagnostic concordance was 89% (κ = 0.88).
The researchers did not observe any statistically significant effect of photography instructions on diagnostic concordance (85% in intervention group vs 80% in controls). Appropriate follow-up was suggested in cases of diagnostic disagreement.
“Parent-operated smartphone photography can accurately be used as a method to provide pediatric dermatologic care,” the researchers concluded.
O’Connor DM, Jew OS, Perman MJ, Castelo-Soccio LA, Winston FK, McMahon PJ. Diagnostic accuracy of pediatric teledermatology using parent-submitted photographs: a randomized control trial [Published online November 15, 2017]. JAMA Dermatol. doi:10.1001/jamadermatol.2017.4280.