Predictive Insights Beyond Boundaries: Integrating Clinical Data for Hepatitis C Forecasting Using Machine Learning and Deep Learning

A person's well-being and wellness are seriously hampered by the chronic diseases' lasting implications and recurrent signs. A startling 58 million people worldwide suffer from an incurable chronic form of hepatitis C, disease is brought about by a virus called hepatitis C (HCV). Additionally, it results in 290,000 deaths every year from cirrhosis and liver cancer, both of which linked to HCV. The goal of this venture is to reliably identify and anticipate hepatitis C utilizing Machine Learning (ML) and deep Learning (DL) techniques. It does this by utilizing ML and DL algorithms' capacity to scan big datasets and spot patterns and associations that help with diagnosis. Predictive models were created utilizing blood values from 615 patients, including both hepatitis patients and healthy blood donors, using a variety of approaches comprising SVM, Logistic regression (LR), KNN, LSTM and others. The dataset underwent extensive preprocessing, which included managing missing values, scaling, and diminished dimensionality using Principal Component Analysis (PCA). After a variety of ML along with the SVM classifier showed the best result, giving an accuracy concerning 98.33%, recall concerning 94.17%, precision concerning 93.99%, and F1-score concerning 94.16%.