A New Artificial Intelligence Supported Approach to Diagnosis and prediction of Psoriasis

Year 2024, Volume: 10 Issue: 2, 405 - 418, 31.08.2024

Mehmet Akif Bülbül

Abstract

Early diagnosis and prediction of psoriasis is crucial to control disease progression, alleviate symptoms and reduce the risk of complications. Diagnosis in the early stages helps to determine the appropriate treatment plan and improve the patient's quality of life. The aim of this study is to enable early diagnosis of psoriasis. For this purpose, a hybrid architecture was created using a stacked auto-encoder, softmax classifier and Firefly Optimization Algorithm. With the created architecture, the architectural parameters of the stacked autocoder and softmax classifier hybrid structure aimed to be created for psoriasis diagnosis and all hyperparameters within the architecture were optimized. The model was implemented on the "Dermatology" dataset in the UCI data warehouse. In addition, machine learning methods such as K-Nearest Neighbor algorithm, Support Vector Machine and Decision Trees, which are frequently used in the literature, were also applied on the same dataset. The findings obtained from the experimental studies are presented in a controversial manner. The findings show that the proposed hybrid architecture achieves better results than other machine learning methods. At the same time, the model optimized and presented with the hybrid architecture can be used as an alternative method in patient decision support systems.

Keywords

Firefly optimization algorithm, stacked auto-encoder, softmax classifier, decision support system

Sedef Hastalığının Tanı ve Tahmininde Yapay Zekâ Destekli Yeni Bir Yaklaşım

Abstract

Sedef hastalığının erken tanı ve tahmini, hastalığın ilerlemesini kontrol altına almak, semptomları hafifletmek ve komplikasyon riskini azaltmak açısından son derece önemlidir. Erken aşamalarda tanı konulması, uygun tedavi planının belirlenmesine ve hastanın yaşam kalitesini artırmaya yardımcı olur. Bu çalışmanın amacı, sedef hastalığının erkenden teşhis edilebilmesini sağlamaktır. Bu amaç doğrultusunda yığılmış oto-kodlayıcı, softmax sınıflanrıcı ve Ateş Böceği Optimizasyon Algoritması kullanılarak hibrit bir mimari oluşturulmuştur. Oluşturulan mimari ile sedef hastalığı teşhisi için oluşturulması hedeflenen yığılmış oto-kodlayıcı ve softmax sınıflandırıcı hibrit yapısının mimari parametreleri ile mimari içerisinde bulunan bütün hiperparametreler optimize edilmiştir. Model UCI veri deposunda bulunan “Dermatoloji” veri seti üzerinde uygulanmıştır. Bunun yanında aynı veri seti üzerinde literatürde sıkça kullanılan makine öğrenme yöntemleri olan K-En yakın komşu algoritması, Destek Vektör Makinası ve Karar Ağaçları metotları da uygulanmıştır. Deneysel çalışmalardan elde edilen bulgular tartışmalı bir şekilde sunulmuştur. Elde edilen bulgular önerilen hibrit mimarinin diğer makine öğrenme yöntemlerine göre daha başarılı sonuçlar elde ettiğini göstermiştir. Aynı zamanda hibrit mimari ile optimize edilen ve sunulan model hasta karar destek sistemlerinde alternatif bir yöntem olarak da kullanılabilir.

Keywords

Ateş böceği optimizasyon algoritması, yığılmış oto-kodlayıcı, softmax sınıflandırıcı, karar destek sistemi

