CLASSIFICATION OF ANEMIA DISEASE USING ARTIFICIAL NEURAL NETWORKS METHODS

Nagihan Yağmur; Hasan Temurtaş; İdris Dağ

Article Details

CLASSIFICATION OF ANEMIA DISEASE USING ARTIFICIAL NEURAL NETWORKS METHODS

Authors:

Nagihan Yağmur | Hasan Temurtaş | İdris Dağ

Publisher:

Kütahya Dumlupinar University

Main Topics:

Engineering

Journal:

Journal of Scientific Reports-B Issue 008, pp.20-34

Document Type:

Article

Publication Date:

12/2023

Document Language:

Turkish

Document ID (Org No.):

2001290330

pISSN:

2717-8625

Keywords:

Abstract:

 Anemia, which occurs when the hemoglobin value falls below a certain reference range and is also called anemia, needs many blood tests, radiological images and analyzes for its diagnosis and treatment. In addition to such a large amount of produced medical data, a doctors decision is required in diagnosing the disease. By processing the medical data taken from the patients, predictions of diseases can be made for new patients and decision support mechanisms can be established for doctors with these predictions. Thanks to these methods, which are very important in reducing the margin of error in the diagnosis of doctors for patients, the evaluation of data records in health institutions is also important for patients and hospitals. Various methods have been used for the classification problem of anemia disease in the literature, and the performance of the proposed algorithms varies according to the datasets due to the changes in the number of patient records in the datasets, the number and characteristics of the blood parameters. In this study, Artificial Neural Networks ANN methods were used to solve the anemia disease classification problem based on blood data on the anemia dataset taken from the Kaggle database. Performance rates were calculated using the Learning Vector Quantization LVQ, Competitive Layer Neural Network CLNN, Pattern Recognition Artificial Neural Network PRNN, Self-Organizing Map SOM methods. The four proposed methods were compared by giving the accuracy values and confusion matrix values of the obtained results. It was concluded that the best success performance was PRNN with 100 sensitivity and 99.88 accuracy, 99.86 specificity, 99.43 precision, followed by LVQ.

 Anemia, which occurs when the hemoglobin value falls below a certain reference range and is also called anemia, needs many blood tests, radiological images and analyzes for its diagnosis and treatment. In addition to such a large amount of produced medical data, a doctors decision is required in diagnosing the disease. By processing the medical data taken from the patients, predictions of diseases can be made for new patients and decision support mechanisms can be established for doctors with these predictions. Thanks to these methods, which are very important in reducing the margin of error in the diagnosis of doctors for patients, the evaluation of data records in health institutions is also important for patients and hospitals. Various methods have been used for the classification problem of anemia disease in the literature, and the performance of the proposed algorithms varies according to the datasets due to the changes in the number of patient records in the datasets, the number and characteristics of the blood parameters. In this study, Artificial Neural Networks ANN methods were used to solve the anemia disease classification problem based on blood data on the anemia dataset taken from the Kaggle database. Performance rates were calculated using the Learning Vector Quantization LVQ, Competitive Layer Neural Network CLNN, Pattern Recognition Artificial Neural Network PRNN, Self-Organizing Map SOM methods. The four proposed methods were compared by giving the accuracy values and confusion matrix values of the obtained results. It was concluded that the best success performance was PRNN with 100 sensitivity and 99.88 accuracy, 99.86 specificity, 99.43 precision, followed by LVQ.

 Anemia, which occurs when the hemoglobin value falls below a certain reference range and is also called anemia, needs many blood tests, radiological images and analyzes for its diagnosis and treatment. In addition to such a large amount of produced medical data, a doctors decision is required in diagnosing the disease. By processing the medical data taken from the patients, predictions of diseases can be made for new patients and decision support mechanisms can be established for doctors with these predictions. Thanks to these methods, which are very important in reducing the margin of error in the diagnosis of doctors for patients, the evaluation of data records in health institutions is also important for patients and hospitals. Various methods have been used for the classification problem of anemia disease in the literature, and the performance of the proposed algorithms varies according to the datasets due to the changes in the number of patient records in the datasets, the number and characteristics of the blood parameters. In this study, Artificial Neural Networks ANN methods were used to solve the anemia disease classification problem based on blood data on the anemia dataset taken from the Kaggle database. Performance rates were calculated using the Learning Vector Quantization LVQ, Competitive Layer Neural Network CLNN, Pattern Recognition Artificial Neural Network PRNN, Self-Organizing Map SOM methods. The four proposed methods were compared by giving the accuracy values and confusion matrix values of the obtained results. It was concluded that the best success performance was PRNN with 100 sensitivity and 99.88 accuracy, 99.86 specificity, 99.43 precision, followed by LVQ.

