Deep-deep neural network language models for predicting mild cognitive impairment

Document Type

Conference Proceeding

Publication Title

CEUR Workshop Proceedings


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


Last Page


Publication Date


This document is currently not available here.