Research Article
BibTex RIS Cite

Makine Öğrenme Yöntemleri ile EEG Sı̇nyallerı̇nden Alzheimer Hastalığı Tanısı

Year 2024, Volume: 14 Issue: 1, 114 - 130, 15.03.2024
https://doi.org/10.31466/kfbd.1359324

Abstract

Alzheimer bilişsel ve nörolojik işlevlerin ilerleyici kaybı olan, insan yaşamını olumsuz yönde etkileyen, geri dönüşümü mümkün olmayan bir tür nörodejeneratif hastalıktır. Hastalığın tedavisi mümkün olmadığından, erken tanı ile ilerleyişi yavaşlatmak büyük önem taşımaktadır. Tanı aşamasının uzun sürmesi tedavinin gecikmesine ve bilişsel, nörolojik kayıpların artmasına sebep olmaktadır. Bu çalışmanın amacı, kayıpların en aza indirgenmesi için Elektroensefalogram (EEG) sinyallerinden Alzheimer hastalığının (AH) tanısını makine öğrenme yöntemleri ile gerçekleştirmektir. Yapılan çalışmada AH’lı 24 kişi ve sağlıklı 24 kişinin EEG sinyalleri %50 örtüşme ile 4 saniyelik epoklara ayrılmıştır. Sinyallerin Bağımsız Bileşen Analizi (ICA) değerleri hesaplanmış ve EEG kanallarından ICA değerlerine göre otomatik gürültü temizle işlemi yapılmıştır. Her bir sinyalin zaman alanından spektral alana geçişi Welch metodu kullanılarak gerçekleştirilmiştir. 1-30 Hz aralığında Welch Spektral analizi ile Güç Spektral Yoğunluğu (PSD) elde edilen sinyallerden 20 adet istatistiksel ve spektral özellik çıkarımı yapılmış ve öznitelik vektörü oluşturulmuştur. Spearman korelasyon katsayısı ile her özelliğin etiket ile korelasyon ilişkisine bakılmış ve eşik değerine göre 9 özellik seçimi yapılarak yeni öznitelik vektörü oluşturulmuştur. Elde edilen öznitelik vektörlerinin %70’i eğitim, %30’u test olarak ayrılmıştır. Makine öğrenme (ML) yöntemlerinden Destek Vektör Makineleri (SVM) ve k-En Yakın Komşu (kNN) yöntemleri 10 kat çapraz doğrulama ile eğitim ve test işlemleri Temel Bileşen Analizi (PCA) uygulanmadan ve uygulanarak gerçekleştirilmiştir. Çıkan sonuçlar doğruluk, duyarlılık, özgüllük, hassasiyet ve F-Skor değerlerine göre karşılaştırılmıştır. AH tanısında en iyi doğruluk oranı 20 özellikten oluşan öznitelik vektörüne PCA uygulanmasıyla %96.59 SVM ile elde edilmiştir.

