Performance of machine learning algorithms for dementia assessment: impacts of language tasks, recording media, and modalities

Table 9 Results obtained by applying ML algorithms on PCA-based acoustic features that are extracted from all datasets

Classifier	PDT	SRT	Web	Phone
DT	0.78 (± 0.16)	0.78 (± 0.02)	0.72 (± 0.21)	0.80 (± 0.16)
ET	0.61 (± 0.28)	0.61 (± 0.28)	0.68 (± 0.22)	0.92 (± 0.10)
kNN	0.61 (± 0.08)	0.78 (± 0.02)	0.61 (± 0.08)	0.80 (± 0.28)
LDA	0.50 (± 0.14)	0.50 (± 0.14)	0.50 (± 0.14)	0.87 (± 0.09)
R_SVM	0.61 (± 0.08)	0.65 (± 0.18)	0.72 (± 0.21)	0.76 (± 0.17)
L_SVM	0.50 (± 0.14)	0.35 (± 0.33)	0.89 (± 0.16)	0.67 (± 0.25)
LR	0.72 (± 0.21)	0.22 (± 0.16)	0.89 (± 0.16)	0.60 (± 0.28)
RF	0.54 (± 0.15)	0.78 (± 0.02	0.79 (± 0.23)	0.93 (± 0.07)

ISSN: 1472-6947