Erythemato-squamous diseases diagnosis and prediction using artificial intelligence

Abstract

In this study, artificial intelligence was applied to accurately diagnose and predict erythemato-squamous diseases (ESDs). Feature selection was performed for 34 features in the dataset with the wrapper feature selection method. 18 features were selected using the feature selection method. In the analyses performed with machine learning algorithms, results were obtained and compared with both the initial 34 features and the selected 18 features. Six different machine learning classification algorithms were compared for erythemato-squamous diseases. Naive Bayes algorithm was determined as the most successful algorithm in the diagnosis and prediction of erythemato-squamous diseases with an accuracy rate of 99.45%. In addition, it was determined that the applied feature selection method increased the performance of all algorithms. When the results obtained in the study are examined, it is seen that wrapper feature selection plays an important role in improving the performance of machine learning models.

Keywords

• Artificial intelligence
• machine learning
• attribute selection. erythemato-squamous.

Yapay zeka kullanılarak erythemato-squamous hastalıklarının tanısı ve tahmini

Abstract

Bu çalışmada, erythemato-squamous hastalıklarını (ESDs) doğru bir şekilde tahmin etmek için yapay zeka uygulanmıştır. Veri setinde bulunan 34 özellik için wrapper nitelik seçim yöntemi ile özellik seçimi yapılmıştır. Analiz sonrasında 18 özellik seçilmiştir. Makine öğrenmesi algoritmaları ile gerçekleştirilen analizlerde hem başlangıçtaki 34 özellikle hem de seçilen 18 özellikle sonuçlar alınıp karşılaştırılmıştır. Erythemato-squamous hastalıklar için altı farklı makine öğrenmesi sınıflandırma algoritması karşılaştırılmıştır. Naive Bayes algoritması, 99.45% doğruluk oranıyla erythemato-squamous hastalık tahmininde en başarılı algoritma olarak tespit edilmiştir. Bunun yanı sıra, uygulanan özellik seçim yönteminin tüm algoritmaların performansını yükselttiği tespit edilmiştir. Çalışmada elde edilen sonuçlar incelendiğinde, wrapper nitelik seçiminin makine öğrenmesi modellerinin performansının iyileştirilmesinde önemli bir rol oynadığı görülmektedir.

Keywords

• Yapay zeka
• makine öğrenmesi
• özellik seçimi
• erythemato-squamous

References

1. Kumar, Y., Koul, A., Singla, R., ve Ijaz, M. F., Artificial intelligence in disease diagnosis: a systematic literature review, synthesizing framework and future research agenda, Journal of ambient intelligence and humanized computing, 14(7), 8459-8486, (2023).
2. Massaro, M., Digital transformation in the healthcare sector through blockchain technology. Insights from academic research and business developments. Technovation, 120, 102386, (2023).
3. Flores, M., Glusman, G., Brogaard, K., Price, N. D. ve Hood, L., P4 medicine: how systems medicine will transform the healthcare sector and society, Personalized medicine, 10(6), 565-576, (2013).
4. Swain, D., Mehta, U., Mehta, M., Vekariya, J., Swain, D., Gerogiannis, V. C., ... ve Acharya, B., Differential diagnosis of erythemato-squamous diseases using a hybrid ensemble machine learning technique, Intelligent Decision Technologies, 18(2), 1495-1510, (2024).
5. Singh, S. K., Sinha, A., ve Yadav, S., Performance analysis of machine learning algorithms for erythemato-squamous diseases classification. IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE), pp. 1-6, (2022).
6. Shaukat, Z., Zafar, W., Ahmad, W., Haq, I. U., Husnain, G., Al-Adhaileh, M. H., ... ve Algarni, A., Revolutionizing Diabetes Diagnosis: Machine Learning Techniques Unleashed, Healthcare (Switzerland), vol. 11, no. 21, 2023, doi: 10.3390/healthcare11212864.
7. Dicuonzo, G., Donofrio, F., Fusco, A., & Shini, M., Healthcare system: Moving forward with artificial intelligence, Technovation, vol. 120, Feb. 2023, doi: 10.1016/j.technovation.2022.102510.
8. Wang, Z., Chang, L., Shi, T., Hu, H., Wang, C., Lin, K., and Zhang, J., Identifying diagnostic biomarkers for Erythemato-Squamous diseases using explainable machine learning, Biomed Signal Process Control, vol. 100, 2025, doi: 10.1016/j.bspc.2024.107101.

