Conference Program

Return to main conference page

All Times EDT

Wednesday, September 21
Wed, Sep 21, 11:30 AM - 1:00 PM
Various Rooms
Roundtable Discussions

RL43: Diagnostic Tests' Accuracy Goals (303628)

Kristen Meier, Illumina 
*Dandan Xu, US Food and Drug Administration 

Keywords: sensitivity, specificity, likelihood ratio, positive predictive value, negative predictive value, medical decision making

Pennello (2021 Classification accuracy goals for diagnostic tests based on risk stratification, Biostatistics & Epidemiology, 5:2, 149-168, DOI: 10.1080/24709360.2021.1878406) developed a framework for setting classification accuracy goals that confer clinical usefulness of a diagnostic test. This framework has been used to evaluate diagnostic tests in regulatory submissions (https://www.accessdata.fda.gov/cdrh_docs/pdf16/P160037B.pdf). Developers and manufacturers may benefit from this framework when setting classification accuracy goals at the design stage of a validation study for an investigational diagnostic test. In this roundtable we will highlight key ideas from this paper and encourage dialogue on the use of this approach in practice.