Prediction of Liver Diseases with Machine Learning Method

Year 2022, , 115 - 122, 30.06.2022

Mustafa Teke

https://doi.org/10.51764/smutgd.1106793

Cited By: 1

Abstract

In this study, a disease prediction model study based on the logistic regression classification of liver test results from machine learning algorithms was performed. The liver works like a factory in the human body. Disease of this organ causes many effects that harm the whole body. In this study, the disease prediction model for this vital organ was performed according to certain criteria and parameters. In the study, values such as protein, albumin and bilirubin belonging to the liver were examined in the disease prediction model. The data model used in the study was taken from the open source kaggle website. The prediction model was implemented in the jupyter notebook environment with python language. Logistic regression model was preferred for categorical data estimation. The model created contained 84% accuracy. Confusion matrix calculation table was used as evaluation criterion and presented in the study.

Keywords

Machine learning, Logistic regression, Liver disease.

Makine Öğrenmesi Yöntemi ile Karaciğerde Oluşan Hastalıkların Tahmini

Abstract

Bu çalışmada karaciğer test sonuçlarının makine öğrenmesi algoritmalarından lojistik regresyon sınıflandırılmasına dayalı hastalık tahmin modeli çalışması yapılmıştır. Karaciğer insan vücudunda adeta bir fabrika gibi çalışmaktadır. Bu organın hastalanması bütün vücuda zarar veren birçok etki meydana getirmektedir. Bu çalışmada belirli ölçütlere ve parametrelere göre bu hayati organ için hastalık tahmin modeli gerçekleştirilmiştir. Çalışmada karaciğere ait protein, albümin ve bilurubin gibi değerler hastalık tahmin modelinde incelenmiştir. Çalışmada kullanılan veri modeli açık kaynaklı kaggle web sitesinden alınmıştır. Tahmin modeli python dili ile jupyter notebook ortamında gerçekleştirilmiştir. Kategorik veri tahmini içinse lojistik regresyon modeli tercih edilmiştir. Oluşturulan model %84 doğruluk içermiştir. Değerlendirme ölçütü olarak karmaşıklık matrisi kullanılmış ve çalışmada sunulmuştur.

