Detecting mild cognitive impairment in narratives in Brazilian Portuguese: first steps towards a fully automated system

Autores

  • Marcos Vinícius Treviso University of São Paulo http://orcid.org/0000-0001-7496-4951
  • Leandro Borges dos Santos University of São Paulo
  • Christopher Shulby University of São Paulo
  • Lilian Cristine Hübner Pontifical Catholic University of Rio Grande do Sul
  • Letícia Lessa Mansur University of São Paulo
  • Sandra Maria Aluísio University of São Paulo

DOI:

https://doi.org/10.15448/1984-7726.2018.1.30955

Palavras-chave:

Diagnóstico clínico, Comprometimento cognitivo leve, Segmentação automática de sentença, Métricas de complexidade sintática, Ferramentas de análise do discurso

Resumo

In recent years, Mild Cognitive Impairment (MCI) has received a great deal of attention, as it may represent a pre-clinical state of Alzheimer´s disease (AD). In the distinction between healthy elderly (CTL) and MCI patients, automated discourse analysis tools have been applied to narrative transcripts in English and in Brazilian Portuguese. However, the absence of sentence boundary segmentation in transcripts prevents the direct application of methods that rely on these marks for the correct use of tools, such as taggers and parsers. To our knowledge, there are only a few studies evaluating automatic sentence segmentation in transcripts of neuropsychological tests. The purpose of this study is to investigate the impact of
the automatic sentence segmentation method DeepBond on nine syntactic complexity metrics extracted of transcripts of CTL and MCI patients.

***Detecção de comprometimento cognitivo leve em narrativas em Português Brasileiro: primeiros passos para um sistema automatizado***

Nos últimos anos, o Comprometimento Cognitivo Leve (CCL) tem recebido bastante atenção, uma vez que pode representar um estado pré-clínico da Doença de Alzheimer (DA). Na distinção entre idosos saudáveis (CTL) e pacientes com CCL, ferramentas de análise automática do discurso têm sido aplicadas a transcrições de narrativas em inglês e em português brasileiro. No entanto, a ausência da segmentação dos limites da sentença em transcrições impede a aplicação direta de métodos que empregam essas pontuações para o uso correto de ferramentas, como taggers e parsers. Segundo nosso conhecimento, há poucos estudos avaliando a segmentação automática de sentenças em transcrições de testes neuropsicológicos. O propósito deste estudo é investigar o impacto do método DeepBond para segmentação automática de sentenças em nove métricas de complexidade sintática extraídas de transcrições de CTL e de pacientes com CCL.

Downloads

Não há dados estatísticos.

Referências

ALUÍSIO, S. et al. Computational Tool for Automated Language Production Analysis Aimed at Dementia Diagnosis. In: SILVA, J. et al. (Org.). International Conference on Computational Processing of the Portuguese Language, Demonstration Session, 2016a.

ALUÍSIO, S.; CUNHA, A.; SCARTON, C. Evaluating Progression of Alzheimer’s Disease by Regression and Classification Methods in a Narrative Language Test in Portuguese. In: SILVA, J. et al. (Org.). International Conference on Computational Processing of the Portuguese Language, p. 374-384, Springer International Publishing, 2016b.

ANDREETTA, S.; CANTAGALLO, A.; MARINI, A. Narrative discourse in anomic aphasia. Neuropsychologia, v. 50, n. 8, p. 1787-1793, 2012.

BATISTA, Pedro dos Santos. Avanços em Reconhecimento de Fala para Português Brasileiro e Aplicações: Ditado no Libre Office e Unidade de Resposta Audível com Asterisk. Dissertação (Mestrado) – Universidade Federal do Pará. Belém, 2013.

BAYLES, K. A.; TOMOEDA, C. K.; TROSSET, M. W. Alzheimer's disease: Effects on language. Developmental Neuropsychology, v. 9, n. 2, p. 131-160, 1993.

CÉSAR, K. G. et al. Prevalence of Cognitive Impairment Without Dementia and Dementia in Tremembé, Brazil. Alzheimer Dis Assoc Disord, v. 30, n. 3 p. 264-71, 2016.

CHAND, V. et al. Rubric for Extracting Idea Density from Oral Language Samples. Current Protocols in Neuroscience, v. 10, n. 5, 2012.

CLEMENTE, R. S. G.; RIBEIRO-FILHO, S. T. Comprometimento cognitivo leve: aspectos conceituais, abordagem clínica e diagnóstica. Revista Hospital Universitário Pedro Ernesto, v. 7, n. 1, p. 68-77, 2008.