 Hemoglobin değerinin belirli bir referans aralığının altına düşmesiyle ortaya çıkan ve aynı zamanda kansızlık olarak adlandırılan anemi, teşhis ve tedavisi için birçok kan testine, radyolojik görüntülere, tahlillere ihtiyaç duyar. Bu gibi çok fazla üretilen tıbbi verilerin yanında hastalık teşhisinin konulmasında doktor kararı gereklidir. Hastalardan alınan tıbbi veriler işlenerek yeni hasta bireyler için hastalıkların tahminleri yapılabilir ve bu tahminlerle doktorlar için karar destek mekanizmaları kurulabilmektedir. Doktorların hastalar için koyacağı teşhisteki yanılma payını azaltma konusunda oldukça önemli olan bu yöntemler sayesinde sağlık kurumlarındaki veri kayıtlarının değerlendirilmesi hasta ve hastaneler için de önem arz etmektedir. Literatürde anemi hastalığı sınıflandırma problemi için çeşitli yöntemler kullanılmış olup, veri setlerindeki hasta kayıt sayılarının değişiklik göstermesi, kan parametrelerin sayısının ve özelliklerinin farklı olması gibi durumlardan dolayı önerilen algoritmaların performansları veri setlerine göre değişiklik göstermektedir. Bu çalışmada Kaggle veri tabanından alınan anemi veri seti üzerinde kandaki verilere dayalı olarak anemi hastalığı sınıflandırması problemini çözmek amacıyla Yapay Sinir Ağları YSA yöntemleri kullanılmıştır. Öğrenmeli Vektör Kuantalama LVQ, Rekabetçi Katman Sinir Ağı CLNN, Örüntü Tanıma Yapay Sinir Ağı PRNN, Kendiliğinden Organize Olan Harita SOM yapay sinir ağı yöntemleri kullanılarak başarım oranları hesaplanmıştır. Elde edilen sonuçların doğruluk değerleri ve karışıklık matrisleri verilerek önerilen dört yöntem karşılaştırılmıştır. En iyi başarı performansı 100 hassasiyet ve 99,88 doğruluk, 99,86 özgüllük, 99,43 kesinlik ile PRNN olduğu, onu takiben LVQ olduğu sonucuna ulaşılmıştır.

Article Details

CLASSIFICATION OF ANEMIA DISEASE USING ARTIFICIAL NEURAL NETWORKS METHODS

Authors:

Nagihan Yağmur | Hasan Temurtaş | İdris Dağ

Publisher:

Kütahya Dumlupinar University

Main Topics:

Engineering

Journal:

Journal of Scientific Reports-B Issue 008, pp.20-34

Document Type:

Article

Publication Date:

12/2023

Document Language:

Turkish

Document ID (Org No.):

2001290330

pISSN:

2717-8625

Anemia classification

learning vector quantization

competitive layer neural network

pattern recognition artificial neural network

self-organizing mapAnemi sınıflandırma

öğrenmeli vektör kuantalama

rekabetçi katman sinir ağı

örüntü tanıma yapay sinir ağı

kendiliğinden organize olan harita

Issues

Article Details

Authors: Nagihan Yağmur | Hasan Temurtaş | İdris Dağ

Publisher: Kütahya Dumlupinar University

Main Topics: Engineering

Journal: Journal of Scientific Reports-B Issue 008, pp.20-34

Document Type: Article

Publication Date: 12/2023

Document Language: Turkish

Document ID (Org No.): 2001290330

pISSN: 2717-8625

Issues

Authors:

Nagihan Yağmur | Hasan Temurtaş | İdris Dağ

Publisher:

Kütahya Dumlupinar University

Main Topics:

Engineering

Journal:

Journal of Scientific Reports-B Issue 008, pp.20-34

Document Type:

Article

Publication Date:

12/2023

Document Language:

Turkish

Document ID (Org No.):

2001290330

pISSN:

2717-8625