Keywords

Lojistik regresyon, Karaciğer hastalığı., makine öğrenmesi

References

• Roy, S., Menapace, W., Oei, S., Luijten, B., Fini, E., Saltori, C., & Demi, L. Deep learning for classification and localization of COVID-19 markers in point-of-care lung ultrasound. IEEE transactions on medical imaging, (2020) 39(8), 2676-2687.
• Khalifa, NEM., Taha, MHN., Ali, DE., Slowik, A., & Hassanien, AE. Artificial intelligence technique for gene expression by tumor RNA-Seq data: a novel optimized deep learning approach. IEEE, (2020); 8, 22874-22883.
• Kaur, S., Singla, J., Nkenyereye, L., Jha, S., Prashar, D., Joshi, G. P., & Islam, SR. Medical diagnostic systems using artificial intelligence (ai) algorithms: Principles and perspectives. IEEE (2020); 8, 228049-228069.
• Yao, Z., Li, J., Guan, Z., Ye, Y., & Chen, Y. Liver disease screening based on densely connected deep neural networks. Neural Networks, (2020); 123, 299-304.
• Guo, X., Wang, F., Teodoro, G., Farris, A. B., & Kong, J.. Liver steatosis segmentation with deep learning methods. In 2019 IEEE 16th International Symposium on Biomedical Imaging (2019); (pp. 24-27). IEEE.
• Byra, M., Styczynski, G., Szmigielski, C., Kalinowski, P., Michalowski, L., Paluszkiewicz, R.,& Nowicki, A. Adversarial attacks on deep learning models for fatty liver disease classification by modification of ultrasound image reconstruction method. In 2020 IEEE International Ultrasonics Symposium (IUS) (2020, September); (pp. 1-4). IEEE.
• Yamakawa, M., Shiina, T., Nishida, N., & Kudo, M. Computer aided diagnosis system developed for ultrasound diagnosis of liver lesions using deep learning. In 2019 IEEE International Ultrasonics Symposium (IUS) . (2019, October); (pp. 2330-2333). IEEE.
• Li, Y., He, Q., & Luo, J. A deep learning trial on transient elastography for assessment of liver fibrosis. In 2018 IEEE International Ultrasonics Symposium (IUS) (2018, October); (pp. 1-4). IEEE.
• Arjmand, A., Angelis, CT., Tzallas, AT., Tsipouras, MG., Glavas, E., Forlano, R.,& Giannakeas, N. Deep learning in liver biopsies using convolutional neural networks. In 2019 42nd International Conference on Telecommunications and Signal Processing (TSP) (2019, July); (pp. 496-499). IEEE.
• Alkuşak E. ve Gök M., 2015. “Karaciğer Yetmezliğinin Teşhisinde Makine Öğrenmesi Algoritmalarının Kullanımı”, ISITES 2014 Sempozyumu (ISITES’2014); 18-20 Haziran 2014; Karabük. 703-707.
• Özdemir E. Ballı S. “Türkiye Erkekler Basketbol Ligi Maç Sonuçlarının Makine Öğrenmesi Yöntemleri ile Tahmini”, Mühendislik Bilimleri ve Tasarım Dergisi, 2020; 8 (3): 740 - 752.
• Bayet, J., Hoogenboom, T., Sharma, R., & Angelini, ED. Machine-Learning on Liver Ultrasound to Stratify Multiple Diseases via Blood-Vessels and Perfusion Characteristics. In 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI) (2020, April); (pp. 1351-1354). IEEE.
• Tai, SK., & Lo, YS. Using deep learning to evaluate the segmentation of liver cell from biopsy image. In 2018 9th International Conference on Awareness Science and Technology (iCAST) 2018; (pp. 232-235). IEEE.
• Trivizakis, E., Manikis, GC., Nikiforaki, K., Drevelegas, K., Constantinides, M., Drevelegas, A., & Marias, K. Extending 2-D convolutional neural networks to 3-D for advancing deep learning cancer classification with application to MRI liver tumor differentiation. IEEE journal of biomedical and health informatics, (2018); 23(3), 923-930.
• Jyoti, O., Islam, N., & Hasnain, F. M. S. Prediction of Hepatitis Disease Using Effective Deep Neural Network. In 2020 IEEE International Conference for Innovation in Technology (INOCON) (2020); (pp. 1-5). IEEE.
• Liu, Z., Abdukeyim, N., & Yan, C. Image classification of hepatic echinococcosis based on convolutional neural network. In 2019 6th International Conference on Systems and Informatics (ICSAI) (2019); (pp. 1280-1284). IEEE.
• Lin, R. H., & Chuang, C. L. A hybrid diagnosis model for determining the types of the liver disease. Computers in Biology and Medicine, (2010). 40(7), 665-670.
• Schiff, E. R., Maddrey, W. C., & Sorrell, M. F. Schiff's Diseases of the Liver. John Wiley & Sons . (2011). Parkin, D. M., Bray, F., Ferlay, J., & Pisani, P. Global cancer statistics, 2002. CA: a cancer journal for clinicians, (2005). 55(2), 74-108.
• Reddy, DS., Bharath, R., & Rajalakshmi, P. A novel computer-aided diagnosis framework using deep learning for classification of fatty liver disease in ultrasound imaging. In 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom) (2018, September); (pp. 1-5). IEEE.
• Sorich, M. J., Miners, J. O., McKinnon, R. A., Winkler, D. A., Burden, F. R., & Smith, P. A. Comparison of linear and nonlinear classification algorithms for the prediction of drug and chemical metabolism by human UDP-glucuronosyltransferase isoforms. Journal of chemical information and computer sciences, . (2003) 43(6), 2019-2024.
• Dandıl, E. Karaciğerde Oluşan Hastalıkların Tespitinde Makine Öğrenmesi Yöntemlerinin Kullanılması XV. Akademik Bilişim Konferansı syf 614-617. 23-25 Ocak 2013.
• Gulia, A., Vohra, R., & Rani, P. Liver patient classification using intelligent techniques. International Journal of Computer Science and Information Technologies, (2014). 5(4), 5110-5115.
• Deshmukh, S., Lokhande, A., Wasnik, R., & Singhal, N. Vacuole segmentation and quantification in liver images of Wistar rat. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) . (2020); (pp. 1396-1399). IEEE.
• Lou, Y., Qian, T., Li, F., Zhou, J., Ji, D., & Cheng, M. Investigating of Disease Name Normalization Using Neural Network and Pre-Training. IEEE Access, (2020); 8, 85729-85739.
• URL-1, Albümin. https://www.medicalpark.com.tr/albumin/hg-2198 (Erişim Tarihi: 11.03.2021)
• URL-2, Bilrubin. https://www.memorial.com.tr/tani-ve-testler/bilirubin-testi-nedir (Erişim Tarihi: 11.03.2021)
• URL-3, Aspartat Aminotransferaz. https://www.medicalpark.com.tr/alt/hg-2178 (Erişim Tarihi: 11.03.2021)
• URL-4, Veri seti. https://www.kaggle.com/datasets (Erişim Tarihi: 11.03.2021)