AI-Based Diabetes Risk Assessment Tool

• 

  AI-Based Diabetes Risk Assessment Tool

Inspiration

Diabetes is one of the most common chronic diseases worldwide, and early detection can help people take preventive steps before complications arise. We wanted to create a simple yet powerful tool that not only predicts the risk of diabetes but also helps patients understand their condition and take care of their health with actionable insights.

What it does

Our AI-Based Diabetes Risk Assessment Tool has three main sections:

Prediction – Uses a Support Vector Machine (SVM) model to predict the likelihood of diabetes. Visualization – Provides data visualizations, such as glucose level trends, to help patients better understand their health. About Us – Shares information about our mission and the team behind the project.

Additionally, if the prediction indicates risk, the app suggests steps for better self-care and encourages patients to seek medical advice.

How we built it

Model: Support Vector Machine (SVM) trained on a diabetes dataset. Framework: Streamlit for front-end deployment and interactive UI. Data Visualization: Python libraries to plot and display glucose level trends. Deployment: Streamlit Cloud to make the app accessible online.

Challenges we ran into

Optimizing the SVM model for accurate predictions. Ensuring a user-friendly interface that works well for both technical and non-technical users. Deploying the project seamlessly on Streamlit Cloud within the limited hackathon timeline.

Accomplishments that we're proud of

Successfully building and deploying a functional AI app within the hackathon duration. Integrating prediction, visualization, and actionable advice into a single platform. Creating a tool that can make a positive impact in healthcare awareness.

What we learned

Hands-on experience with machine learning models (SVM) for healthcare prediction. How to deploy Streamlit applications for real-world accessibility. The importance of combining technical accuracy with a user-friendly design.

What's next for AI-Based Diabetes Risk Assessment Tool

Improve model accuracy by experimenting with other algorithms and larger datasets. Add features like personalized diet & lifestyle recommendations. Expand the app to predict risks of other chronic diseases beyond diabetes. Collaborate with healthcare professionals for real-world testing and feedback.

Built With

• github
• matplotlib
• numpy
• pandas
• python
• scikit-learn
• seaborn
• streamlit
• svm