Citation

Kilaskar M, Saindane N, Ansari N, Doshi D, Kulkarni M. SN Comput. Sci. 2022; 3(2).

Copyright

(Copyright © 2022, Holtzbrinck Springer Nature Publishing Group)

DOI

10.1007/s42979-021-00967-0

PMID

unavailable

Abstract

Today, depression is one of the critical mental health problems faced by humans of all ages and gender. In this era of increasing technology, it causes a life of less physical work, continuous pressure on one's life, which creates a risk of intellectual disturbance. The work culture, peer pressure, stressful life, emotional imbalance, family disturbances, and social life are resulting in depression. Depression may also sometimes lead to a heart attack. Depression causes adverse effects and becomes a serious medical problem in how individuals feel and act in everyday life. This psychological state causes feelings of sadness, anxiety, loss of interest in things and jobs, and could barely result in suicide. In this paper, the analysis of different Machine Learning Algorithms has been done and compared them by selecting various parameters and then showing which algorithm is more accurate for predicting depression. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2021.

Language: en

Keywords

Depression; Logistic regression; Machine learning; Random forest; SVM; XGBoost