Dr-Cardio-Care

• 

  Out put and Probality

• 

  inputs

• 

  Home page

• 

  Ai Guidance

Inspiration

Heart disease is the leading cause of death worldwide, yet millions don’t have access to affordable and early screening tools. We wanted to create something that is easy to use, powered by AI, and accessible anywhere helping people take preventive action before it’s too late.

What it does

Dr. CardioCare predicts the probability of heart disease using patient health parameters such as age, blood pressure, cholesterol, and more. It provides real-time predictions with accuracy above 90%. Offers personalized lifestyle guidance (diet, exercise, habits) through Google Gemini Generative AI. Runs on the cloud (Streamlit app) so anyone can access it instantly with a link. Saves patient records for future reference.

How we built it

Machine Learning: Random Forest Classifier trained on heart disease dataset. Generative AI: Integrated Google Gemini for lifestyle recommendations. Frontend & Deployment: Streamlit app hosted on Streamlit Cloud. Data Handling: Pandas + CSV for storing patient records.

Challenges we ran into

Data Preprocessing: Ensuring the dataset was clean and balanced. Integration: Combining predictive ML with Generative AI smoothly. Cloud Deployment: Handling dependencies and environment setup on Streamlit Cloud. UX Design: Making the interface simple for non-technical users.

Accomplishments that we're proud of

Successfully deployed a fully working AI + ML + Cloud solution. Achieved 90%+ accuracy with our Random Forest model. Built a healthcare tool that is both useful and scalable. Combined predictive AI with generative AI guidance for a complete user experience.

What we learned

How to deploy ML models on the cloud using Streamlit. Best practices for combining traditional ML with LLMs for enhanced functionality. The importance of explainability and user trust in healthcare AI. Working with real datasets and tuning ML models for performance.

What's next for Dr-Cardio-Care

Add explainability features (feature importance, SHAP values). Generate a downloadable PDF health report for patients. Integrate with wearable devices (IoT) for real-time monitoring. Expand beyond heart disease to include diabetes, hypertension, and stroke prediction. Deploy on a scalable cloud backend (AWS/Azure) for wider adoption.

Built With

• csv
• google-gemini-api
• pandas
• python
• scikit-learn