In this course we will discuss the principles of interpreting diagnostic test results and evaluating diagnostic tests.
We will first review basic concepts such as sensitivity, specificity, predictive probabilities, likelihood ratios, Bayes theorem and ROC curves. Then we will discuss possible forms of bias that can influence studies evaluating diagnostic test performance and a method to correct for verification bias. Diagnostic meta-analysis and summary ROC curves will be discussed.
Next we will focus on modeling issues in using decision analysis to model diagnostic decisions. Conditional independence and multivariable prediction rules will be explained. The week will end with determining the optimal operating point on the ROC curve and estimating target values for new diagnostic technology.
To get credit for the course you will need to perform assignments. We will do the assignments in part during class so bring a laptop. Expect to spend at least 2 hours per day finishing the assignments after class.
Objective
- Understanding the principles of interpreting diagnostic test results and evaluating diagnostic tests.
Required book: Hunink MGM, Glasziou PP, Siegel JE, Weeks JC, Pliskin JS, Elstein AS, Weinstein MC. Decision Making in Health and Medicine: Integrating Evidence and Values. Cambridge University Press, Cambridge, UK, 2001.
Books are on sale during the Erasmus Winter Programme.