The use of low-density EEG for the classification of PPA and MCI
ObjectiveDissociating Primary Progressive Aphasia (PPA) from Mild Cognitive Impairment (MCI) is an important, yet challenging task. Given the need for low-cost and time-efficient classification, we used low-density electroencephalography (EEG) recordings to automatically classify PPA, MCI and health...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Human Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnhum.2025.1526554/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206697666281472 |
|---|---|
| author | Panteleimon Chriskos Panteleimon Chriskos Kyriaki Neophytou Christos A. Frantzidis Christos A. Frantzidis Jessica Gallegos Alexandros Afthinos Chiadi U. Onyike Argye Hillis Panagiotis D. Bamidis Kyrana Tsapkini Kyrana Tsapkini |
| author_facet | Panteleimon Chriskos Panteleimon Chriskos Kyriaki Neophytou Christos A. Frantzidis Christos A. Frantzidis Jessica Gallegos Alexandros Afthinos Chiadi U. Onyike Argye Hillis Panagiotis D. Bamidis Kyrana Tsapkini Kyrana Tsapkini |
| author_sort | Panteleimon Chriskos |
| collection | DOAJ |
| description | ObjectiveDissociating Primary Progressive Aphasia (PPA) from Mild Cognitive Impairment (MCI) is an important, yet challenging task. Given the need for low-cost and time-efficient classification, we used low-density electroencephalography (EEG) recordings to automatically classify PPA, MCI and healthy control (HC) individuals. To the best of our knowledge, this is the first attempt to classify individuals from these three populations at the same time.MethodsWe collected three-minute EEG recordings with an 8-channel system from eight MCI, fourteen PPA and eight HC individuals. Utilizing the Relative Wavelet Entropy method, we derived (i) functional connectivity, (ii) graph theory metrics and extracted (iii) various energy rhythms. Features from all three sources were used for classification. The k-Nearest Neighbor and Support Vector Machines classifiers were used.ResultsA 100% individual classification accuracy was achieved in the HC-MCI, HC-PPA, and MCI-PPA comparisons, and a 77.78% accuracy in the HC-MCI-PPA comparison.ConclusionWe showed for the first time that successful automatic classification between HC, MCI and PPA is possible with short, low-density EEG recordings. Despite methodological limitations of the current study, these results have important implications for clinical practice since they show that fast, low-cost and accurate disease diagnosis of these disorders is possible. Future studies need to establish the generalizability of the current findings with larger sample sizes and the efficient use of this methodology in a clinical setting. |
| format | Article |
| id | doaj-art-2794cd19d6de4f8ab8daf7e68a207634 |
| institution | Kabale University |
| issn | 1662-5161 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Human Neuroscience |
| spelling | doaj-art-2794cd19d6de4f8ab8daf7e68a2076342025-02-07T06:49:44ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612025-02-011910.3389/fnhum.2025.15265541526554The use of low-density EEG for the classification of PPA and MCIPanteleimon Chriskos0Panteleimon Chriskos1Kyriaki Neophytou2Christos A. Frantzidis3Christos A. Frantzidis4Jessica Gallegos5Alexandros Afthinos6Chiadi U. Onyike7Argye Hillis8Panagiotis D. Bamidis9Kyrana Tsapkini10Kyrana Tsapkini11Department of Neurology, Johns Hopkins School of Medicine, Baltimore, MD, United StatesLaboratory of Medical Physics and Digital Innovation, Faculty of Health Sciences, School of Medicine, Aristotle University of Thessaloniki, Thessaloniki, GreeceDepartment of Neurology, Johns Hopkins School of Medicine, Baltimore, MD, United StatesLaboratory of Medical Physics and Digital Innovation, Faculty of Health Sciences, School of Medicine, Aristotle University of Thessaloniki, Thessaloniki, GreeceSchool of Engineering and Physical Sciences, College of Health and Science, University of Lincoln., Lincoln, United KingdomDepartment of Neurology, Johns Hopkins School of Medicine, Baltimore, MD, United StatesCooper Medical School of Rowan University, Camden, NJ, United StatesDepartment of Psychiatry and Behavioral Sciences, Johns Hopkins School of Medicine, Baltimore, MD, United StatesDepartment of Neurology, Johns Hopkins School of Medicine, Baltimore, MD, United StatesLaboratory of Medical Physics and Digital Innovation, Faculty of Health Sciences, School of Medicine, Aristotle University of Thessaloniki, Thessaloniki, GreeceDepartment of Neurology, Johns Hopkins School of Medicine, Baltimore, MD, United StatesDepartment of Cognitive Science, Johns Hopkins University, Baltimore, MD, United StatesObjectiveDissociating