MACHINE LEARNING FRAMEWORK FOR ACCURATE PREDICTION OF HEPATITIS C VIRUS INFECTION

The current paper managed to develop an efficient machine learning algorithm for HCV disease predictions. The designed framework considers the implementation of data pre-processing, feature extraction, class balancing with SMOTE approach, and the use of the Random Forest algorithm for the development of the final classification model. It was possible to reach an accuracy level of approximately 96.6% in the process. Several advantages are associated with the usage of the proposed framework. Among such benefits, there should be mentioned faster diagnostics, reduced labor costs, increased prediction accuracy, as well as assistance in clinical decisions. As a result, the early identification of HCV patients is going to be possible. As for future developments, it is necessary to mention that in the future it will be possible to integrate big data approaches, the use of deep learning algorithms, cloud deployment opportunities, as well as real-time healthcare management systems.

[1]  S. Dash, S. K. Shakyawar, M. Sharma, and S. Kaushik, ‘‘Big data in healthcare: Management, analysis and future prospects,’’ J. Big Data, vol. 6, no. 1, p. 54, Dec. 2019.  [2]  J. Han, J. Pei, and M. Kamber, Data Mining: Concepts and Techniques. Amsterdam, The Netherlands: Elsevier, 2012.  [3]  B. Hajarizadeh, J. Grebely, and G. J. Dore, ‘‘Epidemiology and natural history of HCV infection,’’ Nature Rev. Gastroenterol. Hepatol., vol. 10, no. 9, pp. 553–562, Sep. 2013. [4]     J. S. Bajaj, ‘‘Alcohol, liver disease and the gut microbiota,’’ Nature Rev. Gastroenterol. Hepatol., vol. 16, no. 4, pp. 235–246, Apr. 2019. [5]  J.-H. Wang, C.-H. Chen, C.-M. Chang, W.-C. Feng, C.-Y. Lee, and S.-N. Lu, ‘‘Hepatitis C virus core antigen is cost-effective in community based screening of active hepatitis C infection in Taiwan,’’ J. Formosan Med. Assoc., vol. 119, no. 1, pp. 504–508, Jan. 2020.  [6]  T. Boettler, P. N. Newsome, M. U. Mondelli, M. Maticic, E. Cordero, M. Cornberg, and T. Berg, ‘‘Care of patients with liver                  disease                     during          the COVID19pandemic:EASLSCMIDpositionpaper,’’JHEPRep.,v ol.2, no. 3, Jun. 2020, Art. no. 100113.  [7]   J. H. Hoofnagle, ‘‘Hepatitis C: The clinical spectrum of disease,’’ Hepa tology, vol. 26, no. S3, pp. 15S–20S, Dec. 1997.  [8]  A. M. Anter, S. Bhattacharyya, and Z. Zhang, ‘‘Multi-stage fuzzy swarm intelligence for automatic hepatic lesion segmentation from CT scans,’’ Appl. Soft Comput., vol. 96, Nov. 2020, Art. no. 106677. [9]    R. T. Ribeiro, R. T. Marinho, and J. M. Sanches, ‘‘Classification and stag ing of chronic liver disease from multimodal data,’’ IEEE Trans. Biomed. Eng., vol. 60, no. 5, pp. 1336–1344, May 2013.  [10] G. Chandrasekaran, P. R. Karthikeyan, N. S. Kumar, and V. Kumarasamy, ‘‘Test scheduling of system-on-chip using dragonfly and ant lion opti mization algorithms,’’ J. Intell. Fuzzy Syst., vol. 40, no. 3, pp. 4905–4917, Mar. 2021, doi: 10.3233/JIFS-201691.