Similarly, ChatGPT 5.1 Thinking-generated median absolute RQS was significantly lower than that of the Main Reader ( p = 0.026) and Secondary Reader A ( p = 0.019), whereas the difference compared with Secondary Reader B did not reach statistical significance ( p = 0.094) (Table 3 ).
← all excerpts
Methodological quality of cardiac CT and MRI radiomics studies assessed using METRICS and RQS by human readers and ChatGPT 5.1 Thinking.
1
0.0940
0.0940