Table 5 MUQUBIA quantitative metrics for differential diagnosis in each diagnostic group of the test set.

From: Differential diagnosis of neurodegenerative dementias with the explainable MRI based machine learning algorithm MUQUBIA

 

Accuracy (%)

Precision (PPV) (%)

Recall (%)

F1 score (%)

NPV (%)

AD

90

88

73

80

91

FTD

93

89

89

89

95

DLB

93

82

95

88

98

CN

98

93

96

94

99

  1. Metrics used to determine the goodness of MUQUBIA in discriminating each diagnostic class.
  2. AD Alzheimer’s dementia, FTD frontotemporal dementia, DLB dementia with Lewy bodies, CN cognitively normal controls, PPV positive predictive value, NPV negative predictive value.
Back to article page