Abstract
In many fields, data-driven decision making has become essential due to machine learning (ML), which provides insights that improve productivity and quality of life. A basic machine learning approach called clustering helps find comparable data points. Clustering plays a critical role in the identification of patient subgroups and the customisation of treatment in the context of tuberculosis (TB) research. While prior studies have recognized its utility, a comprehensive comparative analysis of multiple clustering methods applied to TB data is lacking. Using TB data, this study thoroughly assesses and contrasts four well-known machine learning clustering algorithms: spectral clustering, DBSCAN, hierarchical clustering, and k-means. To evaluate the quality of a cluster, quantitative measures such as the silhouette score, Davies–Bouldin index, and Calinski–Harabasz index are utilised. The results provide quantitative insights that enhance comprehension of clustering and guide future research.

This publication has 18 references indexed in Scilit: