<![CDATA[Respiratory system disease diagnosis often faces challenges in ensuring the accuracy of results due to the complexity of overlapping symptoms. In particular, a method is needed that is able to handle data uncertainty and utilize existing evidence optimally. This study aims to compare two methods, namely Bayes' Theorem and Dempster-Shafer, in diagnosing three types of respiratory diseases: Asthma, Tuberculosis, and Bronchitis. The solution is done by analyzing the percentage of confidence produced by each method based on symptom data. The results show that Bayes' Theorem produces the highest confidence for Tuberculosis (74.92%), while Dempster-Shafer provides the highest confidence for Bronchitis (80%). This comparison indicates that the selection of methods must be adjusted to the characteristics of the data and the needs of the analysis. This study contributes to providing insight into the advantages and disadvantages of each method, which can be used as a reference in developing a more accurate disease diagnosis decision support system.]]>
Copyrights © 2025
