1
|
Castelli MB, Alonso-Recio L, Carvajal F, Serrano JM. Does the Montreal Cognitive Assessment (MoCA) identify cognitive impairment profiles in Parkinson's disease? An exploratory study. APPLIED NEUROPSYCHOLOGY. ADULT 2024; 31:238-247. [PMID: 34894908 DOI: 10.1080/23279095.2021.2011727] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
An important proportion of patients with Parkinson's Disease (PD) present signs of cognitive impairment, although this is heterogeneous. In an attempt to classify this, the dual syndrome hypothesis distinguishes between two profiles: one defined by attentional and executive problems with damage in anterior cerebral regions, and another with mnesic and visuospatial alterations, with damage in posterior cerebral regions. The Montreal Cognitive Assessment (MoCA) is one of the recommended screening tools, and one of the most used, to assess cognitive impairment in PD. However, its ability to specifically identify these two profiles of cognitive impairment has not been studied. The aim of this study was, therefore, to analyze the capacity of the MoCA to detect cognitive impairment, and also to identify anterior and posterior profiles defined by the dual syndrome hypothesis. For this purpose, 59 patients with idiopathic PD were studied with the MoCA and a neuropsychological battery of tests covering all cognitive domains. Results of logistic regression analysis with ROC (Receiver Operating Characteristic) curves showed that MoCA detected cognitive impairment and identified patients with a profile of anterior/attentional and executive deficit, with acceptable sensibility and specificity. However, it did not identify patients with a posterior/mnesic-visuospatial impairment. We discuss the reasons for the lack of sensitivity of MoCA in this profile, and other possible implications of these results with regards the usefulness of this tool to assess cognitive impairment in PD.
Collapse
Affiliation(s)
- María Belén Castelli
- Departamento de Psicología Biológica y de la Salud, Facultad de Psicología, Universidad Autónoma de Madrid, Madrid, Spain
| | - Laura Alonso-Recio
- Departamento de Psicología y Salud, Facultad de Ciencias de la Salud y la Educación, Universidad a Distancia de Madrid, Madrid, Spain
| | - Fernando Carvajal
- Departamento de Psicología Biológica y de la Salud, Facultad de Psicología, Universidad Autónoma de Madrid, Madrid, Spain
| | - Juan Manuel Serrano
- Departamento de Psicología Biológica y de la Salud, Facultad de Psicología, Universidad Autónoma de Madrid, Madrid, Spain
| |
Collapse
|
2
|
Hosseinzadeh M, Gorji A, Fathi Jouzdani A, Rezaeijo SM, Rahmim A, Salmanpour MR. Prediction of Cognitive Decline in Parkinson's Disease Using Clinical and DAT SPECT Imaging Features, and Hybrid Machine Learning Systems. Diagnostics (Basel) 2023; 13:1691. [PMID: 37238175 PMCID: PMC10217464 DOI: 10.3390/diagnostics13101691] [Citation(s) in RCA: 30] [Impact Index Per Article: 30.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Revised: 04/28/2023] [Accepted: 05/04/2023] [Indexed: 05/28/2023] Open
Abstract
BACKGROUND We aimed to predict Montreal Cognitive Assessment (MoCA) scores in Parkinson's disease patients at year 4 using handcrafted radiomics (RF), deep (DF), and clinical (CF) features at year 0 (baseline) applied to hybrid machine learning systems (HMLSs). METHODS 297 patients were selected from the Parkinson's Progressive Marker Initiative (PPMI) database. The standardized SERA radiomics software and a 3D encoder were employed to extract RFs and DFs from single-photon emission computed tomography (DAT-SPECT) images, respectively. The patients with MoCA scores over 26 were indicated as normal; otherwise, scores under 26 were indicated as abnormal. Moreover, we applied different combinations of feature sets to HMLSs, including the Analysis of Variance (ANOVA) feature selection, which was linked with eight classifiers, including Multi-Layer Perceptron (MLP), K-Neighbors Classifier (KNN), Extra Trees Classifier (ETC), and others. We employed 80% of the patients to select the best model in a 5-fold cross-validation process, and the remaining 20% were employed for hold-out testing. RESULTS For the sole usage of RFs and DFs, ANOVA and MLP resulted in averaged accuracies of 59 ± 3% and 65 ± 4% for 5-fold cross-validation, respectively, with hold-out testing accuracies of 59 ± 1% and 56 ± 2%, respectively. For sole CFs, a higher performance of 77 ± 8% for 5-fold cross-validation and a hold-out testing performance of 82 + 2% were obtained from ANOVA and ETC. RF+DF obtained a performance of 64 ± 7%, with a hold-out testing performance of 59 ± 2% through ANOVA and XGBC. Usage of CF+RF, CF+DF, and RF+DF+CF enabled the highest averaged accuracies of 78 ± 7%, 78 ± 9%, and 76 ± 8% for 5-fold cross-validation, and hold-out testing accuracies of 81 ± 2%, 82 ± 2%, and 83 ± 4%, respectively. CONCLUSIONS We demonstrated that CFs vitally contribute to predictive performance, and combining them with appropriate imaging features and HMLSs can result in the best prediction performance.
