Fig. 4
The models were presented as logistic regression equations in this Excel document, it will calculate the predictor (lp) first. According to logit transformation, \(\mathrm{lp}=\mathrm{logit}\left(\mathrm{p}\right)=\log \left(\frac{\mathrm{p}}{1-\mathrm{p}}\right)\), so \(\mathrm{p}=\frac{\exp \left(\mathrm{lp}\right)}{1+\exp \left(\mathrm{lp}\right)}\), the p value will be displayed in the purple cell. *p=The prediction of probability of Mets.