Comparison Analysis of Humans Getting Sick in Winter and Summer Seasons Using Machine Learning

Abstract

Seasonal changes significantly impact human health, with winter and summer posing distinct challenges. This paper examines seasonal disease trends using machine learning methods, analyzing health data containing variables such as temperature, humidity, air quality, and disease prevalence. The study implements algorithms like Random Forest, Support Vector Machine (SVM), and XG Boost, among others, to predict illness trends and explore environmental and physiological factors contributing to diseases such as respiratory infections in winter and dehydration-related conditions in summer. Notably, XG Boost outperformed other models with a predictive accuracy of 92%, demonstrating its robustness in capturing complex interactions. Feature importance analysis further highlighted temperature and humidity as key drivers of disease prevalence. The findings show that machine learning effectively models seasonal health patterns, offering actionable insights for public health interventions, including early warning systems for disease outbreaks and tailored health campaigns. These results underscore the potential of data-driven approaches to mitigate seasonal health risks and enhance healthcare planning.