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

Table 3 Results of classification between CU and MCI

	Accuracy	Precision	Recall	F1 Score	AUC
LR
Clinical data	0.69 ± 0.00	0.65 ± 0.00	0.79 ± 0.00	0.71 ± 0.00	0.74 ± 0.00
Tau PET	0.76 ± 0.00	0.82 ± 0.00	0.64 ± 0.00	0.72 ± 0.00	0.75 ± 0.00
Clinical data with Tau	0.72 ± 0.00	0.68 ± 0.01	0.82 ± 0.04	0.74 ± 0.01	0.79 ± 0.00
SVM
Clinical	0.76 ± 0.00	0.89 ± 0.00	0.57 ± 0.00	0.70 ± 0.00	0.68 ± 0.01
Tau	0.81 ± 0.02	0.91 ± 0.00	0.69 ± 0.00	0.78 ± 0.03	0.72 ± 0.02
Clinical with Tau	0.81 ± 0.02	0.82 ± 0.03	0.79 ± 0.04	0.80 ± 0.02	0.80 ± 0.02
XGB
Clinical	0.69 ± 0.00	0.65 ± 0.00	0.79 ± 0.00	0.71 ± 0.00	0.71 ± 0.01
Tau	0.65 ± 0.06	0.69 ± 0.12	0.56 ± 0.22	0.61 ± 0.00	0.73 ± 0.00
Clinical with Tau	0.72 ± 0.04	0.69 ± 0.05	0.79 ± 0.08	0.73 ± 0.03	0.79 ± 0.02
MLP
Clinical	0.63 ± 0.06	0.66 ± 0.10	0.55 ± 0.06	0.56 ± 0.17	0.71 ± 0.06
Tau	0.75 ± 0.02	0.83 ± 0.06	0.61 ± 0.04	0.70 ± 0.01	0.74 ± 0.01
Clinical with Tau	0.77 ± 0.05	0.75 ± 0.07	0.80 ± 0.04	0.77 ± 0.05	0.78 ± 0.05

CU cognitively un-impaired, MCI mild cognitive impairment 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