Grouping Medical Record Data By Type Diseases With K-Means Algorithm

Abstract

Health is a very valuable thing for human life, because anyone can be affected by health problems without realizing what causes it. People who pay less attention to their health are more likely to get sick. Lack of awareness in protecting and preserving the environment will lead to the rapid spread of disease. Efforts in disease prevention are needed by increasing public awareness about the importance of clean and healthy living behavior. In the application of the k-means algorithm for data processing in finding medical record files in the form of notes and documents about patient identity, examination, treatment, and other service actions given to patients. Clustering is a data analysis method that performs the modeling process without supervision (unsupervised) is also a method that performs data grouping with a partition system. The result is grouping using K-Means Clustering which can help in grouping by type of disease and age, the results are divided into children and toddlers, young and adults, old and elderly.