Spontaneous Language Analysis in Alzheimer’s Disease:Evaluation of Natural Language Processing Technique for Analyzing Lexical Performance

doi:10.1007/s12204-021-2384-3

Abstract

Abstract: Language disorder, a common manifestation of Alzheimer’s disease (AD), has attracted widespread attention in recent years. This paper uses a novel natural language processing (NLP) method, compared with latest deep learning technology, to detect AD and explore the lexical performance. Our proposed approach is based on two stages. First, the dialogue contents are summarized into two categories with the same category. Second,term frequency - inverse document frequency (TF-IDF) algorithm is used to extract the keywords of transcripts,and the similarity of keywords between the groups was calculated separately by cosine distance. Several deep learning methods are used to compare the performance. In the meanwhile, keywords with the best performance are used to analyze AD patients’ lexical performance. In the Predictive Challenge of Alzheimer’s Disease held by iFlytek in 2019, the proposed AD diagnosis model achieves a better performance in binary classification by adjusting the number of keywords. The F1 score of the model has a considerable improvement over the baseline of 75.4%, and the training process of which is simple and efficient. We analyze the keywords of the model and find that AD patients use less noun and verb than normal controls. A computer-assisted AD diagnosis model on small Chinese dataset is proposed in this paper, which provides a potential way for assisting diagnosis of AD and analyzing lexical performance in clinical setting.

Key words: natural language processing (NLP)| Alzheimer’s disease (AD)| mild cognitive impairment| term frequency - inverse document frequency (TF-IDF)| bag of words

CLC Number:

TP 183
R 592

LIU Ning (刘宁), YUAN Zhenming* (袁贞明). Spontaneous Language Analysis in Alzheimer’s Disease:Evaluation of Natural Language Processing Technique for Analyzing Lexical Performance[J]. J Shanghai Jiaotong Univ Sci, 2022, 27(2): 160-167.

References 24

[23]	JOHNSON R, ZHANG T. Deep pyramid convolutional neural networks for text categorization[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1 : Long Papers). Vancouver, Canada: Association for Computational Linguistics, 2017: 562-570.
[1]	MESULAM M, WICKLUND A, JOHNSON N, et al.Alzheimer and frontotemporal pathology in subsets of primary progressive aphasia [J]. Annals of Neurology,2008, 63(6): 709-719.
[24]	LAI S, XU L, LIU K, et al. Recurrent convolutional neural networks for text classification [C]//29th AAAI Conference on Artificial Intelligence. Austin Texas,USA: AAAI, 2015: 2267-2273.
[2]	BARTHA L, BENKE T. Acute conduction aphasia:An analysis of 20 cases [J]. Brain and Language, 2003,85(1): 93-108.
[3]	ROTH C. Boston Diagnostic Aphasia Examination [M]//Encyclopedia of clinical neuropsychology. New York: Springer, 2011: 337-468.
[4]	KLUMPP P, FRITSCH J, NOETH E. ANN-based Alzheimer’s disease classification from bag of words [C]//Speech Communication; 13th ITG-Symposium.Oldenburg, Germany. VDE, 2018: 1-4.
[5]	GOSZTOLYA G, VINCZE V, T′OTH L, et al. Identifying Mild Cognitive Impairment and mild Alzheimer’s disease based on spontaneous speech using ASR and linguistic features [J]. Computer Speech & Language,2019, 53: 181-197.
[6]	JARROLD W, PEINTNER B, WILKINS D, et al.Aided diagnosis of dementia type through computerbased analysis of spontaneous speech [C]//Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality. Baltimore, USA: Association for Computational Linguistics, 2014: 27-37.
[7]	BUCKS R S, SINGH S, CUERDEN J M, et al. Analysis of spontaneous, conversational speech in dementia of Alzheimer type: Evaluation of an objective technique for analysing lexical performance [J]. Aphasiology,2000, 14(1): 71-91.
[8]	AHMED S, HAIGH A M F, DE JAGER C A, et al.Connected speech as a marker of disease progression in autopsy-proven Alzheimer’s disease [J]. Brain, 2013,136(12): 3727-3737.
[9]	ROARK B,MITCHELL M, HOSOM J P, et al. Spoken language derived measures for detecting mild cognitive impairment [J]. IEEE Transactions on Audio, Speech,and Language Processing, 2011, 19(7): 2081-2090.
[10]	WANG J, WANG Y H. Language disorders in Alzheimer’s disease [J]. Chinese Mental Health Journal,1999, 13(5): 263-265 (in Chinese).
[11]	HOLMES D, SINGH S. A stylometric analysis of conversational speech of aphasic patients [J]. Literary and Linguistic Computing, 1996, 11(3): 133-140.
[12]	ILLES J. Neurolinguistic features of spontaneous language production dissociate three forms of neurodegenerative disease: Alzheimer’s, Huntington’s, and Parkinson’s [J]. Brain and Language, 1989, 37(4): 628-642.
[13]	L′OPEZ-DE-IPI ?NA K, L′OPEZ-DE-IPI ?NA K,ALONSO J B, et al. On the selection of non-invasive methods based on speech analysis oriented to automatic Alzheimer disease diagnosis [J]. Sensors (Basel), 2013, 13(5): 6730-6745.
[14]	SPERLING R A, AISEN P S, BECKETT L A, et al.Toward defining the preclinical stages of Alzheimer’s disease: Recommendations from the National Institute on Aging-Alzheimer’s Association workgroups on diagnostic guidelines for Alzheimer’s disease [J].Alzheimer’s & Dementia, 2011, 7(3): 280-292.
[15]	ZENG X Q. Technology implementation of Chinese Jieba segmentation based on Python [J]. China Computer & Communication, 2019, 31(18): 38-39 (in Chinese).
[16]	ORIMAYE S O, WONG J S M, GOLDEN K J, et al.Predicting probable Alzheimer’s disease using linguistic deficits and biomarkers [J]. BMC Bioinformatics,2017, 18(1): 34.
[17]	GARRARD P, RENTOUMI V, GESIERICH B, et al.Machine learning approaches to diagnosis and laterality effects in semantic dementia discourse [J]. Cortex,2014, 55: 122-129.
[18]	DE LIRA J O, ORTIZ K Z, CAMPANHA A C, et al.Microlinguistic aspects of the oral narrative in patients with Alzheimer’s disease [J]. International Psychogeriatrics,2011, 23(3): 404-412.
[19]	ALAPARTHI S, MISHRA M. Bidirectional Encoder Representations from Transformers (BERT): A sentiment analysis odyssey [EB/OL]. (2020-07-02).https://arxiv.org/abs/2007.01127.
[20]	ZHANG Z Y, HAN X, LIU Z Y, et al. ERNIE: enhanced language representation with informative entities[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence,Italy: Association for Computational Linguistics,2019: 1441-1451.
[21]	XUE H. The application of iFLYTEK’s speech technology in mobile phone APP for meeting minutes [J].Computer & Telecommunication, 2017(5): 67-68 (in Chinese).
[22]	FRASER K C, LUNDHOLM FORS K, KOKKINAKIS D. Multilingual word embeddings for the assessment of narrative speech in mild cognitive impairment [J]. Computer Speech & Language, 2019, 53: 121-139.
[23]	JOHNSON R, ZHANG T. Deep pyramid convolutional neural networks for text categorization[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1 : Long Papers). Vancouver, Canada: Association for Computational Linguistics, 2017: 562-570.
[24]	LAI S, XU L, LIU K, et al. Recurrent convolutional neural networks for text classification [C]//29th AAAI Conference on Artificial Intelligence. Austin Texas,USA: AAAI, 2015: 2267-2273.