References

  • AlSharabi, K., Salamah, Y. B., Abdurraqeeb, A. M., Aljalal, M., and Alturki, F. A. (2022). EEG signal processing for Alzheimer’s disorders using discrete wavelet transform and machine learning approaches. IEEE Access, 10, 89781-89797.
  • Aslan, Z. (2022). EEG sinyallerini kullanarak Alzheimer hastalığının otomatik tespiti için bilgisayar destekli tanı sistemi. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 13(2), 213-220.
  • Bairagi, V. (2018). EEG signal analysis for early diagnosis of Alzheimer disease using spectral and wavelet based features. International Journal of Information Technology, 10(3), 403-412.
  • Benesty, J., Chen, J., and Huang, Y. (2008). On the importance of the Pearson correlation coefficient in noise reduction. IEEE Transactions on Audio, Speech, and Language Processing, 16(4), 757-765.
  • Büyükgöze, S. (2019). Beyin Bilgisayar Arayüzleri ve Uygulama Alanları. Mühendislik Alanında Araştırma Makaleleri. Gece Kitaplığı. ISBN: 978-625-7958-40-0.
  • Durongbhan, P., Zhao, Y., Chen, L., Zis, P., De Marco, M., Unwin, Z. C., ... and Sarrigiannis, P. G. (2019). A dementia classification framework using frequency and time-frequency features based on EEG signals. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 27(5), 826-835.
  • Falk, T. H., Fraga, F. J., Trambaiolli, L., and Anghinah, R. (2012). EEG amplitude modulation analysis for semi-automated diagnosis of Alzheimer’s disease. EURASIP Journal on Advances in Signal Processing, 2012, 1-9.
  • Fiscon, G., Weitschek, E., Cialini, A., Felici, G., Bertolazzi, P., De Salvo, S., ... and De Cola, M. C. (2018). Combining EEG signal processing with supervised methods for Alzheimer’s patients classification. BMC medical informatics and decision making, 18(1), 1-10.
  • Fonteijn, H. M., Modat, M., Clarkson, M. J., Barnes, J., Lehmann, M., Hobbs, N. Z., ... and Alexander, D. C. (2012). An event-based model for disease progression and its application in familial Alzheimer's disease and Huntington's disease. NeuroImage, 60(3), 1880-1889.
  • Garcés, M. A., and Orosco, L. L. (2008). EEG signal processing in brain–computer interface. In Smart wheelchairs and brain-computer interfaces (pp. 95-110). Academic Press.
  • Ghanemi, A. (2015). Alzheimer’s disease therapies: Selected advances and future perspectives. Alexandria Journal of Medicine, 51(1), 1-3.
  • Göker, H. (2023). Detection of alzheimer's disease from electroencephalography (EEG) signals using multitaper and ensemble learning methods. Uludağ Üniversitesi Mühendislik Fakültesi Dergisi, 28(1), 141-152.
  • Göker, H. (2023). Welch Spectral Analysis and Deep Learning Approach for Diagnosing Alzheimer's Disease from Resting-State EEG Recordings. Traitement du Signal, 40(1).
  • Günal, S. (2001). Örüntü tanıma uygulamalarında alt uzay analiziyle öznitelik seçimi ve sınıflandırma. Doktora tezi, Osmangazi Üniversitesi, Fen Bilimleri Enstitüsü, Eskişehir.
  • Kurita, T. (2019). Principal component analysis (PCA). Computer Vision: A Reference Guide, 1-4. Miltiadous, A., Gionanidis, E., Tzimourta, K. D., Giannakeas, N., and Tzallas, A. T. (2023). DICE-net: A Novel Convolution-Transformer Architecture for Alzheimer Detection in EEG Signals. IEEE Access.
  • Morabito, F. C., Campolo, M., Ieracitano, C., Ebadi, J. M., Bonanno, L., Bramanti, A., ... and Bramanti, P. (2016, September). Deep convolutional neural networks for classification of mild cognitive impaired and Alzheimer's disease patients from scalp EEG recordings. In 2016 IEEE 2nd International Forum on Research and Technologies for Society and Industry Leveraging a better tomorrow (RTSI) (pp. 1-6). IEEE.
  • Parhi, K. K., and Ayinala, M. (2013). Low-complexity Welch power spectral density computation. IEEE Transactions on Circuits and Systems I: Regular Papers, 61(1), 172-182.
  • Patterson, C. (2018). World Alzheimer report 2018: the state of the art of dementia research: new frontiers. Alzheimer’s Disease International (ADI): London, UK, 2(4), 14-20.
  • Pineda, A. M., Ramos, F. M., Betting, L. E., and Campanharo, A. S. (2020). Quantile graphs for EEG-based diagnosis of Alzheimer’s disease. Plos one, 15(6), e0231169.
  • Sadık, E. Ş. (2022). Comparison Of Machine Learning Algorithms In The Detection Of Alzheimer's Disease. Avrupa Bilim ve Teknoloji Dergisi, (42), 1-5.
  • Safi, M. S., and Safi, S. M. M. (2021). Early detection of Alzheimer’s disease from EEG signals using Hjorth parameters. Biomedical Signal Processing and Control, 65, 102338.
  • Smith, E. E., Reznik, S. J., Stewart, J. L., and Allen, J. J. (2017). Assessing and conceptualizing frontal EEG asymmetry: An updated primer on recording, processing, analyzing, and interpreting frontal alpha asymmetry. International Journal of Psychophysiology, 111, 98-114.
  • Vecchio, F., Miraglia, F., Alù, F., Menna, M., Judica, E., Cotelli, M., and Rossini, P. M. (2020). Classification of Alzheimer’s disease with respect to physiological aging with innovative EEG biomarkers in a machine learning implementation. Journal of Alzheimer's Disease, 75(4), 1253-1261.
  • Xiao, C., Ye, J., Esteves, R. M., and Rong, C. (2016). Using Spearman's correlation coefficients for exploratory data analysis on big dataset. Concurrency and Computation: Practice and Experience, 28(14), 3866-3878.

