Deep-deep neural network language models for predicting mild cognitive impairment
Document Type
Conference Proceeding
Publication Title
CEUR Workshop Proceedings
Abstract
Early diagnosis of Mild Cognitive Impairment (MCI) is currently a challenge. Currently, MCI is diagnosed using specific clinical diagnostic criteria and neuropsychological examinations. As such we propose an automated diagnostic technique using a variant of deep neural networks language models (DNNLM) on the verbal utterances of MCI patients. Motivated by the success of DNNLM on natural language tasks, we propose a combination of deep neural network and deep language models (D2NNLM) to predict MCI. Results on the DementiaBank language transcript clinical dataset show that D2NNLM sufficiently learned several linguistic biomarkers in the form of higher order n-grams and skip-grams to distinguish the MCI group from the healthy group with reasonable accuracy, which could help clinical diagnosis even in the absence of sufficient training data.
First Page
14
Last Page
20
Publication Date
1-1-2016
Recommended Citation
Orimaye, Sylvester Olubolu; Wong, Jojo Sze Meng; and Fernandez, Judyanne Sharmini Gilbert, "Deep-deep neural network language models for predicting mild cognitive impairment" (2016). Global Population Health Faculty Publications. 19.
https://collections.uhsp.edu/global-population-health_pubs/19