Published Paper Details:

This study endeavors to create a reliable anomaly detection system for heart disease using the Bisecting Min-Max DBSCAN algorithm. Given the global impact of heart disease on mortality rates, timely detection is crucial for effective treatment. Conventional methods often struggle to discern subtle patterns within complex heart health data. By harnessing the Bisecting Min-Max DBSCAN algorithm, which integrates the strengths of DBSCAN with adaptability, the study addresses this challenge. Data preprocessing involves comprehensive cleaning, integration, transformation, and reduction to enhance model performance. The model employs bisecting K-means clustering followed by DBSCAN to pinpoint abnormal patterns and outliers. Encouraging results exhibit high precision, recall, F-measure, and accuracy, showcasing the algorithm's effectiveness in anomaly detection. Interpretations suggest that this method can facilitate early diagnosis and intervention, thereby improving patient outcomes in cardiovascular health. This research underscores the importance of advanced anomaly detection techniques in healthcare and lays the groundwork for further refinement and expansion of such methodologies for heart disease diagnosis and beyond.