Abstract
Advancements in artificial intelligence have enabled the use of Large Language Models (LLMs) for disease prediction by analyzing structured healthcare data. This study explores the application of LLMs in predicting diabetes based on patient information, including age, gender, hypertension, heart disease, smoking history, BMI, HbA1c levels, and blood glucose levels. By utilizing AI-driven prompts, the model assesses diabetes risk and provides insights beyond traditional statistical methods. The research evaluates the accuracy of LLM-generated predictions, compares them with conventional machine learning approaches, and examines challenges such as data privacy, model bias, and interpretability. The study aims to enhance early detection, support clinical decision-making, and optimize patient management through AI-driven analytics. Findings contribute to the integration of LLMs in healthcare, demonstrating their potential to improve chronic disease prediction and personalized care strategies.
Presenters
Bhumika ShahAssociate Professor, Data Analytics, Post University, Connecticut, United States
Details
Presentation Type
Paper Presentation in a Themed Session
Theme
KEYWORDS
Artificial intelligence, Data analytics, LLM, Healthcare analytics
