TY - JOUR
T1 - Performance estimation of diagnostic tests for cervical precancer based on fluorescence spectroscopy
T2 - effects of tissue type sample size population and signal-to-noise ratio
AU - Utzinger, Urs
AU - Vanessa Trujillo, E.
AU - Neely Atkinson, E.
AU - Mitchell, Michèle F.
AU - Cantor, Scott B.
AU - Richards-Kortum, Rebecca
N1 - Funding Information:
Manuscript received August 21, 1998; revised April 29, 1999. This work was supported by the Whitaker Foundation under a Cost-Reducing Health Care Technology Grant and by the National Institutes of Health (NIH) under Grant CA72650. Asterisk indicates corresponding author. U. Utzinger and E. V. Trujillo are with the Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX 78712 USA. E. N. Atkinson is with the Department of Biomathematics, University of Texas M. D. Anderson Cancer Center, Houston, TX 77030 USA. M. F. Mitchell is with the Department of Gynecologic Oncology, University of Texas M. D. Anderson Cancer Center, Houston, TX 77030 USA. S. B. Cantor is with the Department of Medical Specialties, University of Texas M. D. Anderson Cancer Center, Houston, TX 77030 USA. *R. Richards-Kortum is with the Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX 78712 USA (e-mail: [email protected]). Publisher Item Identifier S 0018-9294(99)07638-7.
PY - 1999
Y1 - 1999
N2 - Fluorescence spectroscopy may provide a costeffective tool to improve precancer detection. We describe a method to estimate the diagnostic performance of classifiers based on optical spectra and to explore the sensitivity of these estimations to factors affecting spectrometer cost. Fluorescence spectra 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 multiple misclassification costs. We explored the sensitivity of classifier performance to variations in tissue type sample size tested population signal to noise ratio (SNR) and number of excitation and emission wavelengths. Sensitivity and specificity could be evaluated within ±7%. Minimal decrease in diagnostic performance is observed as SNR is reduced to 15 the number of excitationemission wavelength combinations is reduced to 15 or the number of excitation wavelengths is reduced to one. Diagnostic performance is compromised when ultraviolet excitation is not included. Significant spectrometer cost reduction is possible without compromising diagnostic ability. Decision-analytic methods can be used to rate designs based on incremental cost-effectiveness.
AB - Fluorescence spectroscopy may provide a costeffective tool to improve precancer detection. We describe a method to estimate the diagnostic performance of classifiers based on optical spectra and to explore the sensitivity of these estimations to factors affecting spectrometer cost. Fluorescence spectra 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 multiple misclassification costs. We explored the sensitivity of classifier performance to variations in tissue type sample size tested population signal to noise ratio (SNR) and number of excitation and emission wavelengths. Sensitivity and specificity could be evaluated within ±7%. Minimal decrease in diagnostic performance is observed as SNR is reduced to 15 the number of excitationemission wavelength combinations is reduced to 15 or the number of excitation wavelengths is reduced to one. Diagnostic performance is compromised when ultraviolet excitation is not included. Significant spectrometer cost reduction is possible without compromising diagnostic ability. Decision-analytic methods can be used to rate designs based on incremental cost-effectiveness.
KW - Cervix
KW - Cost-effectiveness analysis
KW - Diagnosis
KW - Fluorescence spectroscopy
KW - Precancer
KW - Signal-to-noise ratio (SNR)
UR - http://www.scopus.com/inward/record.url?scp=0032711173&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0032711173&partnerID=8YFLogxK
U2 - 10.1109/10.797989
DO - 10.1109/10.797989
M3 - Article
C2 - 10582414
AN - SCOPUS:0032711173
SN - 0018-9294
VL - 46
SP - 1293
EP - 1303
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
IS - 11
ER -