Abstract:

New technology advancements are reshaping the healthcare system's future. The identification of elements that cause depression may lead to novel research and therapies. Because depression is becoming a major public health problem across the globe. Using machine learning methods, this paper proposes a comprehensive methodological framework for processing and exploring heterogeneous data in order to better understand the relationship between quality of life and depression. As a result, the experimental investigation is separated into two sections. The first section describes a data consolidation procedure. The data connection is constructed, and the Secure Hash Algorithm idea is used to uniquely identify each data relation. Hashing is used to find and index the data's real objects. The second section offered a model that used both unsupervised and supervised machine learning approaches. The consolidation technique aided in the creation and confirmation of the research hypothesis. The Self organising map generated 08 cluster solutions, and the classification problems were drawn from the clustered data to verify the performance of the posterior probability multiclass Support Vector Machine. The assumptions about the significance of sampling resulted in elements that cause despair. The suggested model was used to enhance classification performance, yielding a classification accuracy of 91.16%.

Description:

Depression, healthcare, quality of life, secure hash algorithm SHA-1, supervised learning, unsupervised learning.