JJEM: Special Edition 2 (December 2024)
JJEM: Special Edition 2 (December 2024)
2024-12-08
Student Mental Health Assessment via Machine Learning Techniques.
Srinidhi R K, Adarsh M J.
The consequences of anxiety, stress and other pressures of the modern world affect people on the international level. In a recent study, it was established that technology in health care was capable of identifying much more data concerning the human body than the conventional measurement methods. Due to the large data set in the healthcare industry, there is no better approach to passing through such data than using an ML algorithm. To be more precise, an innovative approach of artificial intelligence’s application in the sphere of mental health is to estimate the probability of particular diseases and to offer some recommendations for action. Huge and detailed this information is, and therefore machine learning has become one of the primary tools for healthcare analysis. issues and relationships in data that manual analysis often cannot discover are areas where the broad functions of ML prove useful. The pressure in the contemporary society, worry, and stress on a worldwide level. A similar study was published revealing that hi-tech in health care can obtain significantly rich and denser data about human physical form as those obtained by conventional measurement. Based on the data volume in health care, it is possible to identify that only machine learning (ML) algorithms are suitable for data processing. In detail, the use of artificial intelligence (AI) in mental health care has been more revolutionary since they determine the likelihood of such diseases and offer subsequent suggestions. The tremendous amount of data and its specificity and comprehensiveness require the use of machine learning algorithms, as they perfectly indicate problems and relationships in large datasets that cannot be identified by ordinary examination. Out of all the ML methods, the random forest, decision tree, and logistic regression affairs significantly for healthcare investigation improving the efficacy of estimates and suggestions in mental health.
Machine learning, random-forest, decision-tree, logistic regression