CERVICAL CANCER CLASSIFICATION USING SUPERVISED LEARNING WITH KNN ALGORITHM

Cervical cancer remains a leading cause of morbidity and mortality worldwide, making early detection a critical factor for improving patient outcomes. This study presents a method for classifying cervical cancer using the k-Nearest Neighbors (KNN) algorithm, a supervised learning technique, to identify the likelihood of cervical cancer based on clinical and demographic features. The dataset used for this study includes attributes such as age, HPV infection status, and histopathological findings. Pre-processing steps involve resizing input images to standard dimensions, preparing the data for training the KNN classifier. The KNN algorithm is chosen due to its simplicity, effectiveness, and ability to handle multidimensional data with minimal computational cost. The model’s performance is assessed through cross-validation, utilizing metrics such as accuracy, precision, recall, and F1-score. The classification output categorizes the cases as "Normal" or "Abnormal," indicating the presence or absence of cervical cancer. Experimental results show that the KNN algorithm offers a reliable solution for early cervical cancer detection, yielding promising classification performance. This work demonstrates the potential of supervised learning in medical diagnostics, particularly for aiding healthcare professionals in making accurate and timely decisions in cervical cancer diagnosis, ultimately contributing to the ongoing advancement of AI-assisted healthcare solutions.

Index Terms— Cervical cancer images Dataset, KNN algorithm, supervised learning, machine learning, medical image processing.