A DIAGNOSTIC MODEL FOR THE PREDICTION OF LIVER CIRRHOSIS USING MACHINE LEARNING TECHNIQUES
Liver cirrhosis is the most common type of chronic liver disease in the globe. The ability to forecast the onset of liver cirrhosis sickness is critical for successful treatment and the prevention of catastrophic health implications. As a result, the researchers created a prediction model using machine learning techniques. This study was based on a dataset from the Federal Medical Centre, Yola, which included 583 patient instances and 11 attributes. The proposed model for the prediction of liver cirrhosis sickness employed Nave Bayes, Classification and Regression Tree (CART), and Support Vector Machine (SVM) with 10-fold cross-validation. Accuracy, precision, recall, and F1 Score were used to evaluate the model's performance. Among all the strategies used in this study, the Support Vector Machine (SVM) technique produces the best results, with accuracy of 73%, precision of 73%, recall of 100%, and F1 Score of 84%. Based on medical data from FMC, Yola, this study shows that machine learning methods, specifically the Support Vector Machine, provide a more accurate prediction for liver cirrhosis sickness. This approach can be used to help doctors make better clinical decisions.
Copyright (c) 2022 Ganty Jamila; Gregory Msksha Wajiga, Yusuf Musa Malgwi, Abba Hamman Maidabara
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.Fair East Publishing has chosen to apply for the Creative Common Attribution Noncommercial 4.0 Licence (CC BY) license on our published work. Authors who wish to publish their manuscript in our journal agree on the following terms:
1. Authors retain the copyright and grant us (Fair East Publishing and its subsidiary journals) the right for first publication with the work licensed under a Creative Commons Attribution (CC BY) License which permits others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal. Under this license, author retains the ownership of the copyright of their content, but anyone is allowed to download, reuse, reprint, modify, distribute, and/or copy the contents as long as the original authors and source are cited. No permission is required from the publishers or authors.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (for example, publishing it as a book or submitting it to an institutional repository), with an acknowledgment of its initial publication in Fair East Publishing owned journals.
3. We encourage our authors/contributors to post their work online (such as posting it on their website or some institutional repositories) prior to and during the submission process since it produces scholarly exchange and greater and earlier citation of published work.