Have you ever wondered how medical diagnoses are quantified? What value in a diagnostic test distinguishes disease from health? How is the accuracy of a diagnostic test assessed? In my MAT 380 talk, I will explain the concept, methods, and benefits of using ROC (Receiver Operating Characteristic) Curves to interpret the results of diagnostic tests. ROC Curves graph the sensitivity of a test against the false positive rate to display the accuracy of test outcomes. Through analyzing the area under the curve and finding an optimal cut-off value, ROC curves can be used to dichotomize the presence and absence of disease, offering important medical applications. Come to my talk next Wednesday, March 12 to learn more about ROC curves and the intersection between math and medicine!
Distinguishing Diagnosis: An Introduction to ROC Curve Analysis
by Carlie Porter | Mar 5, 2025 | Uncategorized | 6 comments
6 Comments
Submit a Comment Cancel reply
You must be logged in to post a comment.
Carlie your talk sounds very interesting! I have actually wondered how the accuracy of a diagnostic test is assessed, and I cannot wait to have that question answered when I come to your seminar talk!
Carlie, I am very excited for your talk! As a Pre-Med, this topic is very interesting to me. I can’t wait to learn more about the math behind diagnostic tests in healthcare.
Your talk was great and it was very interesting to hear about the ROC curve and what the confusion matrix was.
It is interesting to see how simple calculus can be used to find optimal cut-off values that have such an important real world application!
I thought your talk was very interesting and very useful. I think it’s so cool that math and science can be intertwined and how you can use math to verify science.
I didn’t realize how much variability there was in the false positivity in medical tests. You gave a very thorough talk.