Subject Area
Electronics and Communication Engineering
Article Type
Original Study
Abstract
Every year, millions of people around the world experience health issues due to liver disease, and It is also being a major global cause of mortality. A variety of factors, such as obesity and hepatitis infection, can harm the liver and contribute to these disorders. However, diagnosis of chronic liver disease is often an expensive and complex process, and early detection of liver disease poses challenges because of its elusive symptoms that can often lead to delayed diagnosis. We employed machine learning for this study, to anticipate individuals with liver diseases before symptoms appear. To attain the best accuracy, we create a proposed model that uses grey wolf optimization for select the important features and an additional tree classifier to achieve high accuracy. Using criteria such as accuracy, sensitivity, specificity, precision, recall, and F1-score, we assess the models' performance. Additionally, we contrasted the outcomes of this methodology with a number of machine learning algorithms, including support vector machine, decision tree, gradient boosting, random forest, naive bayes, logistic regression, k-nearest neighbor, and extra tree. The findings demonstrate that our proposed model outperforms traditional approaches in predicting liver diseases with high accuracy and F1-score. The Proposed model performs the best, with an overall processing time of 1.5s, an F1-score of 100%, 100% Precision, 100% Recall, and 99.5% Accuracy.
Keywords
Machine learning algorithms, Classification, Prediction, GWO
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Khedr, Abrar Rizk M.; Saleh, Ahmed I.; Samra, Ahmed S.; and AbdElhalim, Eman
(2023)
"Early Liver Disease Diagnosis using Grey Wolf Optimization Algorithm,"
Mansoura Engineering Journal: Vol. 49
:
Iss.
3
, Article 1.
Available at:
https://doi.org/10.58491/2735-4202.3146
