International Journal of Multidisciplinary Research and Publications ISSN (Online): 2581-6187 160 Yunita Sartika Sari, “Implementation of Naïve Bayes Classifier to Determine Disease,” International Journal of Multidisciplinary Research and Publications (IJMRAP), Volume 6, Issue 2, pp. 160-163, 2023. Implementation of Naïve Bayes Classifier to Determine Disease Yunita Sartika Sari Universitas Mercu Buana, Jl. Meruya Selatan No.1 Email address: yunita.sartika@mercubuana.ac.id Abstract—Information system is a system that provides information for management in making decisions. One of the efforts made to improve the quality of health services requires an optimal and structured system that is easy to use. In this study data collection was carried out through interviews and using the Naïve Bayes Classifier method. For the method of analysis using the SWOT method. The purpose of this study is to determine common diseases by implementing the Naïve Bayes method. Keywords— Information Systems, Naïve Bayes, Classifier. I. INTRODUCTION Background In the current era of globalization, technological advances are growing rapidly, including in the health sector. The availability of health information is very necessary in the implementation of effective and efficient health efforts. One of these technological advancements is Information Technology which has developed throughout all areas of human life. Medical record is a file that contains notes and documents regarding patient identity, examination, treatment and other actions for patients while receiving treatment at service providers for patients both inpatient and outpatient [1]. In 2003 RAND Health Information Technology (HIT) began conducting studies to better understand the role and importance of Electronic Medical Records (EMR) in improving health services and informing the government so they can maximize the benefits of EMR and improve health services. Electronic Medical Record (EMR) is a system that contains a patient's medical history and illness, diagnostic test results, other medical data and information on treatment costs. The development of information technology that is currently happening allows the development of a way of storing and managing data electronically, at the Pekanbaru "X" Hospital just implementing the Electronic Medical Record (EMR)[2]. Based on the Attachment to SK PB IDI No 315/PB/A.4/88 Concerning Health Medical Records, records in written form or descriptions of service activities provided by medical/health service providers to a patient. Based on the Decree of the Minister of Health Number: 269/Menkes/PER/III/2008 concerning medical records, it is explained that a medical record is a file that contains notes and documents regarding patient identity, examination, treatment, actions and other services that have been provided to patients. This study aims to facilitate the community's needs in knowing the disease based on the symptoms felt and make it easier to receive health information online using the Naïve Bayes Classifier Method. Based on the background above, we identify and formulate problems to provide information regarding health easily and efficiently The goal to be achieved in this research is to be able to easily monitor diseases that often occur in the community. provide information about the history of the disease in each patient, and provide education to the public about the disease. The expected benefits of this research are expected to provide a sense of security to the community when checking conditions and provide interesting experiences so that people are not afraid to carry out health checks. II. LITERATURE REVIEW Naïve Bayes Classifier The RFM Method is used to analyze data for each customer based on segmentation using the "usage rate" attribute on the data, helping Naive Bayes, a method of classifying data, produce the result that 62% of the data is feasible and 38% is not feasible [4]. The processed data can then be used as a basic reference in decision-making. Based on the Bayes Theorem, the Naive Bayes Classifier is a straightforward probability classifier. The Bayes theorem will be paired with "Naive," which denotes the independence of each attribute and variable. In supervised learning, the Naive Bayes Classifier can be effectively trained [5]. X : Data with unknown class H: Hypothesis data is a specific class P(H/X): Probability of hypothesis H based on condition X (posteriori probability) P(H): Probability of the hypothesis H (probability prior) P(X/H): Probability of X based on conditions in the hypothesis HP(X): Probability of X Characteristics of the Naive Bayes Classifier The Naïve Bayes method works robustly on isolated data which is usually data with different characteristics (outliners). Naïve Bayes can also handle incorrect attribute values by ignoring training data during the model building and prediction processes. 1. Tough dealing with irrelevant attributes. 2. Attributes that have a correlation can degrade classification performance