Tips for Teachers of Evidence-Based Medicine: Understanding Odds Ratios and Their Relationship to Risk Ratios
Bibliographic record
Abstract
Odds ratios (OR) commonly appear in the medical literature summarizing the comparative effects of interventions and exposures in observational studies, randomized trials, and meta-analyses. Clinicians find it difficult to understand odds and odds ratios as measures of association, although they may be comfortable with the parallel concepts of risk and risk ratios. Probably, no one (with the possible exception of certain statisticians) intuitively understands a ratio of odds.1,2 Nevertheless, odds ratios are frequently encountered in research reports as the principal measure of association.3–5 Odds and risk constitute parallel statistical metrics for measuring frequency and ratios of frequency. Their relationship might be compared to the use of different scales such as Fahrenheit and Centigrade to report absolute values of and relationships between different temperatures. Until recently, the choices between the odds and risk metrics were determined largely on the basis of their statistical properties rather than on the basis of their usefulness as means of communicating the results of research to clinicians and their patients. In a previous article, we have demonstrated approaches to helping teachers and learners to master the concepts of risk, relative risk, and risk reduction as the preferred framework for the purposes of clinical application.6 The content of that article may be regarded as pre-requisite knowledge for the purposes of the present discussion and demonstration. This article presents an approach in helping clinician understand what odds and odds ratios mean and when can they numerically substitute risk and risk ratio for odds and odds ratios. Odds ratios may be chosen as the measure of association by authors of studies conforming to a variety of designs, only some of which mandate their use in preference to risk ratios. These include randomized trials, systematic reviews, case control studies, and studies involving the use of logistical regression. In teaching clinical learners who are not familiar with this measure of outcome, we have found it important to concentrate initially on the conceptual understanding of odds and odds ratios and to avoid combining this with discussion of study design issues. We have correspondingly not included discussion of these issues in this article. We will present interactive approaches that educators have developed to overcome ‘stumbling blocks’ among learners. To help the reader envision these approaches, we present sequenced advice for teachers and characteristic learner responses. The “tips” in this article are adapted from approaches developed by educators with experience in teaching evidence-based medicine skills to clinicians. We present a full description of the development of the tips in this series and pertinent background information elsewhere.7 Each tip includes section on “when to use the tip,” “The script,” the “bottom line,” and a “summary card.” The first tip helps learners to understand the relationship between odds and probability (risk) and to define circumstances when odds and risks are similar. The second tip builds on the first and helps learners understand what an odds ratio is and when it is similar to the risk ratio.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.083 | 0.162 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.011 | 0.003 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; both teacher heads agree on what is shown here.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".