Skip to main content

Table 3 Classification results comparing sensitivity, specificity, accuracy, AUC-ROC and error rates for different methods

From: Boosting the diagnostic power of amyloid-β PET using a data-driven spatially informed classifier for decision support

Method Features Sensitivity Specificity Accuracy AUC Error rate
Aβ clusters 1–4, GM voxels and GM SUVR 6 0.83 0.81 0.81 0.91 0.19
Aβ clusters 1–4 4 0.74 0.84 0.80 0.87 0.20
Composite SUVR 1 0.67 0.86 0.79 0.82 0.21
GM voxels and GM SUVR 2 0.44 0.85 0.69 0.71 0.31