Estimating the capacity for improvement in risk prediction with a marker.
The Papanicolaou smear (Pap test), used for the detection and prevention of neoplastic lesions of the cervix, is known to have both false negative and false positive results. Proper handling of the diagnostic uncertainty resulting from these errors demands quantification of flaws. Traditionally, sensitivity, specificity and predictive values are used for that aim. In this study another approach is advocated, namely the use of the likelihood ratio. For cervical cytology this ratio is the quotient of the probability of a Pap class within the diseased population to the probability of that same Pap class within the non-diseased group. This approach enables the characterization of each Pap class separately, and is therefore much better for clinical interpretation of the result. It is also a superior approach for quality assessment.