Collapse
Affiliation(s)
- Mahdi Hosseinzadeh
- Technological Virtual Collaboration (TECVICO Corp.), Vancouver, BC V5E 3J7, Canada;
- Department of Electrical & Computer Engineering, University of Tarbiat Modares, Tehran 14115111, Iran
| | - Arman Gorji
- Neuroscience and Artificial Intelligence Research Group (NAIRG), Student Research Committee, Hamadan University of Medical Sciences, Hamadan 6517838736, Iran
| | - Ali Fathi Jouzdani
- Neuroscience and Artificial Intelligence Research Group (NAIRG), Student Research Committee, Hamadan University of Medical Sciences, Hamadan 6517838736, Iran
| | - Seyed Masoud Rezaeijo
- Department of Medical Physics, Faculty of Medicine, Ahvaz Jundishapur University of Medical Sciences, Ahvaz 6135715794, Iran
| | - Arman Rahmim
- Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC V5Z 1L3, Canada
- Departments of Radiology and Physics, University of British Columbia, Vancouver, BC V6T 1Z4, Canada
| | - Mohammad R. Salmanpour
- Technological Virtual Collaboration (TECVICO Corp.), Vancouver, BC V5E 3J7, Canada;
- Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC V5Z 1L3, Canada
| |
Collapse
|
3
|
Salmanpour MR, Bakhtiyari M, Hosseinzadeh M, Maghsudi M, Yousefirizi F, Ghaemi MM, Rahmim A. Application of novel hybrid machine learning systems and radiomics features for non-motor outcome prediction in Parkinson's disease. Phys Med Biol 2023; 68. [PMID: 36595257 DOI: 10.1088/1361-6560/acaba6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2022] [Accepted: 12/14/2022] [Indexed: 12/15/2022]
Abstract
Objectives.Parkinson's disease (PD) is a complex neurodegenerative disorder, affecting 2%-3% of the elderly population. Montreal Cognitive Assessment (MoCA), a rapid nonmotor screening test, assesses different cognitive dysfunctionality aspects. Early MoCA prediction may facilitate better temporal therapy and disease control. Radiomics features (RF), in addition to clinical features (CF), are indicated to increase clinical diagnoses, etc, bridging between medical imaging procedures and personalized medicine. We investigate the effect of RFs, CFs, and conventional imaging features (CIF) to enhance prediction performance using hybrid machine learning systems (HMLS).Methods.We selected 210 patients with 981 features (CFs, CIFs, and RFs) from the Parkinson's Progression-Markers-Initiative database. We generated 4 datasets, namely using (i), (ii) year-0 (D1) or year-1 (D2) features, (iii) longitudinal data (D3, putting datasets in years 0 and 1 longitudinally next to each other), and (iv) timeless data (D4, effectively doubling dataset size by listing both datasets from years 0 and 1 separately). First, we directly applied 23 predictor algorithms (PA) to the datasets to predict year-4 MoCA, which PD patients this year have a higher dementia risk. Subsequently, HMLSs, including 14 attribute extraction and 10 feature selection algorithms followed by PAs were employed to enhance prediction performances. 80% of all datapoints were utilized to select the best model based on minimum mean absolute error (MAE) resulting from 5-fold cross-validation. Subsequently, the remaining 20% was used for hold-out testing of the selected models.Results.When applying PAs without ASAs/FEAs to datasets (MoCA outcome range: [11,30]), Adaboost achieved an MAE of 1.74 ± 0.29 on D4 with a hold-out testing performance of 1.71. When employing HMLSs, D4 + Minimum_Redundancy_Maximum_Relevance (MRMR)+K_Nearest_Neighbor Regressor achieved the highest performance of 1.05 ± 0.25 with a hold-out testing performance of 0.57.Conclusion.Our study shows the importance of using larger datasets (timeless), and utilizing optimized HMLSs, for significantly improved prediction of MoCA in PD patients.
