Automatic Detection of Cognitive Impairments through Acoustic Analysis of Speech

Author(s): Ryosuke Nagumo*, Yaming Zhang, Yuki Ogawa, Mitsuharu Hosokawa, Kengo Abe, Takaaki Ukeda, Sadayuki Sumi, Satoshi Kurita, Sho Nakakubo, Sangyoon Lee, Takehiko Doi, Hiroyuki Shimada

Journal Name: Current Alzheimer Research

Volume 17 , Issue 1 , 2020

  Journal Home
Translate in Chinese
Become EABM
Become Reviewer

Abstract:

Background: Early detection of mild cognitive impairment is crucial in the prevention of Alzheimer’s disease. The aim of the present study was to identify whether acoustic features can help differentiate older, independent community-dwelling individuals with cognitive impairment from healthy controls.

Methods: A total of 8779 participants (mean age 74.2 ± 5.7 in the range of 65-96, 3907 males and 4872 females) with different cognitive profiles, namely healthy controls, mild cognitive impairment, global cognitive impairment (defined as a Mini Mental State Examination score of 20-23), and mild cognitive impairment with global cognitive impairment (a combined status of mild cognitive impairment and global cognitive impairment), were evaluated in short-sentence reading tasks, and their acoustic features, including temporal features (such as duration of utterance, number and length of pauses) and spectral features (F0, F1, and F2), were used to build a machine learning model to predict their cognitive impairments.

Results: The classification metrics from the healthy controls were evaluated through the area under the receiver operating characteristic curve and were found to be 0.61, 0.67, and 0.77 for mild cognitive impairment, global cognitive impairment, and mild cognitive impairment with global cognitive impairment, respectively.

Conclusion: Our machine learning model revealed that individuals’ acoustic features can be employed to discriminate between healthy controls and those with mild cognitive impairment with global cognitive impairment, which is a more severe form of cognitive impairment compared with mild cognitive impairment or global cognitive impairment alone. It is suggested that language impairment increases in severity with cognitive impairment.

Keywords: Mild cognitive impairment, global cognitive impairment, acoustic analysis, speech, sentence reading, machine learning.

