Design Of An Interpretable Model For Disease Diagnosis Among University Students

In the healthcare domain, precise and prompt disease diagnosis is essential for effective treatment and better patient outcomes. With the advancements in artificial intelligence and machine learning, diagnostic systems have become increasingly important for augmenting medical decision-making. This undergraduate project aims to create an interpretable disease diagnostic system using a rule-based approach, focusing on six prevalent diseases among university students. To achieve this, the project follows a systematic methodology. It begins with an extensive literature review to identify the most common diseases relevant to university students. Next, a comprehensive dataset is gathered, incorporating pertinent medical features and diagnostic outcomes. When delivering diagnostic results, the system elucidates its decisions by referencing specific rules and highlighting the key features influencing the outcome. By employing a rule-based approach, natural language processing and incorporating OpenAI GPT3, the system holds promise for enhancing medical decision-making, facilitating early disease detection, and ultimately promoting the well-being of its target demographic.