Demenba applies Mamba/VMamba state space models to full-length neuropsychological interview audio and reports improved dementia classification AUC over an EfficientNet baseline, but the evaluation has significant selection and sample-size problems.
Spoken language biomarkers for detect- ing cognitive impairment,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Recognizing Dementia from Neuropsychological Tests with State Space Models
Demenba applies Mamba/VMamba state space models to full-length neuropsychological interview audio and reports improved dementia classification AUC over an EfficientNet baseline, but the evaluation has significant selection and sample-size problems.