Measurement of health service performance through machine learning using clustering techniques

The health center is the first level public health service center that is run by the Indonesian government. Organizing quality health center services of health center is the hope and satisfaction of every patient. The dimensions of patient satisfaction vary greatly and the scope is very wide. Patient satisfaction can be used as an indicator of quality and service performance of health center. The purpose of this study was to measure the performance of health center services in order to determine the level of patient satisfaction and grouping the Patient Satisfaction Index. With the knowledge of the dimensions of performance and quality of health services provided by the health center, it will facilitate the government in carrying out the function of guidance and control of the health center. This study uses a Machine Learning technology approach with clustering techniques, by grouping the Patient Satisfaction Index with K-Means (Hard Clustering) and Fuzzy C-Mean (Soft Clustering) methods. Based on the subsets produced, clustering techniques can be divided into 2 methods, namely hard clustering techniques and soft clustering techniques. The K-Mean method is widely used in clustering techniques. K-Mean has advantages in computational speed and relatively easy process stages. While the Fuzzy C-Means method has advantages in terms of flexibility in determining clusters so that there is little possibility of converging failure. The experimental results of the Patient Satisfaction Index show that the K-Means method provides better performance with a value of 96% compared to the Fuzzy C-Means method with a value of 76%.