Linguistic markers predict onset of Alzheimer's disease.
Journal
EClinicalMedicine
ISSN: 2589-5370
Titre abrégé: EClinicalMedicine
Pays: England
ID NLM: 101733727
Informations de publication
Date de publication:
Nov 2020
Nov 2020
Historique:
received:
27
04
2020
revised:
19
09
2020
accepted:
22
09
2020
entrez:
9
12
2020
pubmed:
10
12
2020
medline:
10
12
2020
Statut:
epublish
Résumé
The aim of this study is to use classification methods to predict future onset of Alzheimer's disease in cognitively normal subjects through automated linguistic analysis. To study linguistic performance as an early biomarker of AD, we performed predictive modeling of future diagnosis of AD from a cognitively normal baseline of Framingham Heart Study participants. The linguistic variables were derived from written responses to the cookie-theft picture-description task. We compared the predictive performance of linguistic variables with clinical and neuropsychological variables. The study included 703 samples from 270 participants out of which a dataset consisting of a single sample from 80 participants was held out for testing. Half of the participants in the test set developed AD symptoms before 85 years old, while the other half did not. All samples in the test set were collected during the cognitively normal period (before MCI). The mean time to diagnosis of mild AD was 7.59 years. Significant predictive power was obtained, with AUC of 0.74 and accuracy of 0.70 when using linguistic variables. The linguistic variables most relevant for predicting onset of AD have been identified in the literature as associated with cognitive decline in dementia. The results suggest that language performance in naturalistic probes expose subtle early signs of progression to AD in advance of clinical diagnosis of impairment. Pfizer, Inc. provided funding to obtain data from the Framingham Heart Study Consortium, and to support the involvement of IBM Research in the initial phase of the study. The data used in this study was supported by Framingham Heart Study's National Heart, Lung, and Blood Institute contract (N01-HC-25195), and by grants from the National Institute on Aging grants (R01-AG016495, R01-AG008122) and the National Institute of Neurological Disorders and Stroke (R01-NS017950).
Sections du résumé
BACKGROUND
BACKGROUND
The aim of this study is to use classification methods to predict future onset of Alzheimer's disease in cognitively normal subjects through automated linguistic analysis.
METHODS
METHODS
To study linguistic performance as an early biomarker of AD, we performed predictive modeling of future diagnosis of AD from a cognitively normal baseline of Framingham Heart Study participants. The linguistic variables were derived from written responses to the cookie-theft picture-description task. We compared the predictive performance of linguistic variables with clinical and neuropsychological variables. The study included 703 samples from 270 participants out of which a dataset consisting of a single sample from 80 participants was held out for testing. Half of the participants in the test set developed AD symptoms before 85 years old, while the other half did not. All samples in the test set were collected during the cognitively normal period (before MCI). The mean time to diagnosis of mild AD was 7.59 years.
FINDINGS
RESULTS
Significant predictive power was obtained, with AUC of 0.74 and accuracy of 0.70 when using linguistic variables. The linguistic variables most relevant for predicting onset of AD have been identified in the literature as associated with cognitive decline in dementia.
INTERPRETATION
CONCLUSIONS
The results suggest that language performance in naturalistic probes expose subtle early signs of progression to AD in advance of clinical diagnosis of impairment.
FUNDING
BACKGROUND
Pfizer, Inc. provided funding to obtain data from the Framingham Heart Study Consortium, and to support the involvement of IBM Research in the initial phase of the study. The data used in this study was supported by Framingham Heart Study's National Heart, Lung, and Blood Institute contract (N01-HC-25195), and by grants from the National Institute on Aging grants (R01-AG016495, R01-AG008122) and the National Institute of Neurological Disorders and Stroke (R01-NS017950).
Identifiants
pubmed: 33294808
doi: 10.1016/j.eclinm.2020.100583
pii: S2589-5370(20)30327-8
pmc: PMC7700896
doi:
Types de publication
Journal Article
Langues
eng
Pagination
100583Informations de copyright
© 2020 Published by Elsevier Ltd.
Déclaration de conflit d'intérêts
Elif Eyigoz and Guillermo Cecchi has worked as salaried employees of IBM Corp. for the full duration of this project. Melissa Naylor was a salaried employee of Pfizer, Inc. when assigned to this project, until October 2018, and since then has been a salaried employee of Takeda Pharmaceuticals. Sachin Mathur and Mar Santamaria have worked as salaried employees of Pfizer, Inc. for the full duration of this project. Guillermo Cecchi declares that IBM holds a patent (US-9508360-B2) for the extraction of one of the features used in the linguistic model.
Références
Brain Lang. 1998 Oct 1;64(3):297-316
pubmed: 9743544
Arch Neurol. 2006 Jan;63(1):15-6
pubmed: 16401731
JAMA. 1996 Feb 21;275(7):528-32
pubmed: 8606473
J Am Geriatr Soc. 2005 Apr;53(4):695-9
pubmed: 15817019
J Alzheimers Dis. 2010;20 Suppl 2:S527-33
pubmed: 20442496
Am J Public Health Nations Health. 1951 Mar;41(3):279-81
pubmed: 14819398
Am J Epidemiol. 1979 Sep;110(3):281-90
pubmed: 474565
Nat Med. 2019 Feb;25(2):277-283
pubmed: 30664784
JAMA. 1994 Apr 6;271(13):1004-10
pubmed: 8139057
J Psychiatr Res. 1975 Nov;12(3):189-98
pubmed: 1202204
Arch Gen Psychiatry. 2003 Feb;60(2):190-7
pubmed: 12578437
PLoS One. 2011;6(7):e21896
pubmed: 21814561
Arch Gen Psychiatry. 1994 Jul;51(7):577-86
pubmed: 8031231
Ann Neurol. 1988 Feb;23(2):138-44
pubmed: 2897823
Int J Geriatr Psychiatry. 2005 Dec;20(12):1180-6
pubmed: 16315148
Clin Epidemiol. 2014 Jan 08;6:37-48
pubmed: 24470773
Neurology. 1997 Dec;49(6):1498-504
pubmed: 9409336
Mol Psychiatry. 2012 Nov;17(11):1056-76
pubmed: 22143004
Alzheimers Dement. 2011 Jan;7(1):35-52
pubmed: 21255742
Neurology. 1999 Dec 10;53(9):1992-7
pubmed: 10599770
Brain Lang. 1996 May;53(2):222-33
pubmed: 8726534
Int Psychogeriatr. 2011 Apr;23(3):404-12
pubmed: 20699046
BMC Med Inform Decis Mak. 2017 Jul 19;17(1):110
pubmed: 28724366
Neurology. 1984 Jul;34(7):939-44
pubmed: 6610841
Brain Lang. 1982 Sep;17(1):73-91
pubmed: 7139272
Arch Gen Psychiatry. 2005 May;62(5):565-73
pubmed: 15867110
Arch Neurol. 2001 Mar;58(3):397-405
pubmed: 11255443
Curr Alzheimer Res. 2012 Jul;9(6):673-86
pubmed: 22471865
Neurology. 1993 Mar;43(3 Pt 1):515-9
pubmed: 8450993
Brain Lang. 1983 May;19(1):124-41
pubmed: 6860932
Psychol Rep. 1987 Jun;60(3 Pt 2):1023-40
pubmed: 3628637
Exp Aging Res. 2004 Oct-Dec;30(4):333-58
pubmed: 15371099
Alzheimers Dement. 2011 May;7(3):280-92
pubmed: 21514248