Presentation Type
Poster
Student
Yes
Track
Health Care Application
Abstract
Non-communicable diseases (NCDs), such as diabetes, are major global health concerns influenced by various health parameters and lifestyle choices. Traditional methods struggle to efficiently predict and manage these conditions due to the complexity and diversity of medical data. There is a need to leverage machine learning algorithms and modern computational tools to accurately predict diabetes, improve diagnosis, and provide actionable insights for better healthcare outcomes. In this project we study the application of machine learning methods for predicting NCDs such as diabetes. Moreover, we leverage hyperparameter tuning techniques for model development and SHapley Additive exPlanation (SHAP) for results interpretations and also develop a web interface for the people for their real-time health analysis. Our experimental results show reasonable performance with the highest accuracy of 76% for diabetes prediction and provide reasonable explanations for the responsible factor related to the results.
Start Date
2-7-2025 1:00 PM
End Date
2-7-2025 2:30 PM
Included in
Computer and Systems Architecture Commons, Other Computer Engineering Commons, Telemedicine Commons
Machine Learning and SHAP Interpretability for Chronic Disease Understanding
Volstorff A
Non-communicable diseases (NCDs), such as diabetes, are major global health concerns influenced by various health parameters and lifestyle choices. Traditional methods struggle to efficiently predict and manage these conditions due to the complexity and diversity of medical data. There is a need to leverage machine learning algorithms and modern computational tools to accurately predict diabetes, improve diagnosis, and provide actionable insights for better healthcare outcomes. In this project we study the application of machine learning methods for predicting NCDs such as diabetes. Moreover, we leverage hyperparameter tuning techniques for model development and SHapley Additive exPlanation (SHAP) for results interpretations and also develop a web interface for the people for their real-time health analysis. Our experimental results show reasonable performance with the highest accuracy of 76% for diabetes prediction and provide reasonable explanations for the responsible factor related to the results.