Hepatitis C Disease Detection Based on PCA–SVM Model

Abstract

Hepatitis C is a liver disease caused by infection with the hepatitis C virus (HCV), which is transmitted through the blood. The disease can lead to diseases ranging from a mild form to serious lifelong illness. Studies to detect the disease early and reduce its effect are continuing. This study proposes an effective support vector machine model supported by principal component analysis for detecting hepatitis c disease. The dataset consisted of twelve independent variables, each containing 582 samples, and these variables were used as inputs to the two classifiers, support vector machine (SVM) and artificial neural network (ANN). The accuracy, sensitivity, specificity, MCC and KAPPA were calculated using two classification models. In addition, performance comparisons of classifiers were made for the two cases with and without PCA (principal component analysis) applied to the inputs. The highest accuracy (98.7%), sensitivity (99.1%), specificity (95.2%), MCC (92.3%) and Kappa (92.3%) in the binary class label were obtained with the SVM with PCA. In the four-class label, the highest accuracy was achieved with the same model with 95.7%. The results show that an SVM classifier model, in which PCA-reduced independent variables are applied to its inputs, may be a candidate for an accurate prediction model to predict hepatitis C disease.

Keywords

• ANN
• Dimensional reduction
• Hepatitis C
• PCA
• SVM

References

1. [1] Hepatitis.https://www.who.int/news-room/fact-sheets/detail/hepatitis-c (accessed Nov. 20,2021)
2. [2] Rayan Z, Alfonse M, Salem ABM. Machine Learning Approaches in Smart Health. Procedia Computer Science 154 (2019) 361–368. https://doi.org/10.1016/J.PROCS.2019.06.052
3. [3] Gündoğdu S. Improving breast cancer prediction using a pattern recognition network with optimal feature subsets. Croatian medical journal 62 (2021) 480–487. https://doi.org/10.3325/cmj.2021.62.480
4. [4] Senturk ZK. Early diagnosis of Parkinson’s disease using machine learning algorithms. Medical Hypotheses 138 (2020) 109603. https://doi.org/10.1016/J.MEHY.2020.109603
5. [5] Ayeldeen H, Shaker O, Ayeldeen G, Anwar KM. Prediction of liver fibrosis stages by machine learning model: A decision tree approach, Paper presented at Third World Conference on Complex Systems (WCCS), Marrakech, Morocco, 23-25 November, IEEE, pp. 1-6, 2015. https://doi.org/10.1109/ICOCS.2015.7483212
6. [6] Orczyk T, Porwik P. Liver fibrosis diagnosis support system using machine learning methods, in: Chaki,R., Cortesi, A., Saeed, K., Chaki, N. (Eds) Advanced Computing and Systems for Security. Advances in Intelligent Systems and Computing. Springer, New Delhi, pp.111-121, 2016. https://doi.org/10.1007/978-81-322-2650-5_8
7. [7] Bhargav, KS, Thota DSSB, Kumari TD, Vikas B. Application of Machine Learning Classification Algorithms on Hepatitis Dataset. International Journal of Applied Engineering Research 13 (2018) 12732–12737.
8. [8] Ahammed K, Satu MS, Khan MI, Whaiduzzaman M. Predicting Infectious State of Hepatitis C Virus Affected Patient's Applying Machine Learning Methods, Paper presented at 2020 IEEE Region 10 Symposium (TENSYMP), Dhaka, Bangladesh, 5-7 June, IEEE, pp. 1371-1374, 2020. http://doi: 10.1109/TENSYMP50017.2020.9230464.

