Nacim Betrouni1, Arnaud Delval1,2, Laurence Chaton1,2, Luc Defebvre1,3, Annelien Duits4, Anja Moonen4, Albert F G Leentjens4, Kathy Dujardin1,3. 1. University Lille, Inserm, CHU Lille, Degenerative & Vascular Cognitive Disorders, Lille, France. 2. Centre Hospitalier Universitaire Lille, Clinical Neurophysiology Department, Lille, France. 3. Centre Hospitalier Universitaire Lille, Neurology and Movement Disorders Department, Lille, France. 4. Maastricht University Medical Center, Maastricht, The Netherlands.
Abstract
BACKGROUND: Cognitive symptoms are common in patients with Parkinson's disease. Characterization of a patient's cognitive profile is an essential step toward the identification of predictors of cognitive worsening. OBJECTIVE: The aim of this study was to investigate the use of the combination of resting-state EEG and data-mining techniques to build characterization models. METHODS: Dense EEG data from 118 patients with Parkinson's disease, classified into 5 different groups according to the severity of their cognitive impairments, were considered. Spectral power analysis within 7 frequency bands was performed on the EEG signals. The obtained quantitative EEG features of 100 patients were mined using 2 machine-learning algorithms to build and train characterization models, namely, support vector machines and k-nearest neighbors models. The models were then blindly tested on data from 18 patients. RESULTS: The overall classification accuracies were 84% and 88% for the support vector machines and k-nearest algorithms, respectively. The worst classifications were observed for patients from groups with small sample sizes, corresponding to patients with the severe cognitive deficits. Whereas for the remaining groups for whom an accurate diagnosis was required to plan the future healthcare, the classification was very accurate. CONCLUSION: These results suggest that EEG features computed from a daily clinical practice exploration modality in-that it is nonexpensive, available anywhere, and requires minimal cooperation from the patient-can be used as a screening method to identify the severity of cognitive impairment in patients with Parkinson's disease.
BACKGROUND:Cognitive symptoms are common in patients with Parkinson's disease. Characterization of a patient's cognitive profile is an essential step toward the identification of predictors of cognitive worsening. OBJECTIVE: The aim of this study was to investigate the use of the combination of resting-state EEG and data-mining techniques to build characterization models. METHODS: Dense EEG data from 118 patients with Parkinson's disease, classified into 5 different groups according to the severity of their cognitive impairments, were considered. Spectral power analysis within 7 frequency bands was performed on the EEG signals. The obtained quantitative EEG features of 100 patients were mined using 2 machine-learning algorithms to build and train characterization models, namely, support vector machines and k-nearest neighbors models. The models were then blindly tested on data from 18 patients. RESULTS: The overall classification accuracies were 84% and 88% for the support vector machines and k-nearest algorithms, respectively. The worst classifications were observed for patients from groups with small sample sizes, corresponding to patients with the severe cognitive deficits. Whereas for the remaining groups for whom an accurate diagnosis was required to plan the future healthcare, the classification was very accurate. CONCLUSION: These results suggest that EEG features computed from a daily clinical practice exploration modality in-that it is nonexpensive, available anywhere, and requires minimal cooperation from the patient-can be used as a screening method to identify the severity of cognitive impairment in patients with Parkinson's disease.
Authors: Dag Aarsland; Lucia Batzu; Glenda M Halliday; Gert J Geurtsen; Clive Ballard; K Ray Chaudhuri; Daniel Weintraub Journal: Nat Rev Dis Primers Date: 2021-07-01 Impact factor: 52.329
Authors: Maria L Bringas Vega; Ivonne Pedroso Ibáñez; Fuleah A Razzaq; Min Zhang; Lilia Morales Chacón; Peng Ren; Lidice Galan Garcia; Peng Gan; Trinidad Virues Alba; Carlos Lopez Naranjo; Marjan Jahanshahi; Jorge Bosch-Bayard; Pedro A Valdes-Sosa Journal: Front Neurosci Date: 2022-06-30 Impact factor: 5.152
Authors: Tiago A Mestre; Seyed-Mohammad Fereshtehnejad; Daniela Berg; Nicolaas I Bohnen; Kathy Dujardin; Roberto Erro; Alberto J Espay; Glenda Halliday; Jacobus J van Hilten; Michele T Hu; Beomseok Jeon; Christine Klein; Albert F G Leentjens; Johan Marinus; Brit Mollenhauer; Ronald Postuma; Rajasumi Rajalingam; Mayela Rodríguez-Violante; Tanya Simuni; D James Surmeier; Daniel Weintraub; Michael P McDermott; Michael Lawton; Connie Marras Journal: J Parkinsons Dis Date: 2021 Impact factor: 5.568