Table 3:

TADPOLE performance metric formulas and definitions for the terms.

Formula	Definitions
$\begin{array}{c}mAUC=\\ \frac{2}{L(L-1)}{\sum }_{i=2}^L{\sum }_{j=1}^i\widehat{A}(c_i,c_j)\end{array}$	ni, nj – {number of points from class i and j. Sij – {the sum of the ranks of the class i test points, after ranking all the class i and j data points in increasing likelihood of belonging to class i, L – number of data points
$\begin{array}{c}BCA=\\ \frac{1}{2L}{\sum }_{i=1}^L\left[\frac{TP}{TP+FN}+\frac{TN}{TN+FP}\right]\end{array}$	TPi, FPi, TNi, FNi the number of true positives, false positives, true negatives and false negatives for class i L number of data points
$MAE=\frac{1}{N}{\sum }_{i=1}^N|{\tilde{M}}_i-M_i|$	Mi is the actual value in individual i in future data. ${\tilde{M}}_i$ is the participant’s best guess at Mi and N is the number of data points
$WES=\frac{{\Sigma }_{i=1}^N{\tilde{C}}_i\left|{\tilde{M}}_i-M_i\right|}{\sum _{i=1}^N{\tilde{C}}_i}$	Mi, ${\tilde{M}}_i$ and N defined as above. ${\tilde{C}}_i={\left(C_{+}-C_{-}\right)}^{-1}$, where is the 50% confidence interval
$CPA=|ACP-0.5|$	actual coverage probability (ACP) - the proportion of measurements that fall within the 50% confidence interval.