SymptoDiagnose

Inspiration

We started "Symptodiagnose" because we wanted to make it easier for people to understand their symptoms and get better help with diagnosing illnesses. Sometimes, figuring out what’s wrong can be hard, so we thought technology could make it simpler and more accurate.

Why it is Creative

"Symptodiagnose" stands out because it integrates advanced machine learning algorithms with a user-friendly interface. Unlike other symptom checkers, our project uses a hybrid approach that combines data-driven insights with expert medical knowledge, offering a more accurate diagnostic tool.

How we built it

We looked at other tools, we drew up plans for how the app would look and work. We built the app step by step, adding features like symptom input and diagnosis tools. We used technology to make sure it worked well by testing it with different data.

Team and Roles

We were a team of two, where Yameen worked on the app's front end, while Hassaan worked on the back end.

Technical Implementations of the project

For both the backend and the front end, we used python, we made use of a dataset found on kaggle.com and used a machine learning algorithm to train the model. We specifically used Support Vector Machine since it was giving us the highest accuracy. We then deployed our app using streamlit.

Built With

• kaggle
• python
• streamlit