Cognitive Performance and Learning Parameters Predict Response to Working Memory Training in Parkinson's Disease.
Parkinson’s disease
clinical trial
cognition
cognitive aging
internet-based intervention
precision medicine
supervised machine learning
working memory
Journal
Journal of Parkinson's disease
ISSN: 1877-718X
Titre abrégé: J Parkinsons Dis
Pays: Netherlands
ID NLM: 101567362
Informations de publication
Date de publication:
2022
2022
Historique:
pubmed:
20
9
2022
medline:
19
10
2022
entrez:
19
9
2022
Statut:
ppublish
Résumé
Working memory (WM) training (WMT) is a popular intervention approach against cognitive decline in patients with Parkinson's disease (PD). However, heterogeneity in WM responsiveness suggests that WMT may not be equally efficient for all patients. The present study aims to evaluate a multivariate model to predict post-intervention verbal WM in patients with PD using a supervised machine learning approach. We test the predictive potential of novel learning parameters derived from the WMT and compare their predictiveness to other more commonly used domains including demographic, clinical, and cognitive data. 37 patients with PD (age: 64.09±8.56, 48.6% female, 94.7% Hoehn & Yahr stage 2) participated in a 5-week WMT. Four random forest regression models including 1) cognitive variables only, 2) learning parameters only, 3) both cognitive and learning variables, and 4) the entire set of variables (with additional demographic and clinical data, 'all' model), were built to predict immediate and 3-month-follow-up WM. The 'all' model predicted verbal WM with the lowest root mean square error (RMSE) compared to the other models, at both immediate (RMSE = 0.184; 95% -CI=[0.184;0.185]) and 3-month follow-up (RMSE = 0.216; 95% -CI=[0.215;0.217]). Cognitive baseline parameters were among the most important predictors in the 'all' model. The model combining cognitive and learning parameters significantly outperformed the model solely based on cognitive variables. Commonly assessed demographic, clinical, and cognitive variables provide robust prediction of response to WMT. Nonetheless, inclusion of training-inherent learning parameters further boosts precision of prediction models which in turn may augment training benefits following cognitive interventions in patients with PD.
Sections du résumé
BACKGROUND
Working memory (WM) training (WMT) is a popular intervention approach against cognitive decline in patients with Parkinson's disease (PD). However, heterogeneity in WM responsiveness suggests that WMT may not be equally efficient for all patients.
OBJECTIVE
The present study aims to evaluate a multivariate model to predict post-intervention verbal WM in patients with PD using a supervised machine learning approach. We test the predictive potential of novel learning parameters derived from the WMT and compare their predictiveness to other more commonly used domains including demographic, clinical, and cognitive data.
METHODS
37 patients with PD (age: 64.09±8.56, 48.6% female, 94.7% Hoehn & Yahr stage 2) participated in a 5-week WMT. Four random forest regression models including 1) cognitive variables only, 2) learning parameters only, 3) both cognitive and learning variables, and 4) the entire set of variables (with additional demographic and clinical data, 'all' model), were built to predict immediate and 3-month-follow-up WM.
RESULT
The 'all' model predicted verbal WM with the lowest root mean square error (RMSE) compared to the other models, at both immediate (RMSE = 0.184; 95% -CI=[0.184;0.185]) and 3-month follow-up (RMSE = 0.216; 95% -CI=[0.215;0.217]). Cognitive baseline parameters were among the most important predictors in the 'all' model. The model combining cognitive and learning parameters significantly outperformed the model solely based on cognitive variables.
CONCLUSION
Commonly assessed demographic, clinical, and cognitive variables provide robust prediction of response to WMT. Nonetheless, inclusion of training-inherent learning parameters further boosts precision of prediction models which in turn may augment training benefits following cognitive interventions in patients with PD.
