P. Barbini et al., INSTRUMENTAL MEASUREMENT OF SKIN COLOR AND SKIN TYPE AS RISK-FACTORS FOR MELANOMA - A STATISTICAL CLASSIFICATION PROCEDURE, Melanoma research, 8(5), 1998, pp. 439-447
Citations number
43
Categorie Soggetti
Oncology,"Dermatology & Venereal Diseases","Medicine, Research & Experimental
A statistical procedure to evaluate melanoma risk in Caucasian subject
s on the basis of colorimetric measurement of skin colour and Fitzpatr
ick phototype is described. One hundred and sixty melanoma patients an
d 546 randomized healthy subjects of similar age, sex and place of ori
gin were examined in the same period for skin colour using a tristimul
us colorimeter and for Fitzpatrick phototype. A clinical score for cla
ssification purposes was obtained by statistical discriminant analysis
with multivariate data transformation and dimension reduction techniq
ues. A Fisher linear classifier was chosen for its simplicity and robu
stness in correctly predicting melanoma risk in new subjects. The clas
sification rule was designed to avoid classifying subjects at high ris
k for melanoma as low risk, i.e. to give a negligible number of false
negatives at the expense of more false positives. The procedure is obj
ective and readily adapted to different clinical requirements. This is
only a preliminary study but it is hoped that by performing more comp
lex statistical analyses, e.g. neural networks, and adding other param
eters (proven risk factors such as number of naevi) the performance wi
ll be further improved. (C) 1998 Lippincott Williams & Wilkins.