9. Akarajarasroj, T., Wattanapermpool, O., Sapphaphab, P., Rinthon, O., Pechprasarn, S., ve Boonkrong, P., Feature Selection in the Classification of Erythemato-Squamous Diseases using Machine Learning Models and Principal Component Analysis, 15th Biomedical Engineering International Conference, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/BMEiCON60347.2023.10322034.
10. Güvenir, H. A., ve Emeksiz, N., An expert system for the differential diagnosis of erythemato-squamous diseases, Expert Systems with Applications, 18(1), 43-49, (2000).
11. Abdi, M. J., ve Giveki, D., Automatic detection of erythemato-squamous diseases using PSO–SVM based on association rules. Engineering Applications of Artificial Intelligence, 26(1), 603-608, (2013). doi: 10.1016/j.engappai.2012.01.017.
12. Igodan, E. C., Thompson, A. F. B., Obe, O., ve Owolafe, O., Erythemato Squamous Disease prediction using ensemble multi-feature selection approach. International Journal of Computer Science and Information Security (IJCSIS), 20, 95-106, (2022).
13. Choi, L. K., Rii, K. B., ve Park, H. W., K-Means and J48 Algorithms to Categorize Student Research Abstracts. International Journal of Cyber and IT Service Management, 3(1), 61-64, (2023).
14. Al-Manaseer, H., Abualigah, L., Alsoud, A. R., Zitar, R. A., Ezugwu, A. E., ve Jia, H., A novel big data classification technique for healthcare application using support vector machine, random forest and J48. In Classification applications with deep learning and machine learning Technologies, Springer International Publishing, 205-215, (2022).
15. Hermawan, D. R., Fatihah, M. F. G., Kurniawati, L., & Helen, A., Comparative study of J48 decision tree classification algorithm, random tree, and random forest on in-vehicle CouponRecommendation data. In 2021 International conference on artificial intelligence and big data analytics, IEEE, 1-6, (2021).
16. Ahmadi, F., Mirabbasi, R., Kumar, R., ve Gajbhiye, S., Prediction of precipitation using wavelet-based hybrid models considering the periodicity. Neural Computing and Applications, 1-20. (2024).
17. Luo, G., Ye, J., Wang, J., ve Wei, Y., Urban Functional Zone Classification Based on POI Data and Machine Learning, Sustainability (Switzerland), vol. 15, no. 5, (2023), doi: 10.3390/su15054631.
18. Pajila, P. B., Sheena, B. G., Gayathri, A., Aswini, J., ve Nalini, M., A Comprehensive Survey on Naive Bayes Algorithm: Advantages, Limitations and Applications, Proceedings of the 4th International Conference on Smart Electronics and Communication, ICOSEC 2023, 1228–1234, (2023), doi: 10.1109/ICOSEC58147.2023.10276274.
19. Elsayad, A. M., Nassef, A. M., ve Al-Dhaifallah, M., Bayesian optimization of multiclass SVM for efficient diagnosis of erythemato-squamous diseases. Biomedical Signal Processing and Control, 71, 103223 (2022).
20. Verma, A. K., ve Pal, S., Prediction of skin disease with three different feature selection techniques using stacking ensemble method. Applied biochemistry and biotechnology, 191(2), 637-656, (2020).
21. Özçift, A., ve Gülten, A. Genetic algorithm wrapped Bayesian network feature selection applied to differential diagnosis of erythemato-squamous diseases. Digital Signal Processing, 23(1), 230-237. (2013).