Machine learning application for classification of Alzheimer's disease stages using 18F-flortaucipir positron emission tomography

Table 2 Results of classification between CU and AD

	Accuracy	Precision	Recall	F1 Score	AUC
LR
Clinical data	0.92 ± 0.00	0.85 ± 0.00	1.00 ± 0.00	0.92 ± 0.00	1.00 ± 0.00
Tau PET	0.88 ± 0.00	0.83 ± 0.00	0.91 ± 0.00	0.87 ± 0.00	0.95 ± 0.01
Clinical data with Tau	0.96 ± 0.00	0.92 ± 0.00	1.00 ± 0.00	0.96 ± 0.00	1.00 ± 0.00
SVM
Clinical	0.96 ± 0.00	0.92 ± 0.00	1.00 ± 0.00	0.96 ± 0.00	1.00 ± 0.01
Tau	0.92 ± 0.00	0.91 ± 0.00	0.91 ± 0.00	0.91 ± 0.00	0.94 ± 0.01
Clinical with Tau	0.96 ± 0.00	0.92 ± 0.00	1.00 ± 0.00	0.96 ± 0.00	1.00 ± 0.00
XGB
Clinical	0.94 ± 0.02	0.88 ± 0.04	1.00 ± 0.00	0.94 ± 0.02	0.99 ± 0.00
Tau	0.88 ± 0.04	0.86 ± 0.05	0.86 ± 0.05	0.86 ± 0.05	0.97 ± 0.01
Clinical with Tau	0.94 ± 0.02	0.88 ± 0.04	1.00 ± 0.00	0.94 ± 0.02	1.00 ± 0.01
MLP
Clinical	0.91 ± 0.05	0.85 ± 0.08	0.98 ± 0.04	0.91 ± 0.06	0.99 ± 0.05
Tau	0.87 ± 0.03	0.83 ± 0.00	0.86 ± 0.05	0.84 ± 0.04	0.91 ± 0.03
Clinical with Tau	0.95 ± 0.01	0.90 ± 0.04	1.00 ± 0.00	0.95 ± 0.01	1.00 ± 0.02

CU cognitively un-impaired, AD Alzheimer’s disease, LR logistic regression, SVM support vector machine, XGB extreme gradient boosting, MLP multilayer perceptron, AUC area under the receiver operating characteristic curve. Values are presented as mean ± SD

ISSN: 1475-925X