Yapay Sinir Ağları Kullanarak Kan Testi Sonuçlarının Sınıflandırılması ve Kullanıcı Ara Yüzünün Geliştirmesi

Year 2021, , 1 - 5, 01.12.2021

Rıza İlhan , Büşranur Güdar

https://doi.org/10.31590/ejosat.1010484

Cited By: 1

Abstract

Hastalıkların başarılı bir şekilde tedavi edilebilmesi için hızlı ve doğru tıbbi teşhis çok önemlidir. NHANES laboratuvarı analizleri ile elde edilen kan testi sonuçlarından hastalıkları tahmin etmek için MLP NN ve ChOA birleştirilerek bir model (Bileşik Model) geliştirilmiştir. Bileşik modelin geliştirilmesine ek olarak kan testi verisetlerinin model ile sınıflandırılarak sınıflandırma doğruluklarının diğer algoritmalar ile karşılaştırılmasını sağlayan bir kullanıcı arayüzü programı geliştirilmiştir. Öncelikle MLP Neural Network Algoritmasını, Chimp Optimization Algoritması ile birleştirerek MLP NN’ün en büyük dezavantajlarından olan aşırı yükleme durumu giderilmiştir. Birleşik model’den elde edilen doğruluk değeri Rastgele Orman (Random Forest), Lojistik Regresyon (Logistic Regression) ve İki Katmanlı Yapay Sinir Ağı ile karşılaştırılmıştır. Sonuçlar, hazırlanan kullanıcı arayüzünde de görüldüğü gibi MLP NN-ChOA modelinin çoğu durumda diğer kıyaslama algoritmalarına kıyasla daha iyi veya karşılaştırılabilir bir performans sağladığını göstermektedir.

Keywords

Kan testi, Yapay sinir ağları, Optimizasyon, Sınıflandırma, Teşhis.

Thanks

İstanbul Aydın Üniversitesi Yazılım Mühendisliği Bölümü'nden Dr. Sedjad Eyni ve Dr. Elnaz Pashaei'ye faydalı yorumları ve tartışmaları için teşekkür ederiz.

Classification of Blood Test Results Using Artificial Neural Networks and Improvement of User Interface

Abstract

Rapid and accurate medical diagnoses are essential for the successful treatment of diseases. A model was developed by combining MLP NN and Chimp Optimization Algorithms to predict diseases from NHANES laboratory blood test results. In addition to the development of this model, a user interface program has been developed that allows datasets to be loaded and trained with the model and compared with other algorithms. First of all, by combining the MLP Neural Network Algorithm with the Chimp Optimization Algorithm, the overload situation, which is the biggest disadvantage of NN, is eliminated. The accuracy value obtained from the combined model was compared with Random Forest, Logistic Regression and Two-Layer Artificial Neural Network. The results show that the MLP NN-ChOA algorithm provides better or comparable performance compared to other benchmarking algorithms in most cases, as seen in the prepared user interface.

Keywords

Blood test, Neural networks, Optimization, Classification, Diagnosis.

References

• Aeinfar, V., Mazdarani, H., Deregeh, F., Hayati, M., & Payandeh, M. (2009). Multilayer perceptron neural network with supervised training method for diagnosis and predicting blood disorder and cancer. IEEE International Symposium on Industrial Electronics, 2075–2080. https://doi.org/10.1109/ISIE.2009.5213591
• Afrakhteh, S., Mosavi, M. R., Khishe, M., & Ayatollahi, A. (2020). Accurate classification of EEG signals using neural networks trained by hybrid population-physic-based algorithm. International Journal of Automation and Computing, 17(1), 108–122. https://doi.org/10.1007/s11633-018-1158-3
• Aljarah, I., Faris, H., & Mirjalili, S. (2018). Optimizing connection weights in neural networks using the whale optimization algorithm. Soft Computing, 22(1). https://doi.org/10.1007/s00500-016-2442-1
• Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
• Demirci, F., Akan, P., Kume, T., Sisman, A. R., Erbayraktar, Z., & Sevinc, S. (2016). Artificial neural network approach in laboratory test reporting: Learning algorithms. American Journal of Clinical Pathology, 146(2), 227–237. https://doi.org/10.1093/ajcp/aqw104
• Gogou, G., Maglaveras, N., Ambrosiadou, B. V., Goulis, D., & Pappas, C. (2001). A neural network approach in diabetes management by insulin administration. In Journal of Medical Systems (Vol. 25, Issue 2, pp. 119–131). https://doi.org/10.1023/A:1005672631019
• Gunčar, G., Kukar, M., Notar, M., Brvar, M., Černelč, P., Notar, M., & Notar, M. (2018). An application of machine learning to haematological diagnosis. Scientific Reports, 8(1). https://doi.org/10.1038/s41598-017-18564-8
• Khishe, M., & Mosavi, M. R. (2020a). Classification of underwater acoustical dataset using neural network trained by chimp optimization algorithm. Applied Acoustics, 157. https://doi.org/10.1016/j.apacoust.2019.107005
• Khishe, M., & Mosavi, M. R. (2020b). Chimp optimization algorithm. Expert Systems with Applications, 149. https://doi.org/10.1016/j.eswa.2020.113338
• Maiellaro, P., Cozzolongo, R., & Marino, P. (2005). Artificial neural networks for the prediction of response to interferon plus ribavirin treatment in patients with chronic hepatitis c. Current Pharmaceutical Design, 10(17), 2101–2109. https://doi.org/10.2174/1381612043384240
• Mosavi, M. R., & Khishe, M. (2017). Training a feed-forward neural network using particle swarm optimizer with autonomous Groups for sonar target classification. Journal of Circuits, Systems and Computers, 26(11). https://doi.org/10.1142/S0218126617501857
• Mosavi, Mohammad Reza, Khishe, M., Naseri, M. J., Parvizi, G. R., & Ayat, M. (2019). Multi-layer perceptron neural network utilizing adaptive best-mass gravitational search algorithm to classify sonar dataset. Archives of Acoustics, 44(1), 137–151. https://doi.org/10.24425/AOA.2019.126360
• Payandeh, M., Aeinfar, M., Aeinfar, V., & Hayati, M. (2009). A new method for diagnosis and predicting blood disorder and cancer using artificial intelligence (Artificial neural networks). International Journal of Hematology-Oncology and Stem Cell Research, 3(4), 25–33.
• Shahmoradi, L., Safdari, R., Mirhosseini, M. M., Arji, G., Jannat, B., & Abdar, M. (2018). Predicting risk of acute appendicitis: A comparison of artificial neural network and logistic regression models. Acta Medica Iranica, 56(12), 784–795.
• Shariati, M., Mafipour, M. S., Mehrabi, P., Bahadori, A., Zandi, Y., Salih, M. N. A., Nguyen, H., Dou, J., Song, X., & Poi-Ngian, S. (2019). Application of a hybrid artificial neural network-particle swarm optimization (ANN-PSO) model in behavior prediction of channel shear connectors embedded in normal and high-strength concrete. Applied Sciences (Switzerland), 9(24). https://doi.org/10.3390/app9245534
• Sinan, U. (2021). Makine öğrenmesi teorik yönleri ve python uygulamaları ile bir yapay zeka ekolü (Atalay Mat). Nobel Akademik Yayıncılık.
• Stanford, C. B., Goodall, J., Wallis, J., Mpongo, E., Wallis, J., & Goodall, J. (1994). Hunting decisions in wild chimpanzees. Behaviour, 131(1–2), 1–18. https://doi.org/10.1163/156853994X00181