Table 1 List of classification targets and abbreviations, and the proportion in the positive class. Targets with ^a indicate continuous variables that were binarized by thresholding on the median cohort value – note that the % positive is expected to be 50%, but the presence of repeated values in these targets means this is not exact. Overall stage was binarized as stage 1 or 2 vs stage 3 or 4. The eleven targets in bold font have their predictive models explored in detail in the Results section and Discussion

From: Interpretability of radiomics models is improved when using feature group selection strategies for predicting molecular and clinical targets in clear-cell renal cell carcinoma: insights from the TRACERx Renal study