INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
A Comparative Study of Machine Learning Techniques for Health Prediction
Authors Name:
Rosemary Varghese
, Anila S , Shyama R
Unique Id:
IJSDR2205062
Published In:
Volume 7 Issue 5, May-2022
Abstract:
Personal well-being refers to both physical as well as mental fitness. In the current scenario of expeditious commercial growth and pandemics, the human race is also challenged by immense psychological pressures. This paper presents the prediction of the most pertinent psychological issues identified by the World Health Organization – Anxiety,Stress, and Depression. Machine Learning algorithms are used for the prediction of the same. The data was previously collected from people in various economic,cultural, and social situations through the Depression,Anxiety, and Stress Scale Questionnaire (DASS21). Three supervised learning algorithms were applied and corresponding confusion matrices were calculated. The accuracies of each model were compared and were found that the model with the best accuracy is K-Nearest-Neighbor.In addition, analysis of the results divulged that the models were sensitive to negative results.
Keywords:
Decision Tree (DT); Depression, Anxiety, Stress (DASS- 21); K Naïve Bayes(NB);Machine Learning
Cite Article:
"A Comparative Study of Machine Learning Techniques for Health Prediction", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.7, Issue 5, page no.325 - 330, May-2022, Available :http://www.ijsdr.org/papers/IJSDR2205062.pdf
Downloads:
000337074
Publication Details:
Published Paper ID: IJSDR2205062
Registration ID:200334
Published In: Volume 7 Issue 5, May-2022
DOI (Digital Object Identifier):
Page No: 325 - 330
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn