Inspiration
My grandparents live in a rural area four hours away from my parents. My parents were worried about their health because of their old age and he wanted a way to monitor their health and also help them improve their own health. This inspired us to come up with HealthWise AI Advisor, which provides personalized recommendations to improve lifestyle and prevent health complications while also tracking health data for loved ones to monitor.
What it does
The HealthWise AI Advisor improves the user's quality of life and health by acting as a daily health advisor. Using health data and the user's inputted concerns, the Advisor makes recommendations and sends notifications about how to resolve the user's health concerns and prevent health complications. The health data can also be shared with loved ones for remote monitoring.
How we built it
We utilized OpenAI's GPT 4o model on top of a website that we built using the NextJS framework and stored data in a database from supabase. The OpenAI model uses a custom prompt we developed to ensure useful and accurate recommendations.
Challenges we ran into
We wanted to extract the user's concerns about their health from their conversations with the AI Advisor. After a lot of brainstorming, we realized we could implement a system that extracts the user's concerns about their health from their messages with the AI chatbot and updates the Advisor's personalized recommendations accordingly. This was challenging for us, and we implemented a way that whenever the user asks a question we make another API call that runs in the backend extracts any user concerns within the message, and saves it to the database to be used as a reference in future conversations.
Accomplishments that we're proud of
We managed to do multiple AI calls to achieve a seamless user experience. We built a fully working MVP product within 24 hours that allows people to improve their health. We are also proud of the fact that our AI Advisor makes personalized recommendations based on user health data as opposed to general recommendations, improving the quality of life of the user.
What we learned
We learned how to use Twilio, which is a service that allows you to handle calls programmatically. Alongside the coding aspect of the project, this project allowed us to uncover a new side of Health Management which is often written off; making small daily efforts towards a healthy life. From this, we not only learned preventative measures that could be suggested for users of HealthWise but practices applicable to our own lives as well.
What's next for HealthWise
We plan to establish a proper user base in the United States, targetting everyday individuals, before branching out internationally as well as working to lessen the burden on overworked patient hospitals. Additionally, we plan on adding new features for the user such as synced health data from different monitoring tools and a voice assistant option for the HealthWise AI Advisor.
Built With
- nextjs
- openai
- supabase
Log in or sign up for Devpost to join the conversation.