|
|
| |
| Detection of Hepatitis (A, B, C, D and E) Viruses Using Machine Learning |
Alile Solomon Osarumwense and Bello Moses Eromosele
|
Abstract:
Hepatitis Disease is a life threatening inflammatory condition of the liver cells that causes damage to the liver which is usually caused by a viral infection which affects persons ranging from infants, older children and adults in respective of age. This disease is caused by Single Stranded RNA Virus (ssRNA Virus family), Symmetrical RNA Virus (sRNA Virus family) and Double-Stranded DNA Virus (dsDNA Virus family). Furthermore, the transmitted Hepatitis Virus is of five types namely: Hepatitis A Virus (HAV), Hepatitis B Virus (HBV), Hepatitis C Virus (HCV), Hepatitis D Virus (HDV) and Hepatitis E Virus (HEV) respectively. The symptoms of this disease are jaundice, fever, fatigue, loss of appetite, nausea, vomiting, abdominal pain, joint pain, dark urine, clay colored faeces and diarrhea just to name a few. Additionally, WHO declared that Hepatitis virus occurs sporadically and categorized as an epidemic worldwide, with a tendency for repeated recurrences. This Hepatitis infection has caused millions of death worldwide yearly due to lack of early diagnosis of the ailment. In recent past, several systems have been developed to diagnose this endemic disease, but they generated a lot of false negative during testing and were unable to detect Hepatitis Disease, its overlapping symptoms and various types. Hence, in this paper, we proposed and simulated a model to predict Hepatitis (A, B, C, D and E) using a machine learning technique called Bayesian Belief Network. The model was designed using Bayes Server and tested with data collected from Hepatitis UCI medical repository. The model had a 99.97% prediction accuracy and 96.98%, 95.08%, 97.32%, 98.11%, 97.71% and 95.71% sensitivity of Hepatitis Disease, HAV, HBV, HCV, HDV and HEV in that order.
|
|
|
| | |