AN AUTOMATED PARKINSON’S DISEASE DIAGNOSIS: A FEATURE SELECTION APPROACH

Sibel Çimen; Bülent Bolat

Makale detayları

AN AUTOMATED PARKINSON’S DISEASE DIAGNOSIS: A FEATURE SELECTION APPROACH

Yazarlar:

Sibel Çimen | Bülent Bolat

Yayıncı:

Süleyman Demirel University

Ana Başlıklar:

Biyomedikal Tanı | Sinyal İşleme

Dergi:

Mühendislik Bilimleri ve Tasarım Dergisi Vol.12 Issue 4, pp.724-735

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001334901

pISSN:

1308-6693

Anahtar kelimeler:

Özet:

 Parkinsons disease is one of the neurodegenerative disorders that significantly affect human health. Patients experience various negative effects such as tremors, walking disorders, and impaired speech. The disease also causes instability in walking, leading to tremors, and affects their writing skills. Studies on detection of disease generally focus on speech analysis. However, PD can be diagnosed by exploiting the loss of motor ability. In this work, a data set which was recorded at Cerrahpasa Faculty of Medicine, Istanbul University is considered. The data were collected from 15 healthy subjects and 75 with Parkinsons Disease.by a graphic tablet. Each subject asked to draw a spiral in two different conditions which are named as static spiral test SST and dynamic spiral test DST respectively, and the drawings transformed into X, Y and Z axis of movement, Grip Angle, and Pressure data. During the study, the effectiveness of SST and DST conditions are considered. Various machine learning algorithms have been tested to determine the best classifier. The effect of features was also considered by utilizing a feature elimination process. As a result, the best classification performance was obtained as 93.55 by using Kernel Naïve Bayes network with SST data, by omitting Z axis.

 Parkinsons disease is one of the neurodegenerative disorders that significantly affect human health. Patients experience various negative effects such as tremors, walking disorders, and impaired speech. The disease also causes instability in walking, leading to tremors, and affects their writing skills. Studies on detection of disease generally focus on speech analysis. However, PD can be diagnosed by exploiting the loss of motor ability. In this work, a data set which was recorded at Cerrahpasa Faculty of Medicine, Istanbul University is considered. The data were collected from 15 healthy subjects and 75 with Parkinsons Disease.by a graphic tablet. Each subject asked to draw a spiral in two different conditions which are named as static spiral test SST and dynamic spiral test DST respectively, and the drawings transformed into X, Y and Z axis of movement, Grip Angle, and Pressure data. During the study, the effectiveness of SST and DST conditions are considered. Various machine learning algorithms have been tested to determine the best classifier. The effect of features was also considered by utilizing a feature elimination process. As a result, the best classification performance was obtained as 93.55 by using Kernel Naïve Bayes network with SST data, by omitting Z axis.

 Parkinsons disease is one of the neurodegenerative disorders that significantly affect human health. Patients experience various negative effects such as tremors, walking disorders, and impaired speech. The disease also causes instability in walking, leading to tremors, and affects their writing skills. Studies on detection of disease generally focus on speech analysis. However, PD can be diagnosed by exploiting the loss of motor ability. In this work, a data set which was recorded at Cerrahpasa Faculty of Medicine, Istanbul University is considered. The data were collected from 15 healthy subjects and 75 with Parkinsons Disease.by a graphic tablet. Each subject asked to draw a spiral in two different conditions which are named as static spiral test SST and dynamic spiral test DST respectively, and the drawings transformed into X, Y and Z axis of movement, Grip Angle, and Pressure data. During the study, the effectiveness of SST and DST conditions are considered. Various machine learning algorithms have been tested to determine the best classifier. The effect of features was also considered by utilizing a feature elimination process. As a result, the best classification performance was obtained as 93.55 by using Kernel Naïve Bayes network with SST data, by omitting Z axis.

 Parkinson hastalığı, insan sağlığını önemli ölçüde etkileyen nörodejeneratif bozukluklardan biridir. Hastalar, titreme, yürüme bozuklukları ve konuşma bozuklukları gibi çeşitli olumsuz etkiler yaşarlar. Hastalık ayrıca yürüme dengesizliğine, titremelere ve yazma becerilerini etkiler. Hastalığın tespiti üzerine yapılan çalışmalar genellikle konuşma analizine odaklanmaktadır. Ancak, Parkinson hastalığı motor yetenek kaybını kullanarak teşhis edilebilir. Bu çalışmada, İstanbul Üniversitesi Cerrahpaşa Tıp Fakültesinde kaydedilen bir veri seti incelenmektedir. Veriler, 15 sağlıklı denekten ve Parkinson hastalığı olan 75 denekten bir grafik tableti kullanılarak toplandı. Her denekten, sırasıyla statik spiral testi SST ve dinamik spiral testi DST olarak adlandırılan iki farklı koşul altında bir spiral çizmesi istenmiş ve çizimler X, Y ve Z eksenlerine hareket, Kavrama Açısı ve Basınç verilerine dönüştürülmüştür. Çalışma sırasında, SST ve DST koşullarının etkinliği dikkate alınmıştır. En iyi sınıflandırıcıyı belirlemek için çeşitli makine öğrenimi algoritmaları test edilmiştir. Özelliklerin etkisi, bir özellik elemesi süreci kullanılarak da dikkate alınmıştır. Sonuç olarak, Z eksenini ihmal ederek SST verileri ile Kernel Naive Bayes ağı kullanılarak 93,55lik en iyi sınıflandırma performansı elde edilmiştir.

Makale detayları

AN AUTOMATED PARKINSON’S DISEASE DIAGNOSIS: A FEATURE SELECTION APPROACH

Yazarlar:

Sibel Çimen | Bülent Bolat

Yayıncı:

Süleyman Demirel University

Ana Başlıklar:

Biyomedikal Tanı | Sinyal İşleme

Dergi:

Mühendislik Bilimleri ve Tasarım Dergisi Vol.12 Issue 4, pp.724-735

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001334901

pISSN:

1308-6693

Artificial Intelligence

Biomedical Computing

Biomedical Signal

Machine Learning

Supervised Learning.Yapay Zeka

Biyomedikal Hesaplama

Biyomedikal Sinyal

Makine Öğrenmesi

Eğiticili Öğrenme.

Sayı

Makale detayları

Yazarlar: Sibel Çimen | Bülent Bolat

Yayıncı: Süleyman Demirel University

Ana Başlıklar: Biyomedikal Tanı | Sinyal İşleme

Dergi: Mühendislik Bilimleri ve Tasarım Dergisi Vol.12 Issue 4, pp.724-735

Belge Tipi: Makale

Yayın Tarihi: 12/2024

Belge Dili: İngilizce

Document ID (Org No.): 2001334901

pISSN: 1308-6693

Sayı

Yazarlar:

Sibel Çimen | Bülent Bolat

Yayıncı:

Süleyman Demirel University

Ana Başlıklar:

Biyomedikal Tanı | Sinyal İşleme

Dergi:

Mühendislik Bilimleri ve Tasarım Dergisi Vol.12 Issue 4, pp.724-735

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001334901

pISSN:

1308-6693