References

• [1] A. Günaydin, “Kurkumin Etken Maddesinin Etkileri v e Kalite Kontrol Çalışmaları Effects and Quality Control Studies of Curcumin,” Dünya Sağlık ve Tabiat Bilimleri Dergisi , vol. 6(1), pp. 14-21, 2023.
• [2] A. W. Armstrong and C. Read, “Pathophysiology, Clinical Presentation, and Treatment of Psoriasis: A Review,” JAMA - Journal of the American Medical Association, vol. 323(19), pp. 1945-1960, 2020. doi:10.1001/jama.2020.4006
• [3] F. Yamazaki, “Psoriasis: Comorbidities,” Journal of Dermatology, vol 48(6), pp. 732-740, 2021. doi:10.1111/1346-8138.15840
• [4] M. A. Bülbül, “Optimization of artificial neural network structure and hyperparameters in hybrid model by genetic algorithm: iOS–android application for breast cancer diagnosis/prediction”, Journal of Supercomputing, vol. 80(4), pp. 4533-4553, 2024. doi:10.1007/s11227-023-05635-z
• [5] I. Pacal and S. Kılıcarslan, “Deep learning-based approaches for robust classification of cervical cancer,” Neural Comput. Appl., vol. 35(25), pp. 18813-18828, 2023. doi:10.1007/s00521-023-08757-w
• [6] R. Raj, N. D. Londhe, and R. S. Sonawane, “Objective scoring of psoriasis area and severity index in 2D RGB images using deep learning,” Multimed. Tools Appl., pp. 1-27, 2024. doi:10.1007/s11042-024-18138-7
• [7] M. S. Rashid, G. Gilanie, S. Naveed, S. Cheema, and M. Sajid, “Automated detection and classification of psoriasis types using deep neural networks from dermatology images,” Signal, Image Video Process., vol. 18(1), pp. 163-172, 2024. doi:10.1007/s11760-023-02722-9
• [8] V. K. Shrivastava, N. D. Londhe, R. S. Sonawane, and J. S. Suri, “A novel approach to multiclass psoriasis disease risk stratification: Machine learning paradigm,” Biomed. Signal Process. Control, vol. 28, pp. 27-40, 2016. doi:10.1016/j.bspc.2016.04.001
• [9] G. Vishwakarma, A. K. Nandanwar, and G. S. Thakur, “Optimized vision transformer encoder with cnn for automatic psoriasis disease detection,” Multimed. Tools Appl., pp. 1-20, 2023. doi:10.1007/s11042-023-16871-z
• [10] M. Dash, N. D. Londhe, S. Ghosh, A. Semwal, and R. S. Sonawane, “PsLSNet: Automated psoriasis skin lesion segmentation using modified U-Net-based fully convolutional network,” Biomed. Signal Process. Control, vol. 52, pp. 226-237, 2019. doi:10.1016/j.bspc.2019.04.002
• [11] L. H. Juang and M. N. Wu, “Psoriasis image identification using k-means clustering with morphological processing,” Meas. J. Int. Meas. Confed., vol. 44(5), pp. 895-905, 2011. doi:10.1016/j.measurement.2011.02.006
• [12] M. A. Bülbül and C. Öztürk, “Optimization, Modeling and Implementation of Plant Water Consumption Control Using Genetic Algorithm and Artificial Neural Network in a Hybrid Structure,” Arab. J. Sci. Eng., vol. 47(2), pp. 2329-2343, 2022. doi:10.1007/s13369-021-06168-4
• [13] M. A. Bülbül, E. Harirchian, M. F. Işık, S. E. Aghakouchaki Hosseini, and E. Işık, “A Hybrid ANN-GA Model for an Automated Rapid Vulnerability Assessment of Existing RC Buildings,” Appl. Sci., vol. 12, no. 10, 2022. doi:10.3390/app12105138
• [14] F. Konak, M. A. Bülbül, and D. Türkoǧlu, “Feature Selection and Hyperparameters Optimization Employing a Hybrid Model Based on Genetic Algorithm and Artificial Neural Network: Forecasting Dividend Payout Ratio,” Comput. Econ., vol. 63, pp. 1673-1693, 2024. doi:10.1007/s10614-023-10530-z
• [15] I. Nurhidayat, B. Pimpunchat, and W. Klomsungcharoen, “More accurate simulation for insurance data based on a modified SVM polynomial method,” J. Intell. Fuzzy Syst., vol. 44(6), pp. 9129-9141, 2023. doi: 10.3233/JIFS-222879
• [16] J. Li, J. Shi, Z. Liu, and C. Feng, “A parallel and balanced SVM algorithm on spark for data-intensive computing,” Intell. Data Anal., vol. 27(4), pp. 1065-1086, 2023. doi:10.3233/IDA-226774
