Optimal MMSE and MoCA cutoffs for cognitive diagnoses in Parkinson's disease: A data-driven decision tree model.

Cognition Cognitive screening Global scale Neuropsychological assessment Parkinson's cognitive decline Threshold value

Journal

Journal of the neurological sciences
ISSN: 1878-5883
Titre abrégé: J Neurol Sci
Pays: Netherlands
ID NLM: 0375403

Informations de publication

Date de publication:
22 Oct 2024
Historique:
received: 23 07 2024
revised: 02 09 2024
accepted: 19 10 2024
medline: 30 10 2024
pubmed: 30 10 2024
entrez: 29 10 2024
Statut: aheadofprint

Résumé

Detecting cognitive impairment in Parkinson's disease (PD) is challenging due to diverse manifestations and outdated diagnostic criteria. Cognitive screening tools, as Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA), are adopted worldwide, but despite several cutoffs has been proposed for PD, no consensus has been reached, hindered by limited sample sizes, lack of validation, and inconsistent age- and education-adjustments. Determine the optimal MMSE and MoCA cutoffs in a large PD cohort, spanning from normal cognition (PD-NC), mild cognitive impairment (PD-MCI) to dementia (PDD), and develop a decision tree model to assist physicians in cognitive workups. Our retrospective Italian multicenter study involves 1780 PD, cognitively diagnosed with a level-II assessment: PD-NC(n = 700), PD-MCI(n = 706), and PDD(n = 374). Optimal cutoffs (for raw scores) were determined through ROC analysis. Then, a machine learning approach-decision trees-was adopted to validate and analyze the possible inclusion of other relevant clinical features. The decision tree model selected as primary feature a MMSE cutoff ≤24 to predict dementia, and a score ≤ 27 for PD-MCI. To enhance PD-MCIvs.PD-NC accuracy, it also recommends including a MoCA score ≤ 22 for PD-MCI, and > 22 for PD-NC. Age and education were not selected as relevant features for the cognitive workup. Both MoCA and MMSE cutoffs exhibited high sensitivity and specificity in detecting PD cognitive statues. For the first time, a clinical decision tree model based on robust MMSE and MoCA cutoffs has been developed, allowing to diagnose PD-MCI and/or PDD with a high accuracy and short administration time.

Sections du résumé

BACKGROUND BACKGROUND
Detecting cognitive impairment in Parkinson's disease (PD) is challenging due to diverse manifestations and outdated diagnostic criteria. Cognitive screening tools, as Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA), are adopted worldwide, but despite several cutoffs has been proposed for PD, no consensus has been reached, hindered by limited sample sizes, lack of validation, and inconsistent age- and education-adjustments.
OBJECTIVES OBJECTIVE
Determine the optimal MMSE and MoCA cutoffs in a large PD cohort, spanning from normal cognition (PD-NC), mild cognitive impairment (PD-MCI) to dementia (PDD), and develop a decision tree model to assist physicians in cognitive workups.
METHODS METHODS
Our retrospective Italian multicenter study involves 1780 PD, cognitively diagnosed with a level-II assessment: PD-NC(n = 700), PD-MCI(n = 706), and PDD(n = 374). Optimal cutoffs (for raw scores) were determined through ROC analysis. Then, a machine learning approach-decision trees-was adopted to validate and analyze the possible inclusion of other relevant clinical features.
RESULTS RESULTS
The decision tree model selected as primary feature a MMSE cutoff ≤24 to predict dementia, and a score ≤ 27 for PD-MCI. To enhance PD-MCIvs.PD-NC accuracy, it also recommends including a MoCA score ≤ 22 for PD-MCI, and > 22 for PD-NC. Age and education were not selected as relevant features for the cognitive workup. Both MoCA and MMSE cutoffs exhibited high sensitivity and specificity in detecting PD cognitive statues.
CONCLUSIONS CONCLUSIONS
For the first time, a clinical decision tree model based on robust MMSE and MoCA cutoffs has been developed, allowing to diagnose PD-MCI and/or PDD with a high accuracy and short administration time.

