GlucoLogic

Inspiration

Diabetes is a very common medical condition due to our rapidly changing lifestyle today. Even in this day and age, a patient would have to wait to consult a doctor to understand the possibility of the condition with the symptoms they have been facing. So, we thought can we make this waiting process shorter and easily accessible? Inspired by the people around us, in our families and in general society, we came up with the idea of GlucoLogic.

What it does

GlucoLogic is designed to be an intelligent diagnostic system that assesses a patient's risk of diabetes, determines the specific type of diabetes (Type 1 or Type 2), and provides recommendations based on symptoms, test results, and risk factors. It evaluates parameters like glucose levels, age, lifestyle factors, and complications while offering clear explanations for its conclusions.

How we built it

We wrote the foundation for GlucoLogic using Prolog, taking advantage of its logical reasoning capabilities and rule-based structure. The code defines rules for identifying diabetes, counting symptoms and risk factors, and providing recommendations based on patient data. Our modular design ensured that different functionalities could be developed and expanded independently.

Challenges we ran into

Complexity of Medical Rules: Translating detailed medical guidelines into a working codebase required time and precision.

Time Constraints: With limited time, completing a fully functional and tested version of GlucoLogic proved to be a challenge.

Accomplishments that we're proud of

Gaining a deeper understanding of diabetes diagnostics and translating that into computational logic.

What we learned

Prolog Basics and Beyond: This project strengthened our understanding of rule-based programming and logical reasoning. Medical Guidelines in Tech: Translating complex medical rules into computational logic is both challenging and rewarding.

What's next for GlucoLogic

Writing a substantial portion of the diagnostic logic that evaluates symptoms, test results, and risk factors.

While we have written a substantial portion of the code, it remains incomplete, so we have decided not to submit it as a final product. However, we plan to:

Complete the code and thoroughly test the system for accuracy and reliability Add machine learning to improve accuracy Develop a user-friendly interface to make the system accessible to non-technical users through REACT based on our Figma prototype Expand the scope of GlucoLogic to address other chronic conditions like hypertension or cardiovascular diseases

Built With

• figma
• react
• s(casp)