Publication Date: 2023/10/07
Abstract: The ongoing threat that cancer poses to the health and prosperity of the world highlights the critical need for early identification and efficient treatment. Machine learning and artificial intelligence have become effective tools for the early detection of diseases like cancer. The K-Nearest Neighbors (KNN) method stands out among them for its efficiency and simplicity. The goal of this study is to use the R implementation of the KNN algorithm to advance the identification of prostate cancer. A difficult diagnostic challenge is presented by the complicated and multifaceted illness of prostate cancer. This work seeks to develop precision medicine in oncology by improving the accuracy and reliability of prostate cancer detection using the capabilities of KNN. The study examines the prostate cancer detection landscape, presents the KNN algorithm's uses in medicine, and describes the study's goals. The KNN model is trained and tested using a dataset that has been pre-processed and used in this methodology. The findings have the potential to revolutionize the detection of prostate cancer by offering a data-driven strategy to supplement healthcare professionals' clinical judgement, thereby improving patient outcomes, and even saving lives.
Keywords: Prostate Cancer, Early Detection, Machine Learning, K-Nearest Neighbors (KNN), Precision Medicine, Diagnosis, Artificial Intelligence.
DOI: https://doi.org/10.5281/zenodo.8416100
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT23SEP1725.pdf
REFERENCES