DIAT | Devpost

calorie chart generated based on user input to chat, useful for diabete patients to track their diet.
Main page(chat page) write feed to the chat and then receive dietary instructions or diabetes suggestions
log in page
registration page, users can fill out more info in the profile page
set goals page(set a timer and a goal to reach) For example, take some med after 5 hours
profile page(records patient's basic info), including Diabetes type, age, dietary restrictions, etc
editing profile page
One example of chat response, users can get the calories chart after the chat generates the answer by pressing the "chart" on the left

Inspiration

The idea for this project stemmed from one of our teammates whose relative has been managing diabetes for years. Witnessing the challenges of maintaining a personalized diet while living with diabetes, they were inspired to create a tool that could offer individualized support. Our goal is to simplify dietary management for diabetes patients, empowering them with a personalized solution that helps them take control of their health.

What it does

Our web app offers a highly personalized experience for users. By interacting with our AI assistant, users receive tailored dietary suggestions that match their individual health needs, preferences, and goals. Users can also log their meals, and the app generates a personalized calorie graph that provides real-time insights into their food intake. This allows users to track their diet and better manage their diabetes, receiving continuous feedback on how their choices align with their personal health goals.

How we built it

We used modern web technologies such as React for the frontend and node.js frameworks for the backend. The AI chat assistant is powered by a natural language processing model that personalizes diet suggestions based on user queries and health data. For the calorie tracking feature, we integrated a robust food database and a graphing library to visually represent each user's unique dietary consumption.

Challenges we ran into

One of our main challenges was ensuring the AI assistant could provide truly personalized and relevant dietary suggestions for individuals with diabetes. Fine-tuning the AI to consider user preferences, health status, and specific diabetes-related concerns took significant effort. Another challenge was optimizing the real-time calorie tracking system to reflect the unique food habits of each user while maintaining an intuitive and seamless user experience.

Accomplishments that we're proud of

We are proud of creating an AI assistant that adapts to each user's unique dietary needs and health goals. By offering personalized diet recommendations, we provide users with valuable, actionable insights they can use in their daily lives. The calorie graph feature also works seamlessly, giving users an individualized look at their eating habits in a way that's easy to understand and apply.

What we learned

Throughout the project, we learned the importance of personalization in health technology, especially when it comes to managing chronic conditions like diabetes. Building a tool that offers tailored support helped us understand how to refine our AI and improve user engagement. We also gained valuable experience in integrating AI with web applications and learned how to optimize data visualization to suit individual users.

What's next for DIAT

We plan to further personalize our app by incorporating additional health data, such as blood sugar levels and activity tracking, to make the AI’s recommendations even more relevant. We also aim to develop version in mobile app. Our goal is to continue refining the app to provide even deeper insights, such as macro- and micronutrient breakdowns tailored to individual needs.