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

Sylvester Olubolu Orimaye, Jojo Sze-Meng Wong, Judyanne Sharmini Gilbert Fernandez

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    4 Citations (Scopus)

    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.
    Original languageEnglish
    Title of host publicationSecond international workshop on Advances in Bioinformatics and Artificial Intelligence: Bridging the Gap (BAI 2016)
    Subtitle of host publicationco-located with 25th International Joint Conference on Artificial Intelligence (IJCAI 2016), New-York, USA, July 11, 2016 [proceedings]
    EditorsAbdoulaye Baniré Diallo, Engelbert Mephu Nguifo, Mohammed Zaki
    PublisherRheinisch-Westfaelische Technische Hochschule Aachen
    Pages14-20
    Number of pages7
    Publication statusPublished - 2016
    EventAdvances in Bioinformatics and Artificial Intelligence 2016 - New York, United States of America
    Duration: 11 Jul 201611 Jul 2016
    http://ceur-ws.org/Vol-1718/ (Proceedings)

    Publication series

    NameCEUR Workshop Proceedings
    PublisherRheinisch-Westfaelische Technische Hochschule Aachen Lehrstuhl Informatik V
    Volume1718
    ISSN (Electronic)1613-0073

    Workshop

    WorkshopAdvances in Bioinformatics and Artificial Intelligence 2016
    Abbreviated titleBAI 2016
    CountryUnited States of America
    CityNew York
    Period11/07/1611/07/16
    Internet address

    Keywords

    • Deep neural networks
    • Mild cognitive impairment
    • Language models

    Cite this