Early Identification of cervical cancer using K-Nearest Neighbor (KNN)
N. Meenakshisundaram, G. Ramkumar
Abstract
Cervical cancer is the fourth most common form of the disease worldwide. It is more common in low-income nations. However, if the diagnosis is made quickly, the patient's clinical treatment might go more smoothly. The lack of trained health cytotechnicians is a major problem, since so many individuals require their conditions diagnosed. Computer-assisted diagnostics (CAD) systems may be extremely useful in improving the accuracy, reliability, speed, and cost of medical diagnosis. This study use K-Nearest Neighbor (KNN) to locate cervical cancer. The Kaggle Website provides access to the Cervical Cancer Dataset (CCD). In the cervical cancer dataset, you will find 32 characteristics and 4 target variables. The suggested model KNN is then compared to the baseline approach Naive Bayes, and conclusions are formed on the superiority of one algorithm over the other.