Md Fahim Anjum1, Soura Dasgupta2, Raghuraman Mudumbai3, Arun Singh4, James F Cavanagh5, Nandakumar S Narayanan6. 1. Department of Electrical and Computer Engineering, The University of Iowa, Iowa, USA. Electronic address: mdfahim-anjum@uiowa.edu. 2. Department of Electrical and Computer Engineering, The University of Iowa, Iowa, USA; Shandong Academy of Sciences, Shandong, Jinan, China. 3. Department of Electrical and Computer Engineering, The University of Iowa, Iowa, USA. 4. Division of Basic Biomedical Sciences, Sanford School of Medicine, University of South Dakota, South Dakota, USA. 5. Department of Psychology, University of New Mexico, New Mexico, USA. 6. Department of Neurology, The University of Iowa, Iowa, USA.
Abstract
OBJECTIVE: We have developed and validated a novel EEG-based signal processing approach to distinguish PD and control patients: Linear-predictive-coding EEG Algorithm for PD (LEAPD). This method efficiently encodes EEG time series into features that can detect PD in a computationally fast manner amenable to real time applications. METHODS: We included a total of 41 PD patients and 41 demographically-matched controls from New Mexico and Iowa. Data for all participants from New Mexico (27 PD patients and 27 controls) were used to evaluate in-sample LEAPD performance, with extensive cross-validation. Participants from Iowa (14 PD patients and 14 controls) were used for out-of-sample tests. Our method utilized data from six EEG leads which were as little as 2 min long. RESULTS: For the in-sample dataset, LEAPD differentiated PD patients from controls with 85.3 ± 0.1% diagnostic accuracy, 93.3 ± 0.5% area under the receiver operating characteristics curve (AUC), 87.9 ± 0.9% sensitivity, and 82.7 ± 1.1% specificity, with multiple cross-validations. After head-to-head comparison with state-of-the-art methods using our dataset, LEAPD showed a 13% increase in accuracy and a 15.5% increase in AUC. When the trained classifier was applied to a distinct out-of-sample dataset, LEAPD showed reliable performance with 85.7% diagnostic accuracy, 85.2% AUC, 85.7% sensitivity, and 85.7% specificity. No statistically significant effect of levodopa-ON and levodopa-OFF sessions were found. CONCLUSION: We describe LEAPD, an efficient algorithm that is suitable for real time application and captures spectral EEG features using few parameters and reliably differentiates PD patients from demographically-matched controls.
OBJECTIVE: We have developed and validated a novel EEG-based signal processing approach to distinguish PD and control patients: Linear-predictive-coding EEG Algorithm for PD (LEAPD). This method efficiently encodes EEG time series into features that can detect PD in a computationally fast manner amenable to real time applications. METHODS: We included a total of 41 PD patients and 41 demographically-matched controls from New Mexico and Iowa. Data for all participants from New Mexico (27 PD patients and 27 controls) were used to evaluate in-sample LEAPD performance, with extensive cross-validation. Participants from Iowa (14 PD patients and 14 controls) were used for out-of-sample tests. Our method utilized data from six EEG leads which were as little as 2 min long. RESULTS: For the in-sample dataset, LEAPD differentiated PD patients from controls with 85.3 ± 0.1% diagnostic accuracy, 93.3 ± 0.5% area under the receiver operating characteristics curve (AUC), 87.9 ± 0.9% sensitivity, and 82.7 ± 1.1% specificity, with multiple cross-validations. After head-to-head comparison with state-of-the-art methods using our dataset, LEAPD showed a 13% increase in accuracy and a 15.5% increase in AUC. When the trained classifier was applied to a distinct out-of-sample dataset, LEAPD showed reliable performance with 85.7% diagnostic accuracy, 85.2% AUC, 85.7% sensitivity, and 85.7% specificity. No statistically significant effect of levodopa-ON and levodopa-OFF sessions were found. CONCLUSION: We describe LEAPD, an efficient algorithm that is suitable for real time application and captures spectral EEG features using few parameters and reliably differentiates PD patients from demographically-matched controls.
Authors: H Tanaka; T Koenig; R D Pascual-Marqui; K Hirata; K Kochi; D Lehmann Journal: Dement Geriatr Cogn Disord Date: 2000 Jan-Feb Impact factor: 2.959
Authors: Simon Little; Alex Pogosyan; Spencer Neal; Baltazar Zavala; Ludvic Zrinzo; Marwan Hariz; Thomas Foltynie; Patricia Limousin; Keyoumars Ashkan; James FitzGerald; Alexander L Green; Tipu Z Aziz; Peter Brown Journal: Ann Neurol Date: 2013-07-12 Impact factor: 10.422
Authors: Claudia Lainscsek; Manuel E Hernandez; Jonathan Weyhenmeyer; Terrence J Sejnowski; Howard Poizner Journal: Front Neurol Date: 2013-12-11 Impact factor: 4.003
Authors: Sharon Hassin-Baer; Oren S Cohen; Simon Israeli-Korn; Gilad Yahalom; Sandra Benizri; Daniel Sand; Gil Issachar; Amir B Geva; Revital Shani-Hershkovich; Ziv Peremen Journal: PLoS One Date: 2022-01-07 Impact factor: 3.240
Authors: Arturo I Espinoza; Patrick May; Md Fahim Anjum; Arun Singh; Rachel C Cole; Nicholas Trapp; Soura Dasgupta; Nandakumar S Narayanan Journal: Clin Park Relat Disord Date: 2022-09-27
Authors: Qiang Zhang; Georgina M Aldridge; Nandakumar S Narayanan; Steven W Anderson; Ergun Y Uc Journal: Neurotherapeutics Date: 2020-11-17 Impact factor: 6.088