Data Classification of Patient Characteristics Based on Nutritional Treatment Using the K-Nearest Neighbors Algorithm

Abstract

For a company engaged in the service and health sector, it is essential to read consumers' characteristics to develop the company and produce the right products. It is still challenging to determine patients' nutritional treatment, with many patients' healthy treatment remained appropriate and accurate for each patient. Patient data collection and patient interviews are needed to obtain suitable treatment data for the patient. However, to get appropriate further treatment, a system must process past patient data, resulting in more accurate follow-up treatments. The method used in this study is to calculate the value of the training data and K point with the K-Nearest Neighbors (K-NN) Algorithm. The goal is to determine the treatment package menu recommendations for consumers. The K-Nearest Neighbors algorithm is one of the algorithms used for the implementation of this system development. The patient characteristics and data distance calculation using the euclidean distance function can produce a category used to determine a more accurate and good nutritional treatment for each patient. The scenario in the test with a comparison of training data and test data 3: 1 has the highest program accuracy reaching 88%, precision reaching 91%, and recall going 95% among all the results of the test scenario.