CUNHA, A. L. V. et al. Automatic Proposition Extraction from Dependency Trees: Helping Early Prediction of Alzheimer's Disease from Narratives. Paper presented at the 28th International Symposium on Computer-Based Medical Systems, Institute of Electrical and Electronics Engineers, 2015. p. 127-130.

ENGEDAL, K.; LAKS, J. Towards a Brazilian dementia plan? Lessons to be learned from Europe. Dementia & Neuropsychologia, v. 10, n. 2, p. 74-78, 2016.

HÜBNER, L. C. et al. BALE: Bateria de Avaliação da Linguagem no Envelhecimento. In: FONSECA, R. P.; ZIMMERMANN, N. et al. Tarefas de avaliação neuropsicológica para adultos: memórias e linguagem. São Paulo: Memnon. (em preparação)

FRASER, K. C.; MELTZER, J. A.; RUDZICZ, F. Linguistic features identify Alzheimer’s disease in narrative speech. Journal of Alzheimer's Disease, v. 49, n. 2, p. 407-422, 2015a.

FRASER, K.C. et al. Sentence segmentation of aphasic speech. 2015 Conference of the North American Chapter of the Association for Computational Linguistics – Human Language Technologies (NAACL-HLT-2015), Denver, Colorado, 2015b.

FRAZIER, L. Syntactic complexity. In: DOWTY D. R.; KARTTUNEN, L.; ZWICKY, A. M. (Org.). Natural language parsing: Psychological, computational, and theoretical perspectives. Cambridge: Cambridge University Press, 1985. p. 129-189.

JERONIMO, G. M. Produção de narrativas orais no envelhecimento sadio, no comprometimento cognitivo leve e na doença de Alzheimer e sua relação com construtos cognitivos e escolaridade. 2015. 201 f. Tese (Doutorado em Linguística) – Pontifícia Universidade Católica do Rio Grande do Sul, Porto Alegre, 2015.

HASAN, M.; DODDIPATLA, R.; HAIN, T. Multi-Pass Sentence-End Detection of Lecture Speech. Paper presented at the 15 Conference of the International Speech Communication Association, Singapore, 2014.

HERRERA JR, E. et al. Epidemiologic survey of dementia in a community-dwelling Brazilian population. Alzheimer Disease & Associated Disorders, v. 16, n. 2, p. 103-108, 2002.

LE BOEUF, C. Raconte: 55 historiettes en images. L'École, 1976.

LEHR, M. et al. Fully Automated Neuropsychological Assessment for Detecting Mild Cognitive Impairment. Paper presented at the 13 Annual Conference of the International Speech Communication Association, Portland, OR, 2012.

LIU, Y. et al. A study in machine learning from imbalanced data for sentence boundary detection in speech. Computer Speech & Language, v. 20, n. 4, p. 468-494, 2006.

LÓPEZ, R.; PARDO, T. A. Experiments on Sentence Boundary Detection in User-Generated Web Content. In: GELBUKH, A (Org.). International Conference on Intelligent Text Processing and Computational Linguistics, Springer International Publishing, p. 227-237, 2015.

MAPSTONE, M. et al. Plasma phospholipids identify antecedent memory impairment in older adults. Nature medicine, v. 20, n. 4, p. 415-418, 2014.

MARQUIAFÁVEL, V. S. Ambiente de suporte à transcrição fonética automática de lemas em verbetes de dicionários do português do Brasil. Dissertação (Mestrado) – Universidade Estadual Paulista Júlio de Mesquita Filho, São José do Rio Preto, 2015. (não publicada)

MCKHANN, G. M. et al. The diagnosis of dementia due to Alzheimer’s disease: Recommendations from the National Institute on Aging-Alzheimer’s Association workgroups on diagnostic guidelines for Alzheimer's disease. Alzheimer's & dementia, v. 7, n. 3, p. 263-269, 2011.

MORRIS, J. C. et al. The Uniform Data Set (UDS): clinical and cognitive variables and descriptive data from Alzheimer Disease Centers. Alzheimer Disease & Associated Disorders, v. 20, n. 4, p. 210-216, 2006.

MUANGPAISAN, W.; PETCHARAT, C.; SRINONPRASERT, V. Prevalence of potentially reversible conditions in dementia and mild cognitive impairment in a geriatric clinic. Geriatrics & gerontology international, v. 12, n. 1, p. 59-64, 2012.

NAKAMURA, A. E. et al. Dementia underdiagnosis in Brazil. The Lancet, v. 385, n. 9966, p. 418-419, 2015.

NIVRE, J.; HALL, J.; NILSSON, J. Maltparser: A data-driven parser-generator for dependency parsing. Paper presented at the 6th International Conference on Language Resources and Evaluation, Genoa, 2006.

