Implementation Of Naive Bayes For Web-Based Patient Demographic Classification At Boy Fazriansyah General Practitioner Practice

Abstract

The development of information technology encourages healthcare facilities to utilize information systems to improve the quality of healthcare services and patient data management. At Boy Fazriansyah General Practitioner Practice, patient data and medical records were previously managed manually, causing patient demographic data to be underutilized. This study aims to implement the Naive Bayes algorithm in a web-based general practitioner system to classify patients’ economic levels based on demographic data. Naive Bayes is a probabilistic classification method based on Bayes’ Theorem, assuming that each attribute is independent of the others. The classification process uses training data by calculating the probability of each class and the probability of each attribute for each class, then determining the class with the highest probability. The attributes used include age, gender, education, occupation, income, and number of dependents, resulting in Low, Medium, and High economic-level categories. The system was developed using the Waterfall method with PHP, Laravel, Bootstrap, and SQLite. Testing was conducted using Black Box Testing and User Acceptance Testing (UAT). The results show that the system successfully classifies patients’ economic levels and provides the results as supporting information for doctors in providing healthcare services.