Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture covers the concepts of Sensitivity and Specificity in diagnostic tests with binary classification outputs, such as pregnancy tests and biomarker tests. Sensitivity is the probability of providing a correct answer for positive samples, while Specificity is for negative samples. The lecture explains how these parameters depend on the biomarker measured and the threshold concentration chosen. It also introduces the Receiver Operating Characteristic (ROC) curve, which is used to compare diagnostic tests based on sensitivity and specificity. The importance of Precision in determining the probability of having a disease given a positive test result is also discussed, considering the prevalence of the disease in the population.