Assessment of automated primary screening on PAPNET of cervical smears in the PRISMATIC trial

Background New technology for computer-assisted screening of cervical smear s that uses neural networks could potentially decrease numbers of screening errors and improve productivity. We assessed an interactive automated syst em (PAPNET) for primary screening of cervical smears. Methods In January, 1997, the National Health Service research and developm ent programme sponsored a multicentre trial to investigate the use of PAPNE T for classification of routine cervical smears as negative or needing furt her microscopic review, compared with conventional primary screening. The s tudy complied with international standards for assessment of automated cerv ical screening systems. 21 700 smears were analysed by the two methods and were classified as inadequate, negative, mild, moderate, or severe dyskaryo sis, invasion, glandular neoplasia, and borderline nuclear changes. 2906 ab normal smears and 298 negative smears were sent for independent cytological review (gold standard). We calculated sensitivity and specificity relative to the findings of the independent review. Findings Agreement of 89.8% between the two methods was shown for all class ifications of smears that were adequate for reporting, The sensitivity was similar for correctly identified abnormal smears on PAPNET-assisted (82%) a nd conventional screening (83%). PAPNET-assisted screening showed significa ntly better specificity (77%) than conventional screening (42%) for identif ication of negative smears, The total mean time for screening and reporting for conventional screening was 10.4 min per smear, and for PAPNET-assisted screening was 3.9 min. Interpretation Use of PAPNET-assisted screening could increase quality and productivity. We recommend carefully organised and controlled development p rojects for the introduction of PAPNET-assisted primary screening of cervic al smears.