Table 4.

Additional imaging response detection performance metrics (balanced F-scores) for each model and the two types of classifier

Predictor set	Support vector machines	Extremely randomised trees
Brain volume	0.555 [0.541–0.569]	0.601 [0.593–0.609]
Number of lesions	0.595 [0.581–0.609]	0.666 [0.655–0.677]
Total lesion volume	0.602 [0.592–0.612]	0.619 [0.610–0.628]
Best low dimensional	0.722 [0.713–0.731]	0.717 [0.708–0.725]
Regional atrophy	0.849 [0.843–0.855]	0.835 [0.829–0.842]
Regional disconnection	0.821 [0.814–0.829]	0.816 [0.809–0.823]
Best high dimensional	0.876 [0.870–0.882]	0.874 [0.868–0.880]

All figures are given as the mean, balanced F-score [95% CI]