Performance estimation of diagnostic tests for cervical precancer based onfluorescence spectroscopy: Effects of tissue type, sample size, population, and signal-to-noise ratio

Fluorescence spectroscopy may provide a cost-effective tool to improve prec ancer detection, We describe a method to estimate the diagnostic performanc e of classifiers based on optical spectra, and to explore the sensitivity o f these estimations to factors affecting spectrometer cost. Fluorescence sp ectra were obtained at three excitation wavelengths in 92 patients with an abnormal Papanicolaou smear and 51 patients with no history of an abnormal smear. Bayesian classification rules were developed and evaluated at multip le misclassification costs. We explored the sensitivity of classifier perfo rmance to variations in tissue type, sample size, tested population, signal to noise ratio (SNR), and number of excitation and emission wavelengths, S ensitivity and specificity could be evaluated within +/-7%, Minimal decreas e in diagnostic performance is observed as SNR is reduced to 15, the number of excitation-emission wavelength combinations is reduced to 15 or the num ber of excitation wavelengths is reduced to one. Diagnostic performance is compromised when ultraviolet excitation is not included, Significant spectr ometer cost reduction is possible without compromising diagnostic ability. Decision-analytic methods can be used to rate designs based on incremental cost-effectiveness.