Abstract

Evaluating the performance of a binary diagnostic test, including artificial intelligence classification algorithms, involves measuring sensitivity, specificity, positive predictive value, and negative predictive value. Particularly when comparing the performance of two diagnostic tests applied on the same set of patients, these metrics are crucial for identifying the more accurate test. However, comparing predictive values presents statistical challenges because their denominators depend on the test outcomes, unlike the comparison of sensitivities and specificities. This paper reviews existing methods for comparing predictive values and proposes using the permutation test. The permutation test is an intuitive, non-parametric method suitable for datasets with small sample sizes. We demonstrate each method using a dataset from MRI and combined modality of mammography and ultrasound in diagnosing breast cancer.