PRUD’HOMMEAUX, E. T.; MITCHELL, M.; ROARK, B. Using Patterns of Narrative Recall for Improved Detection of Mild Cognitive Impairment. In: Annual RESNA Conference/3rd International Conference on Technology and Aging (ICTA). RESNA (Rehabilitation Engineering and Assistive Technology Society of North America), 2011.

PRUD'HOMMEAUX, E.; ROARK, B. Graph-based word alignment for clinical language evaluation. Computational Linguistics, v. 41, n. 4, p. 549-578, 2015.

ROARK, B. et al. Spoken language derived measures for detecting mild cognitive impairment. Institute of Electrical and Electronics Engineers Transactions on Audio, Speech, and Language Processing, v. 19, n. 7, p. 2081-2090, 2011.

SANTOS, L. B. et al. Enriching Complex Networks with Word Embeddings for Detecting Mild Cognitive Impairment from Speech Transcripts. In: Annual Meeting of the Association for Computational Linguist, Vancouver, 2017.

Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Dublin, Ireland: Association for Computational Linguistics, 2017. p. 1284-1296.

SCARTON, C. E.; ALUÍSIO, S. M. Análise da Inteligibilidade de textos via ferramentas de Processamento de Língua Natural: adaptando as métricas do Coh-Metrix para o Português. Linguamática, v. 2, n. 1, p. 45-61, 2010.

SCAZUFCA, M. et al. High prevalence of dementia among older adults from poor socioeconomic backgrounds in Sao Paulo, Brazil. International Psychogeriatrics, v. 20, n. 02, p. 394-405, 2008.

SILVA, J. et al. Out-of-the-box robust parsing of portuguese. In: PARDO, T. A. S. et al. (Org.). International Conference on Computational Processing of the Portuguese Language. Springer Berlin Heidelberg, 2010. p. 75-85.

SAFFRAN, E. M.; BERNDT, R. S.; SCHWARTZ, M. F. The quantitative analysis of agrammatic production: Procedure and data. Brain and language, v. 37, n. 3, p. 440-479, 1989.

SILLA JR, C. N.; KAESTNER, C. A. An analysis of sentence boundary detection systems for English and Portuguese documents. In: GELBUKH, A (Org.). International Conference on Intelligent Text Processing and Computational Linguistics, Seoul, Korea. Springer Berlin Heidelberg, 2004. p. 135-141.

TÓTH, L. et al. Automatic detection of mild cognitive impairment from spontaneous speech using ASR. In: Proceedings of the 16th Annual Conference of the International Speech Communication Association. International Speech and Communication Association, 2015. p. 2694-2698.

TOLEDO, C. M. et al. Automatic classification of written descriptions by healthy adults: an overview of the application of natural language processing and machine learning techniques to clinical discourse analysis. Dementia & Neuropsychologia, v. 8, n. 3, p. 227-235, 2014.

VINCZE, V. et al. Detecting mild cognitive impairment by exploiting linguistic information from transcripts. In: Proceedings of the 54th Annual Meeting of the Association Computer Linguistics. Association for Computational Linguistics, 2016.

WANG, X.; NG, H. T.; SIM, K. C. Dynamic Conditional Random Fields for Joint Sentence Boundary and Punctuation Prediction. In: Interspeech, 2012. p. 1384-1387.

WECHSLER, D. Wechsler Adult Intelligence Scale-III, New York: Psychological Corporation, 1997.

YANCHEVA, M.; FRASER, K.; RUDZICZ, F. Using linguistic features longitudinally to predict clinical scores for Alzheimer's disease and related dementias. Paper presented at the 6 Workshop on Speech and Language Processing for Assistive Technologies (SLPAT2015), Dresden, 2015.

YNGVE, V. A Model and an Hypothesis for Language Structure. Proceedings of the American Philosophical Society, v. 104, n. 5, p. 444-466, 1960.

YUAN, J.; LIBERMAN, M. Speaker identification on the SCOTUS corpus. Journal of the Acoustical Society of America, v. 123, n. 5, p. 3878, 2008.

Downloads

Publicado

2018-06-05

Como Citar

Treviso, M. V., dos Santos, L. B., Shulby, C., Hübner, L. C., Mansur, L. L., & Aluísio, S. M. (2018). Detecting mild cognitive impairment in narratives in Brazilian Portuguese: first steps towards a fully automated system. Letras De Hoje, 53(1), 48–58. https://doi.org/10.15448/1984-7726.2018.1.30955

Edição

Seção

Linguagem na perspectiva da Psico/Neurolinguística e da Neurociência Cognitiva