Collapse
Affiliation(s)
- Mohammad R Salmanpour
- Department of Physics & Astronomy, University of British Columbia, Vancouver, BC, Canada.,Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC, Canada.,Technological Virtual Collaboration (TECVICO Corp), Vancouver, BC, Canada
| | - Mahya Bakhtiyari
- Technological Virtual Collaboration (TECVICO Corp), Vancouver, BC, Canada.,Department of Electrical & Computer Engineering, South Tehran Branch, Islamic Azad University, Tehran, Iran
| | - Mahdi Hosseinzadeh
- Technological Virtual Collaboration (TECVICO Corp), Vancouver, BC, Canada.,Department of Electrical & Computer Engineering, University of Tarbiat Modares, Tehran, Iran
| | - Mehdi Maghsudi
- Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Fereshteh Yousefirizi
- Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC, Canada
| | - Mohammad M Ghaemi
- Technological Virtual Collaboration (TECVICO Corp), Vancouver, BC, Canada.,Medical Informatics Research Centre, Institute for Futures Studies in Health, Kerman University of Medical Sciences, Kerman, Iran.,Department of Health Information Management, Kerman University of Medical Sciences, Kerman, Iran
| | - Arman Rahmim
- Department of Physics & Astronomy, University of British Columbia, Vancouver, BC, Canada.,Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC, Canada
| |
Collapse
|
4
|
Parmera JB, Tumas V, Ferraz HB, Spitz M, Barbosa MT, Smid J, Barbosa BJAP, Schilling LP, Balthazar MLF, de Souza LC, Vale FAC, Caramelli P, Bertolucci PHF, Chaves MLF, Brucki SMD, Nitrini R, Castilhos RM, Frota NAF. Diagnosis and management of Parkinson's disease dementia and dementia with Lewy bodies: recommendations of the Scientific Department of Cognitive Neurology and Aging of the Brazilian Academy of Neurology. Dement Neuropsychol 2022; 16:73-87. [PMID: 36533156 PMCID: PMC9745997 DOI: 10.1590/1980-5764-dn-2022-s105pt] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2021] [Revised: 10/13/2021] [Accepted: 04/27/2022] [Indexed: 11/29/2022] Open
Abstract
Parkinson's disease dementia (PDD) and dementia with Lewy bodies (DLB) represent the second most common type of degenerative dementia in patients aged 65 years and older, leading to progressive cognitive dysfunction and impaired quality of life. This study aims to provide a consensus based on a systematic Brazilian literature review and a comprehensive international review concerning PDD and DLB. Moreover, we sought to report on and give recommendations about the best diagnostic approaches focusing on primary and secondary care. Based on the available data, we recommend clinicians to apply at least one brief global cognitive instrument to assess PDD, such as the Mini-Mental State Examination and preferably the Montreal Cognitive Assessment and the Addenbrooke's Cognitive Examination-Revised. Validated instruments to accurately assess functional abilities in Brazilian PD patients are still incipient. Further studies should focus on biomarkers with Brazilian cohorts.
