Inspiration
We were inspired by how difficult it can be for people to interpret their symptoms without medical knowledge. Many individuals turn to unreliable internet searches that often lead to confusion or unnecessary panic. We wanted to create a simple, intelligent tool that demonstrates how computer science can be used to model medical reasoning and provide structured, data-driven insights into potential conditions.
What it does
Simptify is a web-based symptom analysis tool that allows users to select symptoms they are experiencing and receive a ranked list of possible medical conditions. The app uses a scoring algorithm to compare user inputs with symptom to condition mappings and calculates confidence levels based on overlap. It also explains why each condition was suggested by highlighting matched symptoms, making the output more transparent and understandable.
How we built it
We built Simptify using Python and the Streamlit framework to create an interactive web interface. The backend logic is made by a structured dictionary that maps symptoms to conditions. We used set-based operations to calculate symptom overlap and used a scoring system to rank conditions by likelihood. The interface allows users to select symptoms dynamically, and the results are displayed with clear visual feedback, including confidence levels and explanations.
Challenges we ran into
One of the main challenges was designing a scoring system that felt accurate rather than random. We had to balance simplicity with realism so that the results were both understandable and logically sound. Another challenge was structuring the symptom database in a way that avoided redundancy while still covering a wide range of conditions. Additionally, ensuring the UI remained clean while handling different inputs.
Accomplishments that we're proud of
We are proud of creating a system that simulates real-world reasoning using simple algorithms. The app is fully interactive, easy to use, and provides explainable outputs rather than just raw predictions. We also successfully integrated computer science concepts like set operations, ranking algorithms, and user interface design into a meaningful healthcare-related application.
What we learned
Through this project, we learned how models can be applied to real-world problems like healthcare decision support. We gained experience in building interactive web applications using Streamlit, designing efficient data structures, and implementing algorithms for pattern matching and ranking. We also learned the importance of explaining when dealing with sensitive topics like health.
What's next for Simptify
In the future, we plan to improve Simptify by incorporating more advanced techniques such as machine learning models to generate more accurate predictions. We also want to expand the symptom database, add severity and duration inputs, and implement user accounts for personalized tracking. Ultimately, we aim to transform Simptify into a more intelligent health analysis platform that can provide deeper insights and better support users.
Log in or sign up for Devpost to join the conversation.