[1]
Cabinet Office. Annual Report on the Aging Society 2017. Summary 2018.
[2]
Folstein MF, Folstein SE, McHugh PR. “Mini-mental state”. A practical method for grading the cognitive state of patients for the clinician. J Psychiatr Res 12(3): 189-98. (1975).
[http://dx.doi.org/10.1016/0022-3956(75)90026-6] [PMID: 1202204]
[3]
Nasreddine ZS, Phillips NA, Bédirian V, Charbonneau S, WHitehead V, Collin I, et al. The Montreal Cognitive Assessment, MoCA: a brief screening tool for mild cognitive impairment. J Am Geriatr Soc 53(4): 695-9. (2005).
[http://dx.doi.org/10.1111/j.1532-5415.2005.53221.x] [PMID: 15817019]
[4]
Morris RG. The Cognitive Neuropsychology of Alzheimer-Type Dementia. New York: Oxford University Press. 1996.
[5]
Biassou N, Grossman M, Onishi K, Mickanin J, Hughes E, Robinson KM, et al. Phonologic processing deficits in Alzheimer’s disease. Neurology 45(12): 2165-9. (1995).
[http://dx.doi.org/10.1212/WNL.45.12.2165] [PMID: 8848186]
[6]
Hoffmann I, Németh D, Dye CD, Pákáski M, Irinyi T, Kálmán J. Temporal parameters of spontaneous speech in Alzheimer’s disease. Int J Speech Lang Pathol 12(1): 29-34. (2010).
[http://dx.doi.org/10.3109/17549500903137256] [PMID: 20380247]
[7]
Martínez-Sánchez F, Meilán JJG, García-Sevilla J, Carro J, Arana JM. Oral reading fluency analysis in patients with Alzheimer disease and asymptomatic control subjects. Neurologia 28(6): 325-31. (2013).
[http://dx.doi.org/10.1016/j.nrleng.2012.07.017] [PMID: 23046975]
[8]
König A, Satt A, Sorin A, Hoary R, Toledo-Ronen O, Derreumaux A, et al. Automatic speech analysis for the assessment of patients with predementia and Alzheimer’s disease. Alzheimers Dement (Amst) 1(1): 112-24. (2015).
[http://dx.doi.org/10.1016/j.dadm.2014.11.012] [PMID: 27239498]
[9]
Themistocleous C, Eckerström M, Kokkinakis D. Identification of mild cognitive impairment from speech in Swedish using deep sequential neural networks. Front Neurol 9: 975. (2018).
[http://dx.doi.org/10.3389/fneur.2018.00975] [PMID: 30498472]
[10]
Cera ML, Ortiz KZ, Bertolucci PHF, Minett TSC. Speech and orofacial apraxias in Alzheimer’s disease. Int Psychogeriatr 25(10): 1679-85. (2013).
[http://dx.doi.org/10.1017/S1041610213000781] [PMID: 23742823]
[11]
Östberg P, Bogdanović N, Wahlund LO. Articulatory agility in cognitive decline. Folia Phoniatr Logop 61(5): 269-74. (2009).
[http://dx.doi.org/10.1159/000235649] [PMID: 19696488]
[12]
Watanabe Y, Arai H, Hirano H, Morishita S, Ohara Y, Edahiro A, et al. Oral function as an indexing parameter for mild cognitive impairment in older adults. Geriatr Gerontol Int 18(5): 790-8. (2018).
[http://dx.doi.org/10.1111/ggi.13259] [PMID: 29380503]
[13]
Shimada H, Tsutsumimoto K, Lee S, Doi T, Makizako H, Lee S, et al. Driving continuity in cognitively impaired older drivers. Geriatr Gerontol Int 16(4): 508-14. (2016).
[http://dx.doi.org/10.1111/ggi.12504] [PMID: 25953032]
[14]
Shimada H, Doi T, Lee S, Makizako H. Reversible predictors of reversion from mild cognitive impairment to normal cognition: a 4-year longitudinal study. Alzheimers Res Ther 11(1): 24. (2019).
[http://dx.doi.org/10.1186/s13195-019-0480-5] [PMID: 30867057]
[15]
National Institute for Health and Care Excellence. Alzheimer’s disease - donepezil, galantamine, rivastigmine and memantine (TA217) NICE technology appraisal guidance 2011
[16]
Shimada H, Makizako H, Tsutsumimoto K, Doi T, Lee S, Suzuki T. Cognitive frailty and incidence of dementia in older persons. J Prev Alzheimers Dis 5(1): 42-8. (2018).
[PMID: 29405232]
[17]
Teng EL, Chui HC. The modified mini-mental state. (3MS) examination. J Clin Psychiatry 48(8): 314-8. (1987).
[PMID: 3611032]
[18]
Makizako H, Shimada H, Park H, Doi T, Yoshida D, Uemura K, et al. Evaluation of multidimensional neurocognitive function using a tablet personal computer: test-retest reliability and validity in community-dwelling older adults. Geriatr Gerontol Int 13(4): 860-6. (2013).
[http://dx.doi.org/10.1111/ggi.12014] [PMID: 23230988]
[19]
O’Bryant SE, Humphreys JD, Smith GE, Ivnik RZJ, Graff-Radford NR, Petersen RC, et al. Detecting dementia with the mini-mental state examination in highly educated individuals. Arch Neurol 65(7): 963-7. (2008).
