Authors:
K. Anitha, M. Sakthivanitha, S. Manikandan, S. Belina V. J. Sara
Addresses:
Department of Mathematics, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Chennai, Tamil Nadu, India. Department of Information Technology, Vels Institute of Science Technology and Advance Studies, Chennai, Tamil Nadu, India. Department of Robotics and Automation, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India.Department of Computer Applications, Faculty of Science and Humanities, SRM Institute of Science and Technology, Kattankulathur, Chennai, Tamil Nadu, India.
This study examines the use of statistical analysis and predictive modeling in the understanding of risk factors related to COVID-19 by looking into multi-omics data using logistic regression, which is a statistical model based on the principles of machine learning and allows for the evaluation of numerous predictors and their interactions with other variables to predict the actual disease outcome. There were three methodology stages in the study major: testing based on chi-square for a preliminary check on association amongst variables, predictor selection based upon statistical significance, and, finally, logistic regression modeling to ascertain risks. Significant age-related patterns emerge in susceptibility towards COVID-19. Specifically, risk levels were significantly higher at 2.76, 95% CI: 1.94 – 3.94, odds ratio in the participants aged above 65 years as compared to the subjects aged below 14 years. The association was stronger in the gene analysis of omics data of orf1b. This study found a protective factor while analyzing orf1b omics data in 15-24-year-olds. This cohort had a low odds ratio of 0.53 (95% CI: 0.35–0.79) compared to the reference group with good statistical significance. Such inferences may help construct age-specific COVID-19 risk profiles and identify vulnerable populations using multi-omics data.
Keywords: Omics Data; Logistic Regression; Predictive Modelling; Diverse Genera of Viruses; Spike Proteins; Respiratory Symptoms; Infection Critical; High-Dimensional Omics; Global Health Systems; Biological Underpinning.
Received on: 22/03/2024, Revised on: 18/05/2024, Accepted on: 30/06/2024, Published on: 05/09/2024
AVE Trends in Intelligent Health Letters, 2024 Vol. 1 No. 3, Pages: 178-192