How to Increase the Effectiveness of the Hepatitis Diagnostics by Means of Appropriate Machine Learning Methods
This paper presents how to improve the diagnostic process of hepatitis B and C based on collected questionnaires from patients hospitalized in all regional departments of infectology in Slovakia. Performed experiments were oriented in two directions: economic demands of the recommended treatment based on realized diagnostics and possible improvement of hepatitis diagnostics by means of exploratory and predictive analysis of additional information provided by patients. Exploratory data analysis was used to confirm or to reject some expected relationships between input attributes (e.g. ager or gender) and target diagnosis. Also, predictive mining resulted into interesting decision rules that can be used in medical practice as supporting information at an early stage of the diagnostic process. Finally, analysis of the treatment economic demands based on the estimated costs showed the need for timely and quality diagnostics to minimize the percentage of patients for which was hepatitis diagnosed late.
KeywordsHepatitis CHAID Cost-benefit method
This publication is the result of the Project implementation: University Science Park TECHNICOM for Innovation Applications Supported by Knowledge Technology, ITMS: 26220220182, supported by the Research & Development Operational Programme funded by the ERDF (50 %); supported also by the Slovak Grant Agency of the Ministry of Education and Academy of Science of the Slovak Republic under grant No. 1/1147/12 (50 %).
- 1.Schréter, I., Kristian, P., Klement, C., Kohútová, D., Jarčuška, P., Maďarová, L., Avdičová, M., Máderová, E.: Prevalencia infekcie vírusom hepatitídy C v Slovenskej republike. Klin Mikrobiol Inf Lék 13(2), 54–58 (2007)Google Scholar
- 4.Chen, X., Ma, L., Chu, N., Hu, Y.: Diagnosis based on decision tree and discrimination analysis for chronic hepatitis b in TCM. In: Proceedings of 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops (BIBMW 2011), pp. 817–822. doi: 10.1109/BIBMW.2011.6112478
- 6.Sathyadevi, G.: Application of CART algorithm in hepatitis disease diagnosis. In: Proceedings of IEEE Recent Trends in Information Technology (ICRTIT 2011), pp. 1283–1287 (2011)Google Scholar
- 9.Roslina, A.H., Noraziah, A.: Prediction of Hepatitis Prognosis using support vector machine and wrapper method. In: Proceeding of IEEE Fuzzy Systems and Knowledge Discovery (FSKD 2010), pp. 2209–2211 (2010)Google Scholar
- 12.Vranova, J., Horak, J., Kratka, K., Hendrichova, M., Kovarikova, K.: ROC analysis and the use of cost-benefit analysis for determination of the optimal cut-point. J. Czech Phys. 148, 410–415 (2009)Google Scholar
- 15.Lopez-Raton, M., Rodriguez-Alvarez, M.X., Suarez, C.C., Sampedro, F.G.: OptimalCutpoints: an R package for selecting optimal cutpoints in diagnostic tests. J. Stat. Softw. 61(8), 1–36 (2014)Google Scholar
- 16.Kerber, R.: ChiMerge: discretization of numeric attributes. In: Proceedings of the Tenth National Conference on Artificial Intelligence, pp. 123–128 (1992)Google Scholar