Assessing Accuracy of Population Screening Using Longitudinal Marker

• Activity Number: 92
• Type: Invited
• Date/Time: Sunday, August 4, 2013 : 8:30 PM to 10:30 PM
• Sponsor: Biometrics Section
• Author(s): Paramita Saha-Chaudhuri*+
• Companies: Duke University
• Keywords: ROC ; survival ; prediction ; longitudinal ; screening

Abstract

The World Health Organization defines screening as the presumptive identification of unrecognized disease or defects by means of tests, examinations or other procedures that can be applied rapidly. With the progress of medicine in recent decades, there is now considerable focus on early detection of disease via population screening, giving the patient more treatment options if the disease is found by screening and consequently a better prognosis outlook. Both the benefits and harms of screening are well-documented. There is considerable debate as to whether early screening for diseases, such as cancer and cardiovascular disease, is useful, has a positive trade-off and has a broad public health impact. Once a screening protocol is introduced in practice, there is much controversy as to whether it is possible to forgo screening at all. Given that a screening test is introduced, it is imperative to assess the accuracy of the screening protocol. We introduce a new approach, Screening ROC, that can be used to assess the accuracy of a screening protocol. We demonstrate the approach with simulated and real dataset.