Back

MRMCsamplesize: An R Package for Estimating Sample Sizes for Multi-Reader Multi-Case Studies

Robert, D.; Sathyamurthy, S.; Putha, P.

2023-09-25 radiology and imaging
10.1101/2023.09.25.23296069 medRxiv
Show abstract

Multi-Reader Multi-Case (MRMC) studies are typically used to evaluate improvement in diagnostic accuracy of readers (diagnosticians) when they are assisted by a computer-assisted device (CAD) such as, but not limited to, those based on Artificial Intelligence (AI) algorithms. Statistical analysis of MRMC study data is not trivial and these studies can consume a lot of resources. Optimal planning is crucial and estimation of sample size is a significant step during the study planning phase. MRMC sample size estimations require many parameter assumptions and without pilot data this is generally not intuitive. MRMCsamplesize package can help researchers to estimate sample sizes for an MRMC study in the absence of any pilot data. The program outputs the number of cases required for a given number of readers. The package can also estimate sample sizes for scenarios where intra-cluster correlation (ICC) needs to be adjusted.

Matching journals

The top 9 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.