Collapse
Affiliation(s)
- Jacy Bezerra Parmera
- Universidade de São Paulo, Faculdade de Medicina, Departamento de Neurologia, Grupo de Neurologia Cognitiva e do Comportamento, São Paulo SP, Brasil
| | - Vitor Tumas
- Universidade de São Paulo, Faculdade de Medicina de Ribeirão Preto, Departamento de Neurociências e Ciências do Comportamento, São Paulo SP, Brasil
| | - Henrique Ballalai Ferraz
- Universidade Federal de São Paulo, Escola Paulista de Medicina, Departamento de Neurologia e Neurocirurgia, São Paulo SP, Brasil
| | - Mariana Spitz
- Universidade do Estado do Rio de Janeiro, Serviço de Neurologia, Rio de Janeiro RJ, Brasil
| | - Maira Tonidandel Barbosa
- Universidade Federal de Minas Gerais, Faculdade de Medicina, Departamento de Medicina Interna, Belo Horizonte MG, Brasil
- Faculdade Ciências Médicas de Minas Gerais, Medicina Geriátrica, Belo Horizonte MG, Brasil
| | - Jerusa Smid
- Universidade de São Paulo, Faculdade de Medicina, Departamento de Neurologia, Grupo de Neurologia Cognitiva e do Comportamento, São Paulo SP, Brasil
| | - Breno José Alencar Pires Barbosa
- Universidade de São Paulo, Faculdade de Medicina, Departamento de Neurologia, Grupo de Neurologia Cognitiva e do Comportamento, São Paulo SP, Brasil
- Universidade Federal de Pernambuco, Centro de Ciências Médicas, Área Acadêmica de Neuropsiquiatria, Recife PE, Brasil
- Instituto de Medicina Integral Prof. Fernando Figueira, Recife PE, Brasil
| | - Lucas Porcello Schilling
- Pontifícia Universidade do Rio Grande do Sul, Escola de Medicina, Serviço de Neurologia, Porto Alegre RS, Brasil
- Pontifícia Universidade do Rio Grande do Sul, Instituto do Cérebro do Rio Grande do Sul, Porto Alegre RS, Brasil
- Pontifícia Universidade do Rio Grande do Sul, Programa de Pós-Graduação em Gerontologia Biomédica, Porto Alegre RS, Brasil
| | | | - Leonardo Cruz de Souza
- Universidade Federal de Minas Gerais, Departamento de Clínica Médica, Belo Horizonte MG, Brasil
| | - Francisco Assis Carvalho Vale
- Universidade Federal de São Carlos, Centro de Ciências Biológicas e da Saúde, Departamento de Medicina, São Carlos SP, Brasil
| | - Paulo Caramelli
- Universidade Federal de Minas Gerais, Departamento de Clínica Médica, Belo Horizonte MG, Brasil
| | | | - Márcia Lorena Fagundes Chaves
- Hospital de Clínicas de Porto Alegre, Serviço de Neurologia, Porto Alegre RS, Brasil
- Universidade Federal do Rio Grande do Sul, Faculdade de Medicina, Serviço de Neurologia, Porto Alegre RS, Brasil
| | - Sonia Maria Dozzi Brucki
- Universidade de São Paulo, Faculdade de Medicina, Departamento de Neurologia, Grupo de Neurologia Cognitiva e do Comportamento, São Paulo SP, Brasil
| | - Ricardo Nitrini
- Universidade de São Paulo, Faculdade de Medicina, Departamento de Neurologia, Grupo de Neurologia Cognitiva e do Comportamento, São Paulo SP, Brasil
| | | | | |
Collapse
|
5
|
Parmera JB, Tumas V, Ferraz HB, Spitz M, Barbosa MT, Smid J, Barbosa BJAP, Schilling LP, Balthazar MLF, Souza LCD, Vale FAC, Caramelli P, Bertolucci PHF, Chaves MLF, Brucki SMD, Nitrini R, Castilhos RM, Frota NAF. Diagnosis and management of Parkinson’s disease dementia and dementia with Lewy bodies: recommendations of the Scientific Department of Cognitive Neurology and Aging of the Brazilian Academy of Neurology. Dement Neuropsychol 2022. [DOI: 10.1590/1980-5764-dn-2022-s105en] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022] Open
Abstract
ABSTRACT Parkinson’s disease dementia (PDD) and dementia with Lewy bodies (DLB) represent the second most common type of degenerative dementia in patients aged 65 years and older, leading to progressive cognitive dysfunction and impaired quality of life. This study aims to provide a consensus based on a systematic Brazilian literature review and a comprehensive international review concerning PDD and DLB. Moreover, we sought to report on and give recommendations about the best diagnostic approaches focusing on primary and secondary care. Based on the available data, we recommend clinicians to apply at least one brief global cognitive instrument to assess PDD, such as the Mini-Mental State Examination and preferably the Montreal Cognitive Assessment and the Addenbrooke’s Cognitive Examination-Revised. Validated instruments to accurately assess functional abilities in Brazilian PD patients are still incipient. Further studies should focus on biomarkers with Brazilian cohorts.
