To the Editor.
—At the Second Nordic Workshop on Evidence-Based Health Care in Oslo, Norway, in June 1997, our group worked on the JAMA article on appendicitis.1 I tried to calculate the positive LR by using the numbers provided in Table 3 in the formula2 (sensitivity/[1-specificity]) and calculated, for example, a positive LR of 1.59 vs 3.76 in the article for rigidity and a LR positive of 1.72 vs 7.31 to 8.46 in the article for right lower quadrant pain. The numbers appear to be wrong.The authors alternatively could have presented the findings as a summary of receiver operating characteristic curves, which might have been easier to interpret.
Klovning A. Likelihood Ratios to Determine 'Does This Patient Have Appendicitis?': Comment and Clarification. JAMA. 1997;278(10):819. doi:10.1001/jama.1997.03550100045027