Entropy-Based Machine Learning Model for Fast Diagnosis and Monitoring of Parkinson’s Disease
This study presents the concept of a computationally efficient machine learning (ML) model for diagnosing and monitoring Parkinson’s disease (PD) using rest-state EEG signals (rs-EEG) from 20 PD subjects and 20 normal control (NC) subjects at a sampling rate of 128 Hz. Based on the comparative analy...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/20/8609 |
| _version_ | 1797572273440292864 |
|---|---|
| author | Maksim Belyaev Murugappan Murugappan Andrei Velichko Dmitry Korzun |
| author_facet | Maksim Belyaev Murugappan Murugappan Andrei Velichko Dmitry Korzun |
| author_sort | Maksim Belyaev |
| collection | DOAJ |
| description | This study presents the concept of a computationally efficient machine learning (ML) model for diagnosing and monitoring Parkinson’s disease (PD) using rest-state EEG signals (rs-EEG) from 20 PD subjects and 20 normal control (NC) subjects at a sampling rate of 128 Hz. Based on the comparative analysis of the effectiveness of entropy calculation methods, fuzzy entropy showed the best results in diagnosing and monitoring PD using rs-EEG, with classification accuracy (<i>A</i><sub>RKF</sub>) of ~99.9%. The most important frequency range of rs-EEG for PD-based diagnostics lies in the range of 0–4 Hz, and the most informative signals were mainly received from the right hemisphere of the head. It was also found that <i>A</i><sub>RKF</sub> significantly decreased as the length of rs-EEG segments decreased from 1000 to 150 samples. Using a procedure for selecting the most informative features, it was possible to reduce the computational costs of classification by 11 times, while maintaining an <i>A</i><sub>RKF</sub> ~99.9%. The proposed method can be used in the healthcare internet of things (H-IoT), where low-performance edge devices can implement ML sensors to enhance human resilience to PD. |
| first_indexed | 2024-03-10T20:53:54Z |
| format | Article |
| id | doaj.art-9d75524876d748589251cf45201cdbdc |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:53:54Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9d75524876d748589251cf45201cdbdc2023-11-19T18:05:32ZengMDPI AGSensors1424-82202023-10-012320860910.3390/s23208609Entropy-Based Machine Learning Model for Fast Diagnosis and Monitoring of Parkinson’s DiseaseMaksim Belyaev0Murugappan Murugappan1Andrei Velichko2Dmitry Korzun3Institute of Physics and Technology, Petrozavodsk State University, 185910 Petrozavodsk, RussiaIntelligent Signal Processing (ISP) Research Lab, Department of Electronics and Communication Engineering, Kuwait College of Science and Technology, Block 4, Kuwait City 13133, KuwaitInstitute of Physics and Technology, Petrozavodsk State University, 185910 Petrozavodsk, RussiaDepartment of Computer Science, Institute of Mathematics and Information Technology, Petrozavodsk State University, 185910 Petrozavodsk, RussiaThis study presents the concept of a computationally efficient machine learning (ML) model for diagnosing and monitoring Parkinson’s disease (PD) using rest-state EEG signals (rs-EEG) from 20 PD subjects and 20 normal control (NC) subjects at a sampling rate of 128 Hz. Based on the comparative analysis of the effectiveness of entropy calculation methods, fuzzy entropy showed the best results in diagnosing and monitoring PD using rs-EEG, with classification accuracy (<i>A</i><sub>RKF</sub>) of ~99.9%. The most important frequency range of rs-EEG for PD-based diagnostics lies in the range of 0–4 Hz, and the most informative signals were mainly received from the right hemisphere of the head. It was also found that <i>A</i><sub>RKF</sub> significantly decreased as the length of rs-EEG segments decreased from 1000 to 150 samples. Using a procedure for selecting the most informative features, it was possible to reduce the computational costs of classification by 11 times, while maintaining an <i>A</i><sub>RKF</sub> ~99.9%. The proposed method can be used in the healthcare internet of things (H-IoT), where low-performance edge devices can implement ML sensors to enhance human resilience to PD.https://www.mdpi.com/1424-8220/23/20/8609Parkinson’s diseaseEEGdiagnosisentropymachine learningmonitoring |
| spellingShingle | Maksim Belyaev Murugappan Murugappan Andrei Velichko Dmitry Korzun Entropy-Based Machine Learning Model for Fast Diagnosis and Monitoring of Parkinson’s Disease Sensors Parkinson’s disease EEG diagnosis entropy machine learning monitoring |
| title | Entropy-Based Machine Learning Model for Fast Diagnosis and Monitoring of Parkinson’s Disease |
| title_full | Entropy-Based Machine Learning Model for Fast Diagnosis and Monitoring of Parkinson’s Disease |
| title_fullStr | Entropy-Based Machine Learning Model for Fast Diagnosis and Monitoring of Parkinson’s Disease |
| title_full_unstemmed | Entropy-Based Machine Learning Model for Fast Diagnosis and Monitoring of Parkinson’s Disease |
| title_short | Entropy-Based Machine Learning Model for Fast Diagnosis and Monitoring of Parkinson’s Disease |
| title_sort | entropy based machine learning model for fast diagnosis and monitoring of parkinson s disease |
| topic | Parkinson’s disease EEG diagnosis entropy machine learning monitoring |
| url | https://www.mdpi.com/1424-8220/23/20/8609 |
| work_keys_str_mv | AT maksimbelyaev entropybasedmachinelearningmodelforfastdiagnosisandmonitoringofparkinsonsdisease AT murugappanmurugappan entropybasedmachinelearningmodelforfastdiagnosisandmonitoringofparkinsonsdisease AT andreivelichko entropybasedmachinelearningmodelforfastdiagnosisandmonitoringofparkinsonsdisease AT dmitrykorzun entropybasedmachinelearningmodelforfastdiagnosisandmonitoringofparkinsonsdisease |