Authors:
K. Anitha, S. Silvia Priscila, S. Belina V. J. Sara, Gnaneswari Gnanaguru, M. Sakthivanitha

Addresses:
Department of Mathematics, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Chennai, Tamil Nadu, India. Department of Computer Science, Bharath Institute of Higher Education and Research, Chennai, Tamil Nadu, India. Department of Computer Applications, Faculty of Science and Humanities, SRM Institute of Science and Technology, Kattankulathur, Chennai, Tamil Nadu, India. Department of Computer Applications, CMR Institute of Technology, Bengaluru, Karnataka, India. Department of Information Technology, Vels Institute of Science Technology and Advance Studies, Chennai, Tamil Nadu, India.

Abstract:

The logistic regression analysis in the present study explores the relationship between COVID-19 test outcomes and some of the principal clinical indicators. The main point was made upon SARI and RdRp confirmatory testing. It also considered patients across five discrete categories, age-stratified according to WHO criteria, into four groups. The methodology used a two-stage analytical approach: first, Chi-Square tests to establish associations between sociodemographic variables and the COVID-19 test results, followed by logistic regression to develop predictive models. Statistical analysis revealed distinct patterns in both SARI and RdRp patient groups. In SARI patients, gender was not significantly related to COVID-19 test results. However, RdRp analysis revealed high correlations with age, and some demographic factors are statistically insignificant. The obtained results were a basis for creating the equations of the predictive models through logistic regression. This work is within the research scope on COVID-19 testing dynamics and characteristics of patients. This study identifies key indicators of a positive test result, helping doctors assess risk and manage patients. This research may aid clinical decision-making and resource allocation in COVID-19 testing facilities with predictive models.

Keywords: Logistic Regression; Predictive Modelling; Univariate and Bivariate Model; Real-Time Tracking; Viral Spread; QML Algorithms-E-QSVM; DL-Based Models; Real-Time Tracking.

Received on: 20/06/2024, Revised on: 05/09/2024, Accepted on: 28/10/2024, Published on: 03/12/2024

DOI: 10.69888/FTSHSL.2024.000276

FMDB Transactions on Sustainable Health Science Letters, 2024 Vol. 2 No. 4, Pages: 221-230

• Views : 144
• Downloads : 10

Download PDF