Effective Application of Supervised KNN Algorithm to Ascertain and Assess Abnormal Growth of Blood Cancerous Cells Predictive Modeling

When it comes to healthcare, finding the undetected pattern or clues and interconnecting them for a proper estimation and then eventually diagnoses is very important what can be more helpful than Data mining in this perspective and that too (KNN) regression? In this, we have examined a few datasets of different patients’ clinical and genetic traits related to blood cancerous cells. By this research, we hope to improve the early prediction as well as detection of leukemia enhancing its precision and accuracy so that a better diagnostic outcome can be achieved. Based on X and Y factors that are collected, the algorithm examines the proximity of a given data point to its K-nearest neighbors and estimates how prone the patient is to the deadly cancerous disease. We equalize the factors to increase and enhance the proper end prediction’s effects and its suitability to the situation. Blood malignancy can be probabilized by making use of the full-blood count of the patient this can be done by undertaking a blood test. By doing this, we ultimately aim to prove that KNN regression can be efficiently used in leukemia forecasting and further its successful use as a professional tool in the field of computerized medicine research.