Disease detection is one of the applications where data mining techniques achieved more accurate and useful results. The healthcare sector collects massive volumes of healthcare data that are not mine to discover hidden data for better decision-making, a field of data mining introduces more efficiently and effectively to predict different kinds of diseases.
Clustering medical data into small, meaningful chunks will help in pattern discovery by allowing for the retrieval of a large number of specific data points.
The difference in using clustering the medical data from traditional data mining techniques is in extracting many features of the dataset that have been split into small segments to enable us to discover patterns by adding the data structure. By using clustering techniques, discovered overall correlations between data attributes. Selected data processing makes the mining process more efficient.
The processed disease data are clustered using the K-means algorithm with the K values. Its ease of use and speed, which enable it to perform on a massive dataset. This paper highlights the theoretical side in using the K-Means Clustering algorithm in the context of data mining of disease detection and allowing for reliable and effective diagnosis.
Keywords: Data Mining, Healthcare Sector ,K-Means Clustering.