HairComb Algorithm Quantifies Hair Loss in All Forms of Alopecia
Algorithm is 92 percent accurate and predicted scores with errors comparable to annotators
By Dermsquared Editorial Team | December 14, 2022
An algorithm that quantifies percentage hair loss can be applied to all forms of alopecia, according to a study published online Dec. 14 in JAMA Dermatology .
Cameron Gudobba, from the University of Pennsylvania Perelman School of Medicine in Philadelphia, and colleagues created a new algorithmic quantification system (HairComb) for all hair loss using computational imaging analysis and algorithm design in a multicenter study. Images were collected from 2015 to 2021 and were analyzed from 2019 to 2021.
A total of 404 participants were used for designing and validating HairComb. Scoring systems correlation analysis was conducted for 250 participants (75 with androgenetic alopecia, 66 with alopecia areata, 50 with central centrifugal cicatricial alopecia, 27 other alopecia diagnoses, and 32 unaffected scalps without alopecia). The researchers identified strong correlations for scoring systems with underlying percentage hair loss, with coefficient of determination R 2 values of 0.793 and 0.804 for log of percentage hair loss. Overall, accuracy of 92 percent, 5 percent regression error, 7 percent hair loss difference, and predicted scores with errors comparable to annotators were achieved using HairComb.
"In the future, we hope to make progress toward a more accessible system for scoring alopecia by making our online interface Trichy publicly available, especially to populations with limited access to a dermatologist, providing anyone with a method to quantify and track alopecia in a reliable and standardized way," the authors write.
Two authors disclosed financial ties to the pharmaceutical and hair care product industries.