Analysis of Influenza Datasets for Disease Prediction using AI and ML

Influenza remains a significant global health concern, necessitating accurate predictive models for disease surveillance and management. This study analyzes influenza datasets collected from the CDC and WHO to predict disease trends using artificial intelligence (AI) and machine learning (ML) techniques. Data preprocessing was conducted to refine and structure the datasets for effective analysis. Various machine learning models, including Linear Regression, K-nearest neighbors (KNN), Support Vector Machine (SVM), and Random Forest, were tested to evaluate their predictive capabilities. Descriptive statistics, ANOVA, ARIMA modeling, and box plot analysis were performed to gain insights into the dataset's characteristics. Model performance was assessed using R² mean values and accuracy metrics. The SVM model demonstrated the highest predictive accuracy and was identified as the most effective model for forecasting influenza trends. Future disease predictions for the next four years were generated using the ML approach, providing valuable insights for public health planning. This study highlights the potential of AI-driven analytics in disease prediction and prevention.