Diagnosing the Stage of Hepatitis C Using Machine Learning
Muhammad Bilal Butt1, Majed Alfayad2, Shazia Saqib1
1Department of Computer Science, Lahore Garrison University, Lahore 54000, Pakistan.
Insights
This study introduces an Intelligent Hepatitis C Stage Diagnosis System (IHSDS) using Artificial Neural Network (ANN) for accurate Hepatitis C staging. The IHSDS achieved high precision, offering a non-invasive alternative to liver biopsy for disease management.
Area of Science:
- Hepatology
- Medical Informatics
- Artificial Intelligence
Background:
- Hepatitis C is a global health concern with millions of new cases annually.
- Accurate staging of Hepatitis C is crucial for effective patient management and treatment.
- Traditional methods for staging can be invasive, necessitating alternative approaches.
Purpose of the Study:
- To develop and evaluate an Intelligent Hepatitis C Stage Diagnosis System (IHSDS).
- To utilize machine learning, specifically Artificial Neural Network (ANN), for non-invasive Hepatitis C staging.
- To compare the performance of the proposed system with existing models.
Main Methods:
- A dataset with 29 features was sourced from the UCI machine learning repository.
- 19 relevant features were selected for the study.
- The dataset was split into 70% for training and 30% for validation.
- An Artificial Neural Network (ANN) model was implemented within the IHSDS.
Main Results:
- The IHSDS demonstrated high predictive accuracy.
- Achieved 98.89% precision during the training phase.
- Achieved 94.44% precision during the validation phase.
Conclusions:
- The IHSDS provides a precise and non-invasive method for Hepatitis C staging.
- Machine learning, particularly ANN, is a viable tool for diagnosing liver disease stages.
- The developed system shows significant potential for clinical application in Hepatitis C management.
Abstract:
Hepatitis C is a prevalent disease in the world. Around 3 to 4 million new cases of Hepatitis C are reported every year across the globe. Effective, timely prediction of the disease can help people know about their Stage of Hepatitis C. To identify the Stage of disease, various noninvasive serum biochemical markers and clinical information of the patients have been used. Machine learning techniques have been an effective alternative tool for determining the Stage of this chronic disease of the liver to prevent biopsy side effects. In this study, an Intelligent Hepatitis C Stage Diagnosis System (IHSDS) empowered with machine learning is presented to predict the Stage of Hepatitis C in a human using Artificial Neural Network (ANN). The dataset obtained from the UCI machine learning repository contains 29 features, out of which the 19 most reverent are selected to conduct the study; 70% of the dataset is used for training and 30% for validation purposes. The precision value is compared with the proposed IHSDS with previously presented models. The proposed IHSDS has achieved 98.89% precision during training and 94.44% precision during validation.