[http://dx.doi.org/10.1001/archneur.65.7.963] [PMID: 18625866]
[20]
Shimada H, Makizako H, Doi T, Tsutsumimoto K, Lee S, Suzuki T. Cognitive impairment and disability in older Japanese adults. PLoS One 11(7) e0158720 (2016).
[http://dx.doi.org/10.1371/journal.pone.0158720] [PMID: 27415430]
[21]
Noble K, Glosser G, Grossman M. Oral reading in dementia. Brain Lang 74(1): 48-69. (2000).
[http://dx.doi.org/10.1006/brln.2000.2330] [PMID: 10924216]
[22]
Pattamadilok C, Chanoine V, Pallier C, Anton J-L, Nazarian B, Belin P, et al. Automaticity of phonological and semantic processing during visual word recognition. Neuroimage 1149: 244-55. (2017).
[http://dx.doi.org/10.1016/j.neuroimage.2017.02.003]
[23]
Boersma P, Weenink D. Praat: doing phonetics by computer Available at:. www.fon.hum.uva.nl/praat
[24]
Skodda S, Grönheit W, Schlegel U. Impairment of vowel articulation as a possible marker of disease progression in Parkinson’s disease. PLoS One 7(2) e32132 (2012).
[http://dx.doi.org/10.1371/journal.pone.0032132] [PMID: 22389682]
[25]
Wutzler A, Becker R, Lämmler G, Haverkamp W, Steinhagen-Thiessen E. The anticipatory proportion as an indicator of language impairment in early-stage cognitive disorder in the elderly. Dement Geriatr Cogn Disord 36(5-6): 300-9. (2013).
[http://dx.doi.org/10.1159/000350808] [PMID: 24022211]
[26]
Lowit A, Brendel B, Dobinson C, Howell P. An investigation into the influences of age, pathology and cognition on speech production. J Med Speech-Lang Pathol 14: 253-62. (2006).
[PMID: 19330040]
[27]
Bishop C. Pattern Recognition and Machine Learning. Springer 2006.
[28]
Fawcett T. An introduction to ROC analysis. Pattern Recognit Lett 27: 861-74. (2006).
[http://dx.doi.org/10.1016/j.patrec.2005.10.010]
[29]
Ambroise C, McLachlan GJ. Selection bias in gene extraction on the basis of microarray gene-expression data. Proc Natl Acad Sci USA 99(10): 6562-6. (2002).
[http://dx.doi.org/10.1073/pnas.102102699] [PMID: 11983868]
[30]
Cawley GC, Talbot NLC. On over-fitting in model selection and subsequent selection bias in performance evaluation. J Mach Learn Res 11: 2079-107. (2010).
[31]
Alegret M, Peretó M, Pérez A, Valero S, Espinosa A, Ortega G, et al. The role of verb fluency in the detection of early cognitive impairment in Alzheimer’s disease. J Alzheimers Dis 62(2): 611-9. (2018).
[http://dx.doi.org/10.3233/JAD-170826] [PMID: 29480180]
[32]
Wingfield A, Poon LW, Lombardi L, Lowe D. Speed of processing in normal aging: effects of speech rate, linguistic structure, and processing time. J Gerontol 40(5): 579-85. (1985).
[http://dx.doi.org/10.1093/geronj/40.5.579] [PMID: 4031406]
[33]
Salthouse TA, Coon VE. Influence of task-specific processing speed on age differences in memory. J Gerontol 48(5): 245-55. (1993).
[http://dx.doi.org/10.1093/geronj/48.5.P245] [PMID: 8366270]
[34]
Beck LH, Bransome ED Jr, Mirsky AF, Rosvold HE, Sarason I. A continuous performance test of brain damage. J Consult Psychol 1956.; 20(5): 343-50.
[http://dx.doi.org/10.1037/h0043220] [PMID: 13367264]
[35]
Petersen RC, Doody R, Kurz A, Mohs RC, Morris JC, Rabins PV, et al. Current concepts in mild cognitive impairment. Arch Neurol 58(12): 1985-92. (2001).
[http://dx.doi.org/10.1001/archneur.58.12.1985] [PMID: 11735772]
[36]
Mueller KD, Koscik RL, Hermann BP, Johnson SC, Turkstra LS. Declines in connected language are associated with very early mild cognitive impairment: results from the Wisconsin Registry for Alzheimer’s prevention. Front Aging Neurosci 9: 437. (2018).
[http://dx.doi.org/10.3389/fnagi.2017.00437] [PMID: 29375365]
[37]
Swets JA. Measuring the accuracy of diagnostic systems. Science 240(4857): 1285-93. (1988).
[http://dx.doi.org/10.1126/science.3287615] [PMID: 3287615]
[38]
Tóth L, Hoffmann I, Gosztolya G, Vincze V, Szatloczki G, Banreti Z, et al. A speech recognition-based solution for the automatic detection of mild cognitive impairment from spontaneous speech. Curr Alzheimer Res 15(2): 130-8. (2018).
[http://dx.doi.org/10.2174/1567205014666171121114930] [PMID: 29165085]


Rights & PermissionsPrintExport Cite as

Article Details

VOLUME: 17
ISSUE: 1
Year: 2020
Page: [60 - 68]
Pages: 9
DOI: 10.2174/1567205017666200213094513

Article Metrics

PDF: 17
HTML: 4
EPUB: 1
PRC: 1