Collapse
Affiliation(s)
| | | | | | | | - Maira Tonidandel Barbosa
- Universidade Federal de Minas Gerais, Brasil; Faculdade Ciências Médicas de Minas Gerais, Brasil
| | | | - Breno José Alencar Pires Barbosa
- Universidade de São Paulo, Brasil; Universidade Federal de Pernambuco, Brasil; Instituto de Medicina Integral Prof. Fernando Figueira, Brasil
| | - Lucas Porcello Schilling
- Pontifícia Universidade do Rio Grande do Sul, Brasil; Pontifícia Universidade do Rio Grande do Sul, Brasil; Pontifícia Universidade do Rio Grande do Sul, Brasil
| | | | | | | | | | | | | | | | | | | | | |
Collapse
|
6
|
Performance at the clock drawing test of individuals affected by Parkinson’s disease and healthy subjects: a retrospective study. Neurol Sci 2019; 41:843-849. [DOI: 10.1007/s10072-019-04167-w] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2019] [Accepted: 11/18/2019] [Indexed: 10/25/2022]
|
7
|
Optimized machine learning methods for prediction of cognitive outcome in Parkinson's disease. Comput Biol Med 2019; 111:103347. [DOI: 10.1016/j.compbiomed.2019.103347] [Citation(s) in RCA: 20] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/25/2019] [Revised: 06/03/2019] [Accepted: 06/27/2019] [Indexed: 11/17/2022]
|
8
|
Vásquez KA, Valverde EM, Aguilar DV, Gabarain HJH. Montreal Cognitive Assessment scale in patients with Parkinson Disease with normal scores in the Mini-Mental State Examination. Dement Neuropsychol 2019; 13:78-81. [PMID: 31073382 PMCID: PMC6497025 DOI: 10.1590/1980-57642018dn13-010008] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/06/2024] Open
Abstract
Several screening tests have been used for cognitive evaluation in Parkinson’s disease (PD).
Collapse
Affiliation(s)
- Krisly Arguedas Vásquez
- Geriatrician-Gerontologist Hospital Carlos Luis Valverde Vega, Caja Costarricense de Seguro Social, Alajuela, Costa Rica
| | - Erick Miranda Valverde
- Geriatrician-Gerontologist Memory Clinic, National Hospital of Geriatrics and Gerontology, Caja Costarricense de Seguro Social, San José, Costa Rica
| | - Daniel Valerio Aguilar
- Geriatrician-Gerontologist Memory Clinic, National Hospital of Geriatrics and Gerontology, Caja Costarricense de Seguro Social, San José, Costa Rica
| | - Henri-Jacques Hernández Gabarain
- Physician Neurologist Memory Clinic, National Hospital of Geriatrics and Gerontology, CAja Costarricense de Seguro Social, San José, Costa Rica
| |
Collapse
|