Implementation of the Web-Based K-Means Clustering Algorithm on Hypertension Levels in the Elderly at the Bungah District Health Center

Abstract

Hypertension is a systolic pressure above 140 mmHg and a diastolic pressure above 90
mmHg . Hypertension often occurs in the elderly, namely aged 45 to 90 years and over. This research
was carried out at the community health center in Bungah sub - district with the aim that so that patients
receive appropriate treatment, a web-based system is needed to group hypertension data into several
classes ( clusters ), so that degenerative diseases caused by hypertension can be minimized . The
method used in data grouping is the K-Means Clustering method . Clustering is one of the fields of
recognition science that is created so that a system can carry out grouping. In this study, 100
hypertension data were grouped into 4 clusters . The hypertension data used consists of two attributes,
namely systole and diastole . The working mechanism is to normalize the data first, then the system
groups the data into groups that have the same characteristics. Next, the system will display the results
of the clustering process which consists of four (4) clusters , namely cluster 1 Isolated Systolic
Hypertension, cluster 2 Grade 1 (mild hypertension), cluster 3 Grade 2 (moderate hypertension), and
cluster 4 Grade 3 (high hypertension). The data used for clustering is 100 data from blood pressure
examinations of patients at the Community Health Center using a sphygmomanometer. The results of
the last iteration of 100 hypertension data in the system were used as parameters for calculating the
level of effectiveness, by comparing the data from the clustering test results to the data from the
diagnosis a which produced an effectiveness value of 80%