Diagnosis of Alzheimer's Disease from EEG Signals with Machine Learning Methods

Year 2024, Volume: 14 Issue: 1, 114 - 130, 15.03.2024
https://doi.org/10.31466/kfbd.1359324

Abstract

Alzheimer's is an irreversible neurodegenerative disease with progressive loss of cognitive and neurological functions that negatively affects human life. Since the disease is incurable, early diagnosis and slowing down the progression is of great importance. Prolonged diagnosis leads to delayed treatment and increased cognitive and neurological deficits. The aim of this study is to diagnose Alzheimer's disease (AD) from Electroencephalogram (EEG) signals using machine learning methods to minimize these losses. In this study, EEG signals of 24 people with AD and 24 healthy people were divided into 4-second epochs with 50% overlap. Independent Component Analysis (ICA) values of the signals were calculated and automatic noise removal was performed from the EEG channels according to the ICA values. The transition of each signal from the time domain to the spectral domain was performed using the Welch method. In the range of 1-30 Hz, 20 statistical and spectral features were extracted from the signals whose Power Spectral Density (PSD) was obtained by Welch Spectral analysis and a feature vector was created. Spearman correlation coefficient was used to correlate each feature with the label and 9 features were selected according to the threshold value and a new feature vector was created. Of the feature vectors obtained, 70% of the feature vectors were allocated as training and 30% as test. Machine learning (ML) methods Support Vector Machines (SVM) and k-Nearest Neighbor (kNN) methods were trained and tested with 10-fold cross validation without and with Principal Component Analysis (PCA). The results were compared according to accuracy, sensitivity, specificity, precision and F-Score values. The best accuracy rate for AD diagnosis was 96.59% with SVM by applying PCA to a feature vector consisting of 20 features.