Identifiants

pubmed: 39471638
pii: S0022-510X(24)00419-2
doi: 10.1016/j.jns.2024.123283
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

123283

Informations de copyright

Copyright © 2024 Elsevier B.V. All rights reserved.

Déclaration de conflit d'intérêts

Declaration of competing interest The authors declare no competing financial interest.

Auteurs

Eleonora Fiorenzato (E)

Department of Neuroscience, University of Padua, Padua, Italy. Electronic address: eleonora.fiorenzato@unipd.it.

Simone Cauzzo (S)

Department of Neuroscience, University of Padua, Padua, Italy; Department of Medicine, University of Padua, Padua, Italy. Electronic address: simone.cauzzo@unipd.it.

Luca Weis (L)

IRCCS San Camillo Hospital, Venice, Italy.

Michela Garon (M)

Department of Neuroscience, University of Padua, Padua, Italy; Padua Neuroscience Center (PNC), University of Padua, Padua, Italy. Electronic address: michela.garon@unipd.it.

Francesca Pistonesi (F)

Department of Neuroscience, University of Padua, Padua, Italy. Electronic address: francesca.pistonesi@unipd.it.

Valeria Cianci (V)

Department of Neuroscience, University of Padua, Padua, Italy.

Maria Laura Nasi (ML)

Complex Operative Unit (UOC) of the Psychology, Neurology Hospital division, Padua University Hospital, Padua, Italy. Electronic address: marialaura.nasi@studenti.unipd.it.

Francesca Vianello (F)

Department of Neuroscience, University of Padua, Padua, Italy. Electronic address: francesca.vianello.3@unipd.it.

Anna Lena Zecchinelli (AL)

Parkinson Institute Milan, ASST G. Pini-CTO, Milan, Italy. Electronic address: anna.zecchinelli@asst-pini-cto.it.

Gianni Pezzoli (G)

Fondazione Grigioni Per il Morbo Di Parkinson, Milan, Italy. Electronic address: gianni.pezzoli@asst-pini-cto.it.

Elisa Reali (E)

Parkinson Institute Milan, ASST G. Pini-CTO, Milan, Italy.

Beatrice Pozzi (B)

Parkinson Institute Milan, ASST G. Pini-CTO, Milan, Italy.

Ioannis Ugo Isaias (IU)

Parkinson Institute Milan, ASST G. Pini-CTO, Milan, Italy; Department of Neurology, University Hospital of Würzburg, Julius Maximilian University of Würzburg, Würzburg, Germany. Electronic address: ioannis.isaias@asst-pini-cto.it.

Chiara Siri (C)

Parkinson Institute Milan, ASST G. Pini-CTO, Milan, Italy; Movement Disorders Rehabilitation Department, Moriggia-Pelascini Hospital, Gravedona, Italy.

Gabriella Santangelo (G)

Department of Psychology, University of Campania "Luigi Vanvitelli", Caserta, Italy. Electronic address: gabriella.santangelo@unicampania.it.

Sofia Cuoco (S)

Department of Medicine, Surgery and Dentistry "Scuola Medica Salernitana", Neuroscience Section, University of Salerno, Baronissi, Salerno, Italy.

Paolo Barone (P)

Department of Medicine, Surgery and Dentistry "Scuola Medica Salernitana", Neuroscience Section, University of Salerno, Baronissi, Salerno, Italy. Electronic address: pbarone@unisa.it.

Angelo Antonini (A)

Department of Neuroscience, University of Padua, Padua, Italy; Padua Neuroscience Center (PNC), University of Padua, Padua, Italy; Parkinson and Movement Disorders Unit, Study Center for Neurodegeneration (CESNE), Department of Neuroscience, University of Padua, Padua, Italy. Electronic address: angelo.antonini@unipd.it.

Roberta Biundo (R)

Complex Operative Unit (UOC) of the Psychology, Neurology Hospital division, Padua University Hospital, Padua, Italy; Department of General Psychology, University of Padua, Padua, Italy. Electronic address: roberta.biundo@unipd.it.

Classifications MeSH