AdversaCare

• 

  Home Page

• 

  Sign Up

• 

  Doctor Dashboard View

• 

  Data Analysis Pie Graph

Inspiration

One of our team members has a family member who underwent extensive medical treatments for epilepsy, including multiple brain surgeries. Navigating complex medication regimens and the risk of drug interactions sparked our motivation to build a tool that could reduce the likelihood of misdiagnosis and prevent adverse drug reactions. We wanted to create something that empowers clinicians with better data and insights when making life-saving decisions.

What it does

AdversaCare is a web platform that helps doctors identify potentially dangerous drug-drug interactions by querying the openFDA Adverse Events API. It collects key patient information via a short intake form and uses that data to surface similar real-world reported reactions. The results are summarized through clear, interactive visualizations, helping doctors make informed, evidence-backed prescribing decisions.

How we built it

We built the frontend using React for a responsive and intuitive user experience. On the backend, we used Flask (Python) to handle API queries and form submissions. For data analysis and visualization, we integrated various Python libraries such as Pandas, Plotly, and Requests to process, format, and display the openFDA data in a meaningful way.

Challenges we ran into

One of the main challenges was designing a robust backend architecture that could handle and securely store both patient and doctor data while maintaining clear separation and access control. Structuring the database schemas and managing interactions between frontend inputs and backend processes required several iterations. We also had to navigate the complexities of querying and interpreting FDA’s adverse event reports, which are not always standardized.

Accomplishments that we're proud of

We successfully built a full-stack web app that integrates with the openFDA API, performs real-time data queries, and transforms the results into interactive, insightful visualizations. We’re especially proud that the platform supports both patients and clinicians, and that we’ve created a workflow that makes this complex data actionable in real-world clinical settings.

What we learned

Backend design and system architecture are far more complex and critical than we initially expected. We learned how important it is to plan data flow, schema relationships, and API handling early on. We also gained hands-on experience with real-world medical data and how to responsibly and meaningfully extract insights from it.

What's next for AdversaCare

Our next step is to enhance our querying system with curated, condition-specific searches and then apply supervised machine learning models to assess the risk level of certain drug combinations. We also aim to build out a secure login system for doctors, expand intake options, and eventually integrate with existing EHR systems to bring AdversaCare closer to real-world deployment in clinical environments.

Built With

• flask
• github
• matplotlib
• numpy
• openfda
• pandas
• python
• react
• tailwindcss