Health Sense

• 

  Disease Prediction

• 

  Diabetes Prediction

• 

  Lung Cancer Prediction

• 

  Heart Disease Prediction

Inspiration

Millions of people suffer from chronic diseases like diabetes, heart disease, and lung cancer often diagnosed too late. Early prediction can save lives, but access to screening and personalized insights remains limited, especially in developing regions.

What it does

Health Sense bridges the healthcare gap by offering an AI-powered disease prediction platform that delivers fast, reliable, and accessible health risk assessments for multiple conditions. Users simply enter their basic health metrics such as age, glucose level, blood pressure, or lifestyle habits and the system predicts the likelihood of diseases using advanced machine learning models

Key Features

1.Disease Prediction Dashboard: A unified and interactive dashboard where users can select the disease they want to check and instantly get predictions. 2.Diabetes Prediction: Predicts diabetes risk using parameters like glucose levels, BMI, insulin levels, and age. Trained on medical datasets to provide accurate early warnings. 3.Heart Disease Prediction: Utilises cardiovascular data, including blood pressure, cholesterol levels, chest pain type, and heart rate, to assess the risk of heart disease. 4.Lung Cancer Prediction: Estimates the probability of lung cancer based on age, smoking history, shortness of breath, and other risk indicators.

How we built it

We developed Health Sense using Python (Streamlit) for the front-end interface and integrated machine learning models (XGBoost) for disease prediction. Each prediction model (Diabetes, Heart Disease, Lung Cancer) was trained on trusted open-source medical datasets, pre-processed for bias reduction and balanced accuracy. The UI ensures a clean, responsive experience, allowing users to interact easily with the predictive models.

Challenges we ran into

• Finding quality medical datasets with balanced features for training.
• Handling missing values and standardising diverse health parameters.
• Optimising ML models to ensure accuracy across diseases.
• Deploying the entire app with a unified, user-friendly interface under time constraints.

Accomplishments that we're proud of

• Empowered communities with a free and accessible AI health tool that supports early disease detection and awareness.
• Unified multiple disease predictions (diabetes, heart disease, and lung cancer) into one easy-to-use platform.
• Bridged the healthcare gap for individuals without access to regular medical checkups through data-driven insights.
• Delivered measurable impact by demonstrating how AI can transform preventive healthcare for communities worldwide.
• Promoted the concept of accessible preventive healthcare through technology.

What we learned

• How to turn an idea into a working AI health solution within a short timeline, balancing innovation and practicality.
• The importance of rapid collaboration combining data science, design, and development to build an impactful healthcare tool.
• How small UI and UX choices can significantly improve user engagement and make AI predictions more trustworthy and understandable.
• That real impact happens when technology meets empathy building not just for performance, but for communities who need it most.
• How spark creativity under pressure, pushing us to integrate multiple models and deploy a full product end-to-end.

What's next for Health Sense

• Expanding to more diseases such as Kidney Disease, Liver Disorders, and Alzheimer’s Prediction.
• Integrating wearable device data (Fitbit, Apple Health, etc.) for continuous monitoring.
• Adding a chat-based health assistant powered by AI for preventive guidance.
• Partnering with healthcare institutions for clinical validation and real-world deployment.

Built With

• machine-learning
• matplotlib
• numpy
• pandas
• plotly
• python
• scikit-learn
• seaborn
• streamlit
• streamlitcloud
• xgboost