Skip to main content
. 2023 Aug 3;4(9):100802. doi: 10.1016/j.patter.2023.100802

Table 7.

RadCliQ scores of models that jointly generate findings and impression sections, including R2Gen, WCL, CvT2DistilGPT2, and the random retrieval baseline model

RadCliQ
R2Gen 1.552
WCL 1.511
CvT2DistilGPT2 1.463
Random retrieval of jointly the findings and impression 1.726

Lower is better. The 95% confidence interval and range of metric scores are available in Table S7.

indicates the best-performing model.