Machine Learning for the Preliminary Diagnosis of Dementia

Table 1

Comparison of demographic data among the groups with different stages of cognitive impairment.

Group	CDR 0	CDR 0.5 (MCI)	CDR 0.5 (VMD)	CDR ≥ 1	F/x^2
N	51	113	98	265
Age, year (mean (SD))	68.1 (10.7)	71.8 (9.3)	76.1 (8.9)	78.9 (9.5)	30.772	<0.001
Female, N (%)	24 (47.1)	55 (48.7)	59 (60.2)	156 (58.9)	5.689	0.128
Education, year (mean (SD))	6.9 (5.1)	6.4 (4.5)	4.4 (4.0)	4.5 (4.5)	8.452	<0.001
MoCA, mean (SD)	21.1 (7.1)	18.0 (5.6)	11.1 (5.1)	7.2 (3.9)	202.176	<0.001
CASI, mean (SD)	85.5 (11.3)	78.3 (10.1)	63.5 (14.0)	47.7 (15.1)	202.478	<0.001
IADL, mean (SD)	8.0 (0.0)	7.3 (1.2)	6.0 (1.5)	2.7 (2.0)	314.797	<0.001
NPI-sum, mean (SD)	3.0 (4.1)	5.6 (6.8)	6.1 (7.3)	9.7 (10.5)	12.386	<0.001

CDR: Clinical Dementia Rating Scale; MCI: mild cognitive impairment; VMD: very mild dementia; N: number of participants; MoCA: Montreal Cognitive Assessment; IADL: Instrumental Activities of Daily Living; NPI-sum: sum score of Neuropsychiatric Inventory. Post hoc analysis showed CDR 0 < MCI < VMD < CDR≧1; post hoc analysis showed CDR 0 = MCI > VMD = CDR≧1; post hoc analysis showed CDR 0 = MCI = VMD < CDR ≥ 1.