• [17] G. Sandhu, A. Singh, P. S. Lamba, D. Virmani, and G. Chaudhary, “Modified Euclidean-Canberra blend distance metric for kNN classifier,” Intell. Decis. Technol., vol. 17(2), pp. 527-541, 2023. doi:10.3233/idt-220223
• [18] M. A. Bülbül, “Kuru Fasulye Tohumlarının Çok Sınıflı Sınıflandırılması İçin Hibrit Bir Yaklaşım,” Iğdır Üniversitesi Fen Bilim. Enstitüsü Derg., vol. 13(1), pp. 33-43, 2023. doi:10.21597/jist.1185949
• [19] I. Roshanski, M. Kalech, and L. Rokach, “Automatic Feature Engineering for Learning Compact Decision Trees,” Expert Syst. Appl., vol. 229, pp. 120470, 2023. doi:10.1016/j.eswa.2023.120470
• [20] G. Nanfack, P. Temple, and B. Frénay, “Learning Customised Decision Trees for Domain-knowledge Constraints,” Pattern Recognit., vol. 142, pp. 109610, 2023. doi:10.1016/j.patcog.2023.109610
• [21] Z. Cheng, H. Song, D. Zheng, M. Zhou, and K. Sun, “Hybrid firefly algorithm with a new mechanism of gender distinguishing for global optimization,” Expert Syst. Appl., vol. 224, pp. 120027, 2023. doi:10.1016/j.eswa.2023.120027
• [22] T. Thepphakorn and P. Pongcharoen, “Modified and hybridised bi-objective firefly algorithms for university course scheduling,” Soft Comput., vol. 27(14), pp. 9735-9772, 2023. doi:10.1007/s00500-022-07810-5
• [23] M. Akdağ and M. Çelebi, “Ateş Böceği Algoritması ile Yağlı Tip Transformatörün Ağırlık Optimizasyonu,” DÜMF Mühendislik Derg., vol. 2, pp. 169–180, 2022. doi:10.24012/dumf.1075008
• [24] J. Yang and L. Wang, “Nonlocal, local and global preserving stacked autoencoder based fault detection method for nonlinear process monitoring,” Chemom. Intell. Lab. Syst., vol. 235, pp. 104758 2023. doi:10.1016/j.chemolab.2023.104758
• [25] R. R. Jagat, D. S. Sisodia, and P. Singh, “Web-S4AE: a semi-supervised stacked sparse autoencoder model for web robot detection,” Neural Comput. Appl., vol. 35(24), pp. 17883-17898, 2023. doi:10.1007/s00521-023-08668-w
• [26] K. Adem, S. Kiliçarslan, and O. Cömert, “Classification and diagnosis of cervical cancer with stacked autoencoder and softmax classification,” Expert Syst. Appl., vol. 115, pp. 557–564, 2019. doi:10.1016/j.eswa.2018.08.050
• [27] K. E. M and Dejey, “Stacked autoencoder with novel integrated activation functions for the diagnosis of autism spectrum disorder,” Neural Comput. Appl., 2023. doi:10.1007/s00521-023-08565-2
• [28] W. Zeng et al., “Wear indicator construction for rolling bearings based on an enhanced and unsupervised stacked auto-encoder,” Soft Comput., pp. 1-14, 2023. doi:10.1007/s00500-023-09068-x
• [29] E. D. Übeyli and I. Güler, “Automatic detection of erythemato-squamous diseases using adaptive neuro-fuzzy inference systems,” Comput. Biol. Med., vol. 35(5), pp. 421-433, 2005. doi:10.1016/j.compbiomed.2004.03.003
• [30] M. Jiang et al., “Personalized and adaptive neural networks for pain detection from multi-modal physiological features,” Expert Syst. Appl., vol. 235, pp. 121082, 2024. doi:10.1016/j.eswa.2023.121082
• [31] U. Prasad, S. Chakravarty, and G. Mahto, “Lung cancer detection and classification using deep neural network based on hybrid metaheuristic algorithm,” Soft Comput., pp. 1-224, 2023. doi:10.1007/s00500-023-08845-y
• [32] P. Sengodan, K. Srinivasan, R. Pichamuthu, and S. Matheswaran, “Early detection and classification of malignant lung nodules from CT images: An optimal ensemble learning,” Expert Syst. Appl., vol. 229, pp. 120361, 2023. doi:10.1016/j.eswa.2023.120361
• [33] A. M. Carrington et al., “Deep ROC Analysis and AUC as Balanced Average Accuracy, for Improved Classifier Selection, Audit and Explanation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45(1), pp. 329-341 2023. doi:10.1109/TPAMI.2022.3145392