Reliable facial color analysis using a digital camera and its relationship with pathological patterns: A pilot study

Abstract

IntroductionAccording to East Asian medicine (EAM) theory, facial color serves as a diagnostic clue to pathological conditions. The aim of this pilot study was to examine the relationship between facial color parameters and EAM pathological patterns. MethodsA total of 23 normal subjects participated in our study. The subjects were asked to complete Yin deficiency, Phlegm, Cold-Heat, and Food Retention Questionnaires. After taking digital photographs of the subjects’ faces, L* (luminance), a* (red-green balance), and b* (yellow-blue balance) values of the five facial regions (forehead, left and right cheeks, nose, and chin) were calculated. We randomly selected 10 samples and conducted intra- and inter-rater reliability tests. Finally, we examined the relationship between L*, a*, and b* values and the four pattern questionnaires scores. ResultsIntra-class correlation coefficients of intra- and inter-rater reliability ranged from 0.640 to 0.994. Cold pattern scores had a positive correlation with L* values and a negative correlation with a* values of the left and right cheeks and nose regions (r=0.573, 0.565, and 0.534), and had a negative correlation with a* values of the forehead and nose regions (r=−0.447, −0.576). Heat pattern scores had a negative correlation with the left and right cheeks regions (r=−0.466, −0.440). Yin deficiency and Food Retention Questionnaire scores had a negative correlation with b* values on the left cheek region (r=−0.415, −0.523). ConclusionsWe conclude that facial color analysis using L*a*b* values is reliable, and facial luminance and color are indicative of EAM pathological patterns.