INTERACTIVE NEURAL NETWORK-ASSISTED SCREENING - AN ECONOMIC-ASSESSMENT

OBJECTIVE: To apply clinical effectiveness estimates of interactive, n eural network-assisted (INNA) screening to economic cervical cancer sc reening models to assess the economic impact of using this technology. STUDY DESIGN: Estimates of the sensitivity of INNA screening were dra wn from a recently completed comprehensive synthesis of the INNA liter ature and applied to the Computer Model for Designing CANcer ConTROL P rograms-based Cervical Cancer Screen economic model. The economic anal ysis was conducted from a modified payer perspective using costs borne by payers combined with patient cancer were updated to 1997 values us ing the medical care component of the Consumer Price Index. The model was run for a cohort of women starting at age 20 and screened on a tri ennial schedule through age 75. RESULTS: In the primary analysis (sens itivity of unassisted manual examination assumed to be 85%), the ratio s found in this investigation varied from approximately $35,000 to $80 ,000 per life year saved, with the preponderance of ratios <$50,000 pe r life year saved. These results were sensitive to estimates of sensit ivity of unassisted manual screening but not to estimates of treatment costs. CONCLUSION: This investigation applied accuracy data on INNA r escreening to a model of the cost-effectiveness of cervical cancer scr eening. The results support the use of INNA rescreening as an appropri ate expenditure of resources to identify missed cases of cervical epit helial abnormalities and potential cervical cancer.