Identifiants
pubmed: 36120792
pii: JPD223448
doi: 10.3233/JPD-223448
pmc: PMC9661332
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
2235-2247Références
Brain Commun. 2020 Aug 27;2(2):fcaa115
pubmed: 32954349
Neuropsychol Rehabil. 2020 May;30(4):673-708
pubmed: 29968519
Neurosci Biobehav Rev. 2019 Aug;103:163-177
pubmed: 31100297
J Parkinsons Dis. 2018;8(s1):S107-S113
pubmed: 30584158
Front Psychiatry. 2020 Nov 19;11:554475
pubmed: 33329091
Mov Disord. 2016 Aug;31(8):1080-94
pubmed: 27431515
J Am Geriatr Soc. 2005 Apr;53(4):695-9
pubmed: 15817019
JAMA. 2020 Feb 11;323(6):548-560
pubmed: 32044947
J Psychiatr Res. 1982-1983;17(1):37-49
pubmed: 7183759
Annu Rev Clin Psychol. 2018 May 7;14:91-118
pubmed: 29401044
Neuropsychol Rev. 2021 Jun;31(2):288-311
pubmed: 33523408
Sci Rep. 2020 Mar 23;10(1):5227
pubmed: 32251360
J Neurol Neurosurg Psychiatry. 2016 Oct;87(10):1099-105
pubmed: 27401782
Lancet Neurol. 2003 Apr;2(4):229-37
pubmed: 12849211
Int Psychogeriatr. 2013 Jul;25(7):1115-23
pubmed: 23570673
Mov Disord. 2010 Nov 15;25(15):2649-53
pubmed: 21069833
Front Hum Neurosci. 2012 May 15;6:141
pubmed: 22615692
Parkinsonism Relat Disord. 2020 Mar;72:13-22
pubmed: 32078917
Mov Disord. 2011 Aug 15;26(10):1814-24
pubmed: 21661055
Neurology. 1967 May;17(5):427-42
pubmed: 6067254
Brain. 1988 Apr;111 ( Pt 2):299-321
pubmed: 3378138
Annu Rev Psychol. 2013;64:135-68
pubmed: 23020641
Neuropsychopharmacology. 2021 Mar;46(4):828-835
pubmed: 33027802
J Cent Nerv Syst Dis. 2020 Jan 16;12:1179573519899469
pubmed: 32002011
NPJ Schizophr. 2021 Aug 19;7(1):40
pubmed: 34413310
Philos Trans R Soc Lond B Biol Sci. 2015 Jul 5;370(1672):
pubmed: 26009763
Ther Adv Psychopharmacol. 2013 Apr;3(2):101-13
pubmed: 24167681
Dev Psychol. 2014 Jan;50(1):304-15
pubmed: 23688173
Front Aging Neurosci. 2020 Oct 14;12:575804
pubmed: 33173503
Psychol Res. 2014 Nov;78(6):821-35
pubmed: 24652343
Proc Natl Acad Sci U S A. 2011 Jun 21;108(25):10081-6
pubmed: 21670271
J Neurol Neurosurg Psychiatry. 1992 Mar;55(3):181-4
pubmed: 1564476
Mov Disord. 2013 Dec;28(14):1920-9
pubmed: 24123087
Neuropsychology. 2016 Feb;30(2):190-212
pubmed: 26237626
Front Psychol. 2014 Dec 23;5:1475
pubmed: 25566149
Nat Hum Behav. 2020 Nov;4(11):1145-1155
pubmed: 32868884
Psychol Aging. 2011 Dec;26(4):813-22
pubmed: 21707176
Mov Disord. 2012 Mar;27(3):349-56
pubmed: 22275317
Nat Rev Dis Primers. 2021 Jul 1;7(1):47
pubmed: 34210995
J Gerontol B Psychol Sci Soc Sci. 2020 Sep 14;75(8):e174-e188
pubmed: 32507890
Neurorehabil Neural Repair. 2021 Feb;35(2):117-130
pubmed: 33410387
Transl Psychiatry. 2019 Oct 22;9(1):271
pubmed: 31641106
Psychol Bull. 2010 Jul;136(4):659-76
pubmed: 20565172