OBJECTIVE: To assess the PAPNET System for prescreening triage of cerv
ical smears. STUDY DESIGN: We prospectively prescreened 5,170 consecut
ive cervicovaginal smears with the PAPNET System. The slides were then
manually screened by cytotechnologists blinded to the PAPNET diagnose
s. Cases identified as abnormal by either PAPNET or manual screening w
ere reviewed by a cytopathologist. The PAPNET and manual diagnoses wer
e correlated. RESULTS: Diagnostic concordance between PAPNET and manua
l screening was seen in 4,340 (84%) of the cases (3,167 negative, 1,03
8 abnormal and 135 unsatisfactory). Noncorrelation between PAPNET and
manual diagnosis occurred in 794 cases (543 abnormal by PAPNET and neg
ative manually, 228 negative by PAPNET and abnormal manually, 8 abnorm
al by PAPNET and unsatisfactory manually, 29 unsatisfactory by PAPNET
and negative manually, 7 negative by PAPNET and unsatisfactory manuall
y). The diagnostic sensitivity of the PAPNET System was 82%, diagnosti
c specificity 85%, predictive value of a positive test 66% and predict
ive value of a negative test 93.4%. The false negative fraction of PAP
NET was 6.4% for low grade squamous intraepithelial lesion and above.
CONCLUSION: PAPNET performed effectively for prescreening triage, incr
easing the accuracy of screening and reducing the screening time.