Skip to content

Repository files navigation

Silent Disease Early Detection Engine


Problem Statement

Modern lifestyles and sedentary habits lead to several “silent” health issues such as diabetes, hypertension, anemia, vitamin deficiencies, and early cardiovascular risks. People often remain unaware of these risks until severe complications arise. There is a lack of a unified system that monitors lifestyle factors, predicts early disease risks, and provides actionable health recommendations.


Maitri

Maitri — Your Health Companion That Warns Before Disease Begins


Team Name

Team NoobCoders


Deployed Link

Deployed Web Application: https://maitri-the-early-symptoms-detector.streamlit.app/


PPT Link

PPT Presentation


📊 How It Works

  1. Data Collection: Users provide health and lifestyle data.
  2. Feature Analysis: Data analyzed for correlations with diseases.
  3. Risk Prediction: ML models predict the probability of developing silent diseases.
  4. Alerts & Recommendations: Personalized preventive guidance is provided to the user.

🌟 Key Features

  • Early risk detection for multiple silent diseases
  • Machine-learning based probability scoring
  • Height & weight input with automatic BMI calculation
  • Simple sidebar-based health data entry
  • Clickable disease cards with detailed information
  • Causes, prevention tips & diet recommendations
  • Modern dark-mode health-tech UI
  • Fast and lightweight Streamlit application

🦠 Diseases Covered

  • Diabetes
  • Hypertension (High Blood Pressure)
  • Dyslipidemia (High Cholesterol)
  • Anemia
  • Vitamin D Deficiency
  • Early Cardiovascular Risk
  • Chronic Kidney Disease

🧾 Inputs Used

  • Age and Gender
  • Height (cm) and Weight (kg)
  • Sleep Hours
  • Screen Time
  • Stress Level
  • Physical Activity Level
  • Water Intake
  • Fatigue Level
  • Sun Exposure
  • Hydration Level
  • Diabetes Risk Score
  • Anemia Status

BMI is calculated internally using height and weight.


🛠 Tech Stack

  • Frontend: Streamlit
  • Backend: Python
  • Machine Learning: Scikit-learn
  • UI Styling: HTML & CSS
  • Data Handling: NumPy, Pickle

🚀 How It Works

  1. User enters health data via sidebar
  2. ML models calculate disease risk probabilities
  3. Diseases with ≥40% risk are highlighted
  4. User clicks disease cards to view:
    • Causes
    • Preventive tips
    • Recommended diet

▶ Running the App Locally

pip install streamlit numpy scikit-learn
streamlit run app.py

📂 Project Structure

├── app.py
├── diabetes_model.pkl
├── hypertension_model.pkl
├── dyslipidemia_model.pkl
├── anemia_model.pkl
├── vitaminD_model.pkl
├── cardio_model.pkl
├── kidney_model.pkl
└── README.html

Setup

streamlit run app.py

🎯 Use Cases

  • Early lifestyle disease awareness
  • Preventive healthcare prototypes
  • Public health screening demos

Screenshort

Screenshot 2026-01-04 132352 Screenshot 2026-01-04 132655

📈 Impact

Maitri empowers individuals to take control of their health by predicting risks before they manifest, helping reduce the prevalence of silent diseases and promoting a healthier lifestyle.


Made With Purpose 💜

Maitri means friend — a companion that warns early so health problems never become emergencies.


📬 Future Enhancements

  • PDF health reports
  • Multilingual support
  • Wearable device integration

Author
Shristi Kumari | Anu Kumari

⭐ Liked the concept? Support this project by giving the repository a star.

About

Repository for noobcoders - Vibe Coding Hackathon

Topics

Resources

Stars

3 stars

Watchers

0 watching

Forks

Releases

Packages

Used by

Contributors

Languages