BREAST CANCER RISK ASSESSMENT USING RANDOM FOREST CLASSIFICATION AND TENSORFLOW LITE BASED ANDROID DEPLOYMENT

Abstract: Breast cancer remains one of the leading causes of cancer-related mortality among women worldwide, making early detection and accurate diagnosis essential for improving patient survival rates. Traditional diagnostic methods often require specialised medical expertise, advanced healthcare facilities, and considerable processing time, which may lead to delays in diagnosis and treatment. To address these challenges, this study proposes an AI-enabled Android application for breast cancer prediction using a Random Forest machine learning classifier. The proposed system utilises a breast cancer diagnostic dataset that undergoes preprocessing, feature selection, and normalisation to enhance data quality and model performance. The dataset is divided into training and testing subsets, and a Random Forest classifier is trained to accurately classify tumours as benign or malignant. The trained model is evaluated using performance metrics such as accuracy, precision, recall, F1-score, and confusion matrix to ensure reliable prediction capability. To enable real-time mobile deployment, the optimised model is converted into TensorFlow Lite format and integrated into an Android application. The mobile application allows users to enter diagnostic parameters and instantly receive prediction results without requiring complex computational resources. Experimental results demonstrate that the proposed model achieves high classification accuracy and effectively distinguishes between benign and malignant cases with minimal prediction errors. The integration of machine learning and mobile healthcare technology provides a cost-effective, accessible, and user-friendly solution for breast cancer risk assessment. The proposed system has the potential to support healthcare professionals in clinical decision-making, facilitate early disease detection, and improve overall healthcare outcomes through intelligent and portable diagnostic assistance.

Keywords: Breast Cancer Prediction, Random Forest Classifier, Machine Learning, Android Application, TensorFlow Lite, Artificial Intelligence, Healthcare Analytics, Early Disease Detection.