http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Hepatitis C Severity Prognosis: A Machine Learning Approach
Jangiti Jaydev,Paluri Charit Gupta,Vadlamani Sumedha,Jindal Sumit Kumar 대한전기학회 2023 Journal of Electrical Engineering & Technology Vol.18 No.4
The objective of this work is to accurately predict the severity of the Hepatitis C virus using various Machine Learning (ML) algorithms. This study is developed using thirteen different blood biomarkers, which can classify Hepatitis C into three main classifications: Hepatitis-C, Fibrosis, Cirrhosis. The proposed work studies various algorithms and compares them based on their accuracy rate of predicting the severity. The authors analyzed five ML algorithms relying only on patient demographics and blood biomarker values. Performed a comparative study between algorithms like Random Forest, K-Nearest Neighbors (KNN), Decision Tree, Cat Boost, and Gradient Boost, based on their performance, accuracy rate, F1 score, and confusion matrix. These employed algorithms are supervised learning algorithms since they produce a valuable solution for classification and prediction of the degree of Hepatitis- C virus, alongside accurate rate prediction. One of the models was able to evaluate the severity with an accuracy of 98.7%. Furthermore, for the evaluation of Hepatitis C in this patient cohort, most of the models beat numerous current diagnostic options, including liver biopsy.