Primary Progressive Aphasia (PPA) from Mild Cognitive Impairment (MCI) is an important, yet challenging task. Given the need for low-cost and time-efficient classification, we used low-density electroencephalography (EEG) recordings to automatically classify PPA, MCI and healthy control (HC) individuals. To the best of our knowledge, this is the first attempt to classify individuals from these three populations at the same time.MethodsWe collected three-minute EEG recordings with an 8-channel system from eight MCI, fourteen PPA and eight HC individuals. Utilizing the Relative Wavelet Entropy method, we derived (i) functional connectivity, (ii) graph theory metrics and extracted (iii) various energy rhythms. Features from all three sources were used for classification. The k-Nearest Neighbor and Support Vector Machines classifiers were used.ResultsA 100% individual classification accuracy was achieved in the HC-MCI, HC-PPA, and MCI-PPA comparisons, and a 77.78% accuracy in the HC-MCI-PPA comparison.ConclusionWe showed for the first time that successful automatic classification between HC, MCI and PPA is possible with short, low-density EEG recordings. Despite methodological limitations of the current study, these results have important implications for clinical practice since they show that fast, low-cost and accurate disease diagnosis of these disorders is possible. Future studies need to establish the generalizability of the current findings with larger sample sizes and the efficient use of this methodology in a clinical setting.https://www.frontiersin.org/articles/10.3389/fnhum.2025.1526554/fullprimary progressive aphasiamild cognitive impairmentclassificationelectroencephalography (EEG)functional connectivityenergy rhythms |
| spellingShingle | Panteleimon Chriskos Panteleimon Chriskos Kyriaki Neophytou Christos A. Frantzidis Christos A. Frantzidis Jessica Gallegos Alexandros Afthinos Chiadi U. Onyike Argye Hillis Panagiotis D. Bamidis Kyrana Tsapkini Kyrana Tsapkini The use of low-density EEG for the classification of PPA and MCI Frontiers in Human Neuroscience primary progressive aphasia mild cognitive impairment classification electroencephalography (EEG) functional connectivity energy rhythms |
| title | The use of low-density EEG for the classification of PPA and MCI |
| title_full | The use of low-density EEG for the classification of PPA and MCI |
| title_fullStr | The use of low-density EEG for the classification of PPA and MCI |
| title_full_unstemmed | The use of low-density EEG for the classification of PPA and MCI |
| title_short | The use of low-density EEG for the classification of PPA and MCI |
| title_sort | use of low density eeg for the classification of ppa and mci |
| topic | primary progressive aphasia mild cognitive impairment classification electroencephalography (EEG) functional connectivity energy rhythms |
| url | https://www.frontiersin.org/articles/10.3389/fnhum.2025.1526554/full |
| work_keys_str_mv | AT panteleimonchriskos theuseoflowdensityeegfortheclassificationofppaandmci AT panteleimonchriskos theuseoflowdensityeegfortheclassificationofppaandmci AT kyriakineophytou theuseoflowdensityeegfortheclassificationofppaandmci AT christosafrantzidis theuseoflowdensityeegfortheclassificationofppaandmci AT christosafrantzidis theuseoflowdensityeegfortheclassificationofppaandmci AT jessicagallegos theuseoflowdensityeegfortheclassificationofppaandmci AT alexandrosafthinos theuseoflowdensityeegfortheclassificationofppaandmci AT chiadiuonyike theuseoflowdensityeegfortheclassificationofppaandmci AT argyehillis theuseoflowdensityeegfortheclassificationofppaandmci AT panagiotisdbamidis theuseoflowdensityeegfortheclassificationofppaandmci AT kyranatsapkini theuseoflowdensityeegfortheclassificationofppaandmci AT kyranatsapkini theuseoflowdensityeegfortheclassificationofppaandmci AT panteleimonchriskos useoflowdensityeegfortheclassificationofppaandmci AT panteleimonchriskos useoflowdensityeegfortheclassificationofppaandmci AT kyriakineophytou useoflowdensityeegfortheclassificationofppaandmci AT christosafrantzidis useoflowdensityeegfortheclassificationofppaandmci AT christosafrantzidis useoflowdensityeegfortheclassificationofppaandmci AT jessicagallegos useoflowdensityeegfortheclassificationofppaandmci AT alexandrosafthinos useoflowdensityeegfortheclassificationofppaandmci AT chiadiuonyike useoflowdensityeegfortheclassificationofppaandmci AT argyehillis useoflowdensityeegfortheclassificationofppaandmci AT panagiotisdbamidis useoflowdensityeegfortheclassificationofppaandmci AT kyranatsapkini useoflowdensityeegfortheclassificationofppaandmci AT kyranatsapkini useoflowdensityeegfortheclassificationofppaandmci |