Multivariate analysis of laryngeal fluorescence spectra recorded in vivo

The potential of using various multivariate analysis methods for classification of fluorescence spectra acquired in vivo from laryngeal tissues in Patients was investigated.

Autofluorescence spectra were measured on 29 normal tissue sites and 25 laryngeal lesions using 337-nm excitation. Four different multivariate analysis schemes were applied. Laryngeal fluorescence spectra from patients who had been administered delta-aminolevulinic acid (ALA) were obtained using 405-nm excitation and were classified using partial least squares discriminant analysis (PLS-DA).

For autofluorescence spectra, logistic regression based on principal component analysis (PCA) or PLS, or PLS-DA all resulted in sensitivities and specificities around 90% for lesion vs. normal. Using ALA and 405-nm excitation gave a sensitivity of 100% and a specificity of 69%.

Multivariate analysis of fluorescence spectra could allow classification of laryngeal lesions in vivo with high sensitivity and specificity. PLS performs at least as well as PCA, and PLS-DA performs as well as logistic regression techniques on these data.