PulseWise | Devpost

Home Page
AI Health Assistant
Information Questions
Heart Disease Prediction and Tips
Weather Warning

Inspiration

Our project was inspired by the alarming statistics surrounding heart disease worldwide. With millions of lives at stake each year, especially in the U.S., we were motivated to create a solution that could help individuals better understand and manage their cardiovascular health.

What it does

With early prognosis of the disease, we hope to reduce the complications of patients at risk. Our project is an interactive platform designed to empower users with providing their information and receive feedback on their condition and tailored prevention tips to provide users with a roadmap to wellness. It incorporates an interactive bot for real time assistance, tailored by prevention tips and warnings to provide users with a roadmap to wellness.

How we built it

Our project was built using a combination of Reflex (Python), examination of machine learning models for risk prediction, JavaScript, and Tailwind CSS. One notable aspect of our development approach was the integration of the Gemini AI platform to implement the chatbot functionality. This allowed us advance the interactivity and user experience of our solution. We took advantage of the collaboration features on PyCharm to effectively work through the development process and ensure effective teamwork.

Challenges we ran into

The most significant challenge we encountered was setting up Reflex, as we were not accustomed to coding both the frontend and backend in pure Python. This presented various obstacles, including configuring the correct ports and resolving compatibility issues with our existing codebase. Additionally, processing the machine learning models required meticulous attention to detail, with numerous rounds of trial and error to ensure each factor was accurately accounted for and converted to numerical values. In spite of getting the model to work, Reflex classes made it difficult to connect to one another.

Accomplishments that we're proud of

Despite these challenges, our team is particularly proud of successfully implementing Reflex for the first time in our project. Overcoming this hurdle not only expanded our technical skill set but also demonstrated our team's adaptability and willingness to explore innovative solutions.

What we learned

Throughout the development process, we delved into various technologies and experimented with different machine learning models to determine the most accurate approach for our dataset. This hands-on experience provided us with valuable insights into the strengths and limitations of each model, as well as the importance of data preprocessing and feature engineering in improving accuracy.

What's next for the Heart Project

Moving forward, we plan to refine and optimize the performance and improve accuracy by experimenting with other machine learning models such as Random Forest. We also plan to expand the capabilities of our chatbot by integrating more advanced conversational AI techniques and improving its ability to provide personalized recommendations. Furthermore, we intend to explore opportunities for scalability and integration with other healthcare platforms to broaden the reach and impact of our solution.