CERVICAL CANCER PREDICTION USING ARTIFICIAL NEURAL NETWORKS: A CASE STUDY ON NIGERIAN HEALTHCARE DATA

Abstract

Cervical cancer remains a leading cause of morbidity and mortality in low- and middle-income countries (LMICs), particularly in Nigeria, where limited healthcare resources, inadequate screening programs, and late detection exacerbate the burden. Despite advances in medical science, early detection remains a significant challenge due to socioeconomic barriers and insufficient diagnostic infrastructure. This study addresses these issues by developing a predictive model leveraging Artificial Neural Networks (ANNs) tailored to a Nigerian dataset. The model utilizes advanced data preprocessing techniques, including the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance and Genetic Algorithms (GA) for feature selection, thereby optimizing the predictive accuracy and efficiency of the ANN. The dataset, consisting of 858 records of demographic, clinical, and lifestyle attributes, was preprocessed to handle missing data and normalize features. After applying SMOTE and GA, the optimized ANN model achieved an accuracy of 87%, a recall of 71%, and an Area Under the Curve (AUC) of 0.85, demonstrating significant improvements over baseline models. These results underscore the potential of machine learning to enhance cervical cancer prediction, particularly in resource-constrained settings like Nigeria. This study highlights the transformative potential of artificial intelligence (AI) in reducing healthcare disparities by providing scalable, localized solutions for early cancer detection. It also emphasizes the importance of integrating domain-specific datasets to improve model relevance and performance. The findings provide a foundation for future research aimed at deploying AI-driven healthcare systems in LMICs, with the ultimate goal of reducing cervical cancer-related mortality and improving public health outcomes.