The goal of this session is to to learn how to define and calculate likelihood ratios, and use them to calculate and interpret pretest/posttest probabilities.
Likelihood ratios are used to assess how good a diagnostic test is and to help in selecting appropriate diagnostic test(s).
- LRs have advantages over PPV and NPV because they are less likely to change with the prevalence of the disorder.
- LRs can be calculated for several levels of the symptom/sign or test.
- LRs can be used to calculate posttest probability for a disease of interest.
Bayesian statistics is a field of statistics in which prior beliefs are quantified as pretest probabilities and combined with the LR to calculate posttest probabilities.
- Allow interpretation of clinical screening or diagnostic tests within their clinical context.
10 июл 2024