A Comparative Study of Clustering Algorithms in Mental Health Data Classification

In this research, we analyze the implementation of three different clustering algorithms to sort individuals over five common mental health conditions: Schizophrenia, Depression, Anxiety, Bipolar Disorder and Eating Disorders. The clustering methods evaluated include Spectral clustering, K-Means and Agglomerative Clustering. We carry out a detailed performance analysis to assess the effectiveness of each algorithm at recognizing patterns in the mental health dataset. The results derived from our research are for better comprehension of cluster methods with respect to the identification of mental health conditions and further serve the purpose of more accurate classifications and assisting in early detection. These results have got the capabilities of strengths and weaknesses of each algorithm in the classification of the selected mental health disorders, providing clarity to future research and real-time applications in the area of mental health.