9. [9] Syafa’ah L, Zulfatman Z, Pakaya I, Lestandy M. Comparison of Machine Learning Classification Methods in Hepatitis C Virus. Jurnal Online Informatika 6(2021) 73–78. https://doi.org/10.15575/JOIN.V6I1.719
10. [10] Nandipati SC, XinYing C, Wah KK. Hepatitis C Virus (HCV) Prediction by Machine Learning Techniques. Applications of Modelling and Simulation 4 (2020) 89–100.
11. [11] Shlens J. A tutorial on principal component analysis. arXiv preprint 2014. https://doi.org/10.48550/arXiv.1404.1100
12. [12] 12. Abdi H, Williams LJ. Principal component analysis, Wiley Interdisciplinary Reviews: Computational Statistics 2 (2010) 433-459. https://doi.org/10.1002/wics.101
13. [13] Jolliffe I. Principal component analysis, in Lovric M.(Ed.).International Encyclopedia of Statistical Science. Springer Series in Statistics. Springer, Berlin/Heidelberg, pp.1094-1096, 2011. . https://doi.org/10.1007/978-3-642-04898-2_455
14. [14] Kuhn M, Johnson K. Applied predictive modeling, first ed. Springer, New York, 2013.
15. [15] Kuhn M, Johnson K. Feature engineering and selection: A practical approach for predictive models, first ed. CRC Press, London, 2019.
16. [16] Hotelling H. Analysis of a complex of statistical variables into principal components. Journal of Educational Psychology 24 (1933) 417-441.
17. [17] Shafizadeh-Moghadam H. Fully component selection: An efficient combination of feature selection and principal component analysis to increase model performance. Expert Systems with Applications 186 (2021) 115678. https://doi.org/10.1016/J.ESWA.2021.115678
18. [18] Vinodhini G, Chandrasekaran RM. Sentiment Mining Using SVM-Based Hybrid Classification Model, in: Krishnan G, Anitha, R, Lekshmi R, Kumar, M, Bonato A, Graña M (Eds). Advances in Intelligent Systems and Computing. Paper presented at Computational Intelligence, Cyber Security and Computational Models, Coimbatore, India, 19-21 December. Springer, New Delhi, 246, pp.155-162. 2014. https://doi.org/10.1007/978-81-322-1680-3_18
19. [19] Liang N, Tuo Y, Deng Y, He T. PCA-based SVM classification for simulated ice floes in front of sluice gates. Polar Science (2022) 100839. https://doi.org/10.1016/j.polar.2022.100839.
20. [20] Yanqing Z, Shiwei Z, Junfeng Y, Lei W. Predicting corporate financial distress by PCA-based support vector machines, Paper presented at 2010 International Conference on Networking and Information Technology, Manila, 11-12 June, IEEE, pp. 373-376, 2010. https://doi.org/10.1109/ICNIT.2010.5508491
21. [21] Dua D, Graff C. UCI Machine Learning Repository [http://archive. ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science 2019. (accessed Nov. 15, 2021).
22. [22] Jolliffe I. A 50-year personal journey through time with principal component analysis. Journal of Multivariate Analysis 188 (2022) 104820. https://doi.org/10.1016/J.JMVA.2021.104820
23. [23] Uddin MP, Mamun MA, Hossain MA. PCA-based Feature Reduction for Hyperspectral Remote Sensing Image Classification. IETE Technical Review 38 (2021) 377–396. https://doi.org/10.1080/ 02564602.2020.1740615
24. [24] Schreiber JB. Issues and recommendations for exploratory factor analysis and principal component analysis. Research in Social and Administrative Pharmacy 17 (2021) 1004–1011. https://doi. org/10.1016/J.SAPHARM.2020.07.027
25. [25] Nocedal J, Wright SJ. Numerical Optimization, second ed. Springer, Berlin/Heidelberg, Germany, 2006.
26. [26] Cirillo A, Laudante G, Pirozzi S. Tactile sensor data interpretation for estimation of wire features. Electronics (Switzerland) 10(2021) 1458. https://doi.org/10.3390/ELECTRONICS10121458
27. [27] Toropova AP, Toropov AA, Benfenati E. Semi-correlations as a tool to model for skin sensitization. Food and Chemical Toxicology 157 (2021) 112580. https://doi.org/10.1016/j.fct.2021.112580
28. [28] Lim JY, Nam JS, Shin H, Park J, Song HI, Kang M, Lim K, Choi Y. Identification of Newly Emerging Influenza Viruses by Detecting the Virally Infected Cells Based on Surface Enhanced Raman Spectroscopy and Principal Component Analysis. Analytical Chemistry 91 (2019) 5677–5684. https://doi.org/10.1021/acs. analchem.8b05533