<![CDATA[Dengue Hemorrhagic Fever (DHF) is a potentially hazardous condition and a health concern in various tropical countries. To accurately and swiftly detect this disease, various diagnostic methods have been developed. The incidence of DHF can fluctuate from year to year, influenced by factors such as weather changes, vector control efforts, and socio-economic aspects. In Indonesia, there have been significant outbreaks of DHF in certain years. In this study, the Author conducted a comparison between the Bayesian Theorem method and the Certainty Factor (CF) method to diagnose DHF symptoms. The Bayesian Theorem calculates the probability of the disease based on symptoms, while the Certainty Factor employs a confidence level to link symptoms with the disease. Symptom data from previous DHF patients were collected, and both methods were utilized to diagnose these cases. The analysis results indicate that both methods have their respective strengths and limitations in terms of accuracy and speed. The Bayesian Theorem is accurate when complete symptom data is available, while the Certainty Factor is useful when data is incomplete or uncertainty exists. Both methods can be used concurrently based on context. This research illustrates the application of statistical analysis and data-driven approaches to enhance DHF diagnosis, also stimulating the development of advanced combined methods in the future. This study provides insights into the use of probabilistic approaches and confidence-based logic in DHF diagnostic development. Both methods can be applied interchangeably or in conjunction, depending on data and case characteristics. The results of applying the Bayesian Theorem and Certainty Factor show that the Bayesian Theorem yields 57.29%, while the Certainty Factor achieves 94.47% accuracy in diagnosing DHF.]]>
Copyrights © 2023
