Cervical Precancer Detection Using a Multivariate Statistical Algorithm Based on Laser‐Induced Fluorescence Spectra at Multiple Excitation Wavelengths

This is the authors' abstract. We don't add key points for this paper.

A portable fluorimeter was developed and utilized to acquire fluorescence spectra from 381 cervical sites in 95 patients at 337, 380 and 460 nm excitation immediately prior to colposcopy. A multivariate statistical algorithm was used to extract clinically useful information from tissue spectra acquired in vivo. Two full-parameter algorithms were developed using tissue fluorescence emission spectra at all three excitation wavelengths (161 excitation-emission wavelength pairs) for cervical precancer (squamous intraepithelial lesion [SIL]) detection: a screening algorithm that discriminates between SIL and non-SIL with a sensitivity of 82 +/- 1.4% and specificity of 68 +/- 0.0%, and a diagnostic algorithm that differentiates high-grade SIL from non-high-grade SIL with a sensitivity and specificity of 79 +/- 2% and 78 +/- 6%, respectively. Multivariate statistical analysis was also employed to reduce the number of fluorescence excitation-emission wavelength pairs needed to redevelop algorithms that demonstrate a minimum decrease in classification accuracy. Two reduced-parameter algorithms that employ fluorescence intensities at only 15 excitation-emission wavelength pairs were developed: the screening algorithm differentiates SIL from non-SIL with a sensitivity of 84 +/- 1.5% and specificity of 65 +/- 2% and the diagnostic algorithm discriminates high-grade SIL from non-high-grade SIL with a sensitivity and specificity of 78 +/- 0.7% and 74 +/- 2%, respectively. Both the full-parameter and reduced-parameter screening algorithms discriminate between SIL and non-SIL with a similar specificity (+/-5%) and a substantially improved sensitivity relative to Pap smear screening. A comparison of the full-parameter and reduced-parameter diagnostic algorithms to colposcopy in expert hands indicates that all three have a very similar sensitivity and specificity for differentiating high-grade SIL from non-high-grade SIL.