Intelligent System for Monkeypox Disease Diagnosis Using Hybrid Certainty Factor and Fuzzy Logic Methods

Abstract

Monkeypox cases has the potential to spread rapidly, making early detection crucial to prevent wider transmission. Unfortunately, at the UPT Puskesmas where this study was conducted, there is no system available to assist medical personnel in performing fast and standardized diagnoses. To address this issue, this research developed a web-based intelligent system by combining the Certainty Factor (CF) and Fuzzy Logic methods. The system’s knowledge base was constructed from symptom data collected through expert interviews and literature studies. It was then tested using data from 30 patients with similar symptoms. The processing involved calculating certainty values with CF and mapping them into fuzzy membership degrees. The test results showed an accuracy of 86%, demonstrating that the combination of CF and Fuzzy Logic improves diagnostic accuracy while providing results that are easier to interpret. Therefore, the developed system can serve as a diagnostic aid for monkeypox in primary healthcare centers, particularly in situations with limited diagnostic facilities, and can also serve as a foundation for developing intelligent detection technologies for other infectious diseases.