References

  • AlSharabi, K., Salamah, Y. B., Abdurraqeeb, A. M., Aljalal, M., and Alturki, F. A. (2022). EEG signal processing for Alzheimer’s disorders using discrete wavelet transform and machine learning approaches. IEEE Access, 10, 89781-89797.
  • Aslan, Z. (2022). EEG sinyallerini kullanarak Alzheimer hastalığının otomatik tespiti için bilgisayar destekli tanı sistemi. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 13(2), 213-220.
  • Bairagi, V. (2018). EEG signal analysis for early diagnosis of Alzheimer disease using spectral and wavelet based features. International Journal of Information Technology, 10(3), 403-412.
  • Benesty, J., Chen, J., and Huang, Y. (2008). On the importance of the Pearson correlation coefficient in noise reduction. IEEE Transactions on Audio, Speech, and Language Processing, 16(4), 757-765.
  • Büyükgöze, S. (2019). Beyin Bilgisayar Arayüzleri ve Uygulama Alanları. Mühendislik Alanında Araştırma Makaleleri. Gece Kitaplığı. ISBN: 978-625-7958-40-0.
  • Durongbhan, P., Zhao, Y., Chen, L., Zis, P., De Marco, M., Unwin, Z. C., ... and Sarrigiannis, P. G. (2019). A dementia classification framework using frequency and time-frequency features based on EEG signals. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 27(5), 826-835.
  • Falk, T. H., Fraga, F. J., Trambaiolli, L., and Anghinah, R. (2012). EEG amplitude modulation analysis for semi-automated diagnosis of Alzheimer’s disease. EURASIP Journal on Advances in Signal Processing, 2012, 1-9.
  • Fiscon, G., Weitschek, E., Cialini, A., Felici, G., Bertolazzi, P., De Salvo, S., ... and De Cola, M. C. (2018). Combining EEG signal processing with supervised methods for Alzheimer’s patients classification. BMC medical informatics and decision making, 18(1), 1-10.
  • Fonteijn, H. M., Modat, M., Clarkson, M. J., Barnes, J., Lehmann, M., Hobbs, N. Z., ... and Alexander, D. C. (2012). An event-based model for disease progression and its application in familial Alzheimer's disease and Huntington's disease. NeuroImage, 60(3), 1880-1889.
  • Garcés, M. A., and Orosco, L. L. (2008). EEG signal processing in brain–computer interface. In Smart wheelchairs and brain-computer interfaces (pp. 95-110). Academic Press.
  • Ghanemi, A. (2015). Alzheimer’s disease therapies: Selected advances and future perspectives. Alexandria Journal of Medicine, 51(1), 1-3.
  • Göker, H. (2023). Detection of alzheimer's disease from electroencephalography (EEG) signals using multitaper and ensemble learning methods. Uludağ Üniversitesi Mühendislik Fakültesi Dergisi, 28(1), 141-152.
  • Göker, H. (2023). Welch Spectral Analysis and Deep Learning Approach for Diagnosing Alzheimer's Disease from Resting-State EEG Recordings. Traitement du Signal, 40(1).
  • Günal, S. (2001). Örüntü tanıma uygulamalarında alt uzay analiziyle öznitelik seçimi ve sınıflandırma. Doktora tezi, Osmangazi Üniversitesi, Fen Bilimleri Enstitüsü, Eskişehir.
  • Kurita, T. (2019). Principal component analysis (PCA). Computer Vision: A Reference Guide, 1-4. Miltiadous, A., Gionanidis, E., Tzimourta, K. D., Giannakeas, N., and Tzallas, A. T. (2023). DICE-net: A Novel Convolution-Transformer Architecture for Alzheimer Detection in EEG Signals. IEEE Access.
  • Morabito, F. C., Campolo, M., Ieracitano, C., Ebadi, J. M., Bonanno, L., Bramanti, A., ... and Bramanti, P. (2016, September). Deep convolutional neural networks for classification of mild cognitive impaired and Alzheimer's disease patients from scalp EEG recordings. In 2016 IEEE 2nd International Forum on Research and Technologies for Society and Industry Leveraging a better tomorrow (RTSI) (pp. 1-6). IEEE.
  • Parhi, K. K., and Ayinala, M. (2013). Low-complexity Welch power spectral density computation. IEEE Transactions on Circuits and Systems I: Regular Papers, 61(1), 172-182.
  • Patterson, C. (2018). World Alzheimer report 2018: the state of the art of dementia research: new frontiers. Alzheimer’s Disease International (ADI): London, UK, 2(4), 14-20.
  • Pineda, A. M., Ramos, F. M., Betting, L. E., and Campanharo, A. S. (2020). Quantile graphs for EEG-based diagnosis of Alzheimer’s disease. Plos one, 15(6), e0231169.
  • Sadık, E. Ş. (2022). Comparison Of Machine Learning Algorithms In The Detection Of Alzheimer's Disease. Avrupa Bilim ve Teknoloji Dergisi, (42), 1-5.
  • Safi, M. S., and Safi, S. M. M. (2021). Early detection of Alzheimer’s disease from EEG signals using Hjorth parameters. Biomedical Signal Processing and Control, 65, 102338.
  • Smith, E. E., Reznik, S. J., Stewart, J. L., and Allen, J. J. (2017). Assessing and conceptualizing frontal EEG asymmetry: An updated primer on recording, processing, analyzing, and interpreting frontal alpha asymmetry. International Journal of Psychophysiology, 111, 98-114.
  • Vecchio, F., Miraglia, F., Alù, F., Menna, M., Judica, E., Cotelli, M., and Rossini, P. M. (2020). Classification of Alzheimer’s disease with respect to physiological aging with innovative EEG biomarkers in a machine learning implementation. Journal of Alzheimer's Disease, 75(4), 1253-1261.
  • Xiao, C., Ye, J., Esteves, R. M., and Rong, C. (2016). Using Spearman's correlation coefficients for exploratory data analysis on big dataset. Concurrency and Computation: Practice and Experience, 28(14), 3866-3878.
There are 24 citations in total.

Details

Primary Language Turkish
Subjects Computer Software
Journal Section Articles
Authors

Yeliz Şenkaya 0000-0001-6527-6313

Çetin Kurnaz 0000-0003-3436-899X

Publication Date March 15, 2024
Published in Issue Year 2024 Volume: 14 Issue: 1

Cite

APA Şenkaya, Y., & Kurnaz, Ç. (2024). Makine Öğrenme Yöntemleri ile EEG Sı̇nyallerı̇nden Alzheimer Hastalığı Tanısı. Karadeniz Fen Bilimleri Dergisi, 14(1), 114-130. https://doi.org/10.31466/kfbd.1359324