Research Article
Epidemiological analysis and Machine Learning Prediction of Top 5 Respiratory Viruses
@INPROCEEDINGS{10.4108/eai.28-4-2025.2357823, author={K. Srivatsan and Praveen Abhishek and Varun Rajesh and S. Kamaleswari}, title={Epidemiological analysis and Machine Learning Prediction of Top 5 Respiratory Viruses}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part I}, publisher={EAI}, proceedings_a={ICITSM PART I}, year={2025}, month={10}, keywords={respiratory infections epidemiology virus infections influenza a and b respiratory syncytial virus (rsv) human rhinovirus sars-cov-2 machine learning predictive models public health surveillance outbreak prediction seasonal trends outbreak prediction lstm random forest disease forecasting}, doi={10.4108/eai.28-4-2025.2357823} }- K. Srivatsan
Praveen Abhishek
Varun Rajesh
S. Kamaleswari
Year: 2025
Epidemiological analysis and Machine Learning Prediction of Top 5 Respiratory Viruses
ICITSM PART I
EAI
DOI: 10.4108/eai.28-4-2025.2357823
Abstract
Respiratory viruses are one of the biggest threats to public health, as they are linked with huge morbidity and mortality burdens across different populations. This study suggests a combined epidemiological and machine learning approach to predicting the trends of the five most common respiratory viruses: Influenza A, Influenza B, Respiratory Syncytial Virus (RSV), Human Rhinovirus, and SARS-CoV-2. For this end, epidemiological investigation of historical surveillance data from various areas were conducted to identify trends in seasonal patterns, age- related incidence, and transmission patterns over time. In parallel, various machine learning models, including Random Forest, Support Vector Machines, and Long Short-Term Memory (LSTM) networks, were applied to predict the infection rate and outbreak likelihood. The models were compared with respect to accuracy, F1-score, and root mean square error (RMSE) to gauge the management of ensemble methods. This review emphasizes equilibrium found in marrying traditional epidemiological methods with contemporary data-driven approaches in the maximization of planning and response to outbreaks of viral respiratory infections.
