H5n1 Disease Stage Prediction with Data Visualization Using Python

The timely preliminary assessment of infectious diseases such as the Avian Influenza A (H5N1) virus is critical for effective public health management and patient intervention. This paper details the design and implementation of a desktop-based Expert System for the prediction of H5N1 disease stages based on patient symptom data. The system is developed using Python with a Tkinter Graphical User Interface (GUI) and utilizes a MySQL database for robust data management. In contrast to modern machine learning models that learn patterns from data, this system operates on a predefined knowledge base consisting of a set of deterministic, symptom-based rules derived from established clinical indicators. The application provides a user-friendly workflow, allowing a user to import patient data from a CSV file, which is then processed by a rule-based inference engine. This engine classifies each case into predefined categories, such as "Virus is At 1st Stage," "Virus is At Beigning Stage," or "No Virus." The system architecture, data flow, and the core rule-based logic are described in detail. Furthermore, the system integrates data visualization capabilities, dynamically generating bar charts and pie charts to provide an analytical overview of the predicted outcomes across different patient demographics, such as age groups. This work demonstrates the development of a practical and rapidly deployable decision-support tool capable of automating preliminary clinical screening based on codified expert knowledge. Keywords — Expert System, Rule-Based System, H5N1, Disease Prediction, Clinical Decision Support, Tkinter, Data Visualization, MySQL.