<![CDATA[One of the main reasons people become disabled or die is because of a stroke. The key to swift and effective therapy is an early diagnosis. This research examines the relative performance of the Naïve Bayes and Random Forest algorithms in identifying stroke cases using data collected from patients at the Cipayung Health Center. Age, gender, BMI, smoking status, hypertension, and other physical and mental health issues are some of the characteristics represented in the 644 samples used in the study. Collecting data, cleaning it up, and then evaluating the model using metrics like recall, precision, and accuracy are all part of the research process. With a 92% accuracy rate, the Random Forest algorithm outperformed Naïve Bayes (87% accuracy rate), according to the data. Medical professionals may use these results as a guide to improve stroke detection, which in turn accelerates treatment and lessens the likelihood of consequences. The findings of this study also pave the way for future research into machine learning algorithms.]]>
Copyrights © 2025
