Lg. Koss et al., SIGNIFICANT REDUCTION IN THE RATE OF FALSE-NEGATIVE CERVICAL SMEARS WITH NEURAL-NETWORK-BASED TECHNOLOGY (PAPNET TESTING SYSTEM), Human pathology, 28(10), 1997, pp. 1196-1203
False-negative cervical Pap smears may lead to disability or death fro
m carcinoma of the uterine cervix. New computer technology has led to
the development of an interactive, neural network-based vision instrum
ent to increase the accuracy of cervical smear screening. The instrume
nt belongs to a new class of medical devices designed to provide compu
ter-aided diagnosis (CADx). To test the instrument's performance, 487
archival negative smears (index smears) from 228 ,women,with biopsy-do
cumented high-grade precancerous lesions or invasive cervical carcinom
a (index women),were retrieved from the files of 10 participating labo
ratories that were using federally mandated quality assurance procedur
es. Samples of sequential negative smears (total 9,666) were retrieved
as controls. The instrument was used to identify evidence of missed c
ytological abnormalities, including atypical squamous or glandular cel
ls of undetermined significance (ASCUS, AGUS), low-grade or high-grade
squamous intraepithelial lesions (LSIL, HSIL) and carcinoma. Using th
e instrument, 98 false-negative index smears were identified in 72 of
the 228 index women (31.6%, 95% confidence interval [CI]: 25% to 38%).
Disregarding the debatable categories of ASCUS or AGUS, there were 44
women whose false-negative smears disclosed squamous intraepithelial
lesions (SIL) or carcinoma (19.3%; 95% CI: 14.2% to 24.4%). Unexpected
ly, SILs were also identified in 127 of 9,666 control negative smears
(1.3%; 95% CI: 1.1% to 1.5%). Compared with historical performance dat
a from several participating laboratories, the instrument increased th
e detection rate of SILs in control smears by 25% and increased the yi
eld of quality control rescreening 5.1 times (P < 0.0001). These data
provide evidence that conventional screening and quality control rescr
eening of cervical smears fail to identify a substantial number of abn
ormalities. A significant improvement in performance of screening of c
ervical smears could be achieved with the use of the instrument descri
bed in this report. Copyright (C) 1997 by W.B. Saunders Company.