CLINICAL DATA ANALYSIS FOR EARLY DETECTION OF CERVICAL CANCER USING MACHINE LEARNING
Abstract
This project aimed to leverage machine learning for early detection of cervical cancer, focusing
on the use of clinical data and risk factors. Through detailed data preprocessing, exploratory data
analysis (EDA), and the application of Decision Tree and Random Forest classifiers, we have
explored the potential of predictive models in identifying cervical cancer risks with notable
precision. Our research highlighted the importance of combining clinical indicators with risk
factors to enhance the predictive accuracy of our models. The Random Forest classifier, in
particular, demonstrated superior performance over the Decision Tree model, showcasing the
strengths of ensemble learning in complex prediction tasks. The analysis of feature importance
further provided valuable insights into the factors most predictive of cervical cancer, which could
guide future screening and prevention strategies.
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.