GLIOMA TREATMENT STRATEGIES PREDICTION SYSTEM USING LOGISTIC REGRESSION ALGORITHM
Abstract
Glioma refers to a group of tumours that start in the glial cells in the brain. These cells support the function of the other main brain cell type, the neuron. The delayed diagnosis of glioma can lead to inappropriate treatment choices, impacting patient survival and quality of life. This research work focuses on developing a system for predicting treatment strategies using machine learning. The Design Science Research Methodology (DSRM) guided this research work while Rapid Application Development (RAD) guided the development of the prediction system. The system was developed using Python Integrated Development and Learning Environment, Google Colab and Ydata_profiling. In some of the approaches for predicting glioma treatment strategies proposed in extant literature, the accuracy, time consumption, and potential errors were the major issues. After evaluating six machine learning algorithms (Random Forest, Support Vector Machine, Decision Tree, Logistics Regression, Naïve Bayes and K-Nearest Neighbour), we were able to achieve the highest accuracy of 88.462.pkl with Logistics Regression.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.