An Intelligent Diagnosis System Based on SVM with Dragonfly Metaheuristic Algorithm for Preventing and Predicting Hepatitis C Infection

About 70 million people around the world have been infected with hepatitis C, resulting in about 400,000 deaths per year. It is possible to save lives by providing diabetic patients with an accurate diagnosis and by detecting hepatitis C in its initial phases. Hepatitis C and its prognosis can be better understood with the help of electronic health records (EHRs). Most commonly, it contains clinical practice statistics generated by computer-based procedures. Using these methods, the new tendencies and patterns that normally go unnoticed by medical professionals were uncovered. An automatic diagnosis method based on various machine learning (ML) models is studied in this research to detect hepatitis C in the electronic health records of 615 patients. A new SVM prediction model with Dragonfly (DF) technique is implemented to predict the blood donor, the suspected blood donor, hepatitis, fibrosis, and cirrhosis stages of HCV using real-time blood samples. The F-value, recall, precision, and accuracy performance matrices are used to compare the proposed and existing diagnosis systems with variation of SVM technique. All techniques are tested and put into action using the python.