Skip to main content

Table 4 Semi-quantitative results for local clinical data

From: Comparison of machine learning and semi-quantification algorithms for (I123)FP-CIT classification: the beginning of the end for semi-quantification?

Method number Cut-offs defined by SBRs Accuracy SD Sensitivity SD Specificity SD
SQ 1 Mean − 2SD L + R putamen 0.79 0.08 0.68 0.12 0.97 0.05
SQ 2 Mean − 2SD L + R putamen, L + R caudate 0.78 0.08 0.68 0.11 0.96 0.06
SQ 3 Mean − 1.5SD L + R putamen 0.85 0.06 0.82 0.09 0.90 0.10
SQ 4 Mean − 1.5SD L + R putamen, L + R caudate 0.85 0.06 0.83 0.08 0.88 0.11
SQ 5 Mean − 1SD L + R putamen 0.86 0.06 0.91 0.06 0.77 0.12
SQ 6 Mean − 1SD L + R putamen, L + R caudate 0.86 0.05 0.92 0.06 0.75 0.13
SQ 7 Minimum L + R putamen 0.83 0.06 0.78 0.08 0.92 0.08
SQ 8 Minimum L + R putamen, L + R caudate 0.84 0.07 0.81 0.09 0.89 0.10
SQ 9 Regression − 2SE L + R putamen 0.82 0.07 0.72 0.11 0.99 0.03
SQ 10 Regress − 2SE L + R putamen, L + R caudate 0.82 0.06 0.72 0.10 0.98 0.04
SQ 11 Regress − 1.5SE L + R putamen 0.86 0.06 0.82 0.09 0.93 0.09
SQ 12 Regress − 1.5SE L + R putamen, L + R caudate 0.86 0.06 0.83 0.08 0.91 0.10
SQ 13 Regression − 1SE L + R putamen 0.87 0.06 0.92 0.06 0.78 0.12
SQ 14 Regress − 1SE L + R putamen, L + R caudate 0.87 0.06 0.93 0.06 0.77 0.12
SQ 15 ROC age-matched Lowest putamen 0.87 0.05 0.89 0.06 0.83 0.11
SQ 16 ROC age-matched Lowest putamen, lowest caudate 0.83 0.07 0.92 0.07 0.67 0.16
SQ 17 ROC Lowest putamen 0.86 0.06 0.86 0.08 0.86 0.13
SQ 18 ROC Lowest putamen, lowest caudate 0.84 0.06 0.90 0.07 0.74 0.14