WellnessWise is an intelligent, web-based medical decision support platform that leverages machine learning to assist users in identifying potential health conditions based on symptom analysis and demographic factors. The system provides structured disease insights, treatment guidance, comorbidity awareness, and personalized lifestyle recommendations.
⚠️ Disclaimer: WellnessWise is intended strictly for educational and informational purposes. It does not provide medical diagnosis or replace professional healthcare advice, consultation, or treatment. Always consult a qualified healthcare professional for medical concerns.
- Natural language symptom input with machine learning classification
- TF-IDF vectorization for semantic symptom matching
- Multinomial Naive Bayes classifier for disease prediction
- Interpretable results with confidence scoring
- Demographic-aware predictions (age, gender, pregnancy status)
- Tailored disease recommendations based on user context
- Improved accuracy and relevance compared to generic symptom checkers
Each disease recommendation includes:
- Treatment protocols and medication guidance
- Comorbidity considerations and drug interactions
- Safety precautions and contraindications
- Educational summaries for patient awareness
- Disease-specific dietary recommendations
- Personalized exercise and wellness suggestions
- Preventive health measures
- Conditions grouped by medical system (respiratory, endocrine, cardiovascular, etc.)
- Easy browsing and exploration
- Structured medical knowledge repository
- User registration and authentication
- Session-based security
- SQLite backend with SQLAlchemy ORM
- Clean, modern interface optimized for desktop and mobile
- Intuitive user experience
- Real-time result visualization
- Python 3.8 or higher
- pip package manager
- Git
-
Clone the repository
git clone <repository-url> cd WellnessWise
-
Create a virtual environment (recommended)
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate
-
Install dependencies
pip install -r requirements.txt
Or manually install core packages:
pip install flask pandas scikit-learn numpy
-
Verify dataset Ensure
augmented_diseases_extended.csvexists in the root directory -
Run the application
python app.py
Open your browser and navigate to
http://localhost:5000
-
Register or Log In
- Create a new account or sign in with existing credentials
-
Input Symptoms
- Select symptoms from dropdown menus
- Provide demographic information (age, gender, pregnancy status)
-
View Results
- Review predicted diseases with match scores
- Examine comorbidities and precautions
- Access treatment and lifestyle guidance
Input:
- Symptoms: fever, cough, fatigue
- Age: 35
- Gender: Female
- Pregnancy Status: Not pregnant
Output:
- Top predictions: Influenza, Common Cold, COVID-19
- Match scores, treatment options, and lifestyle recommendations
| Component | Technology |
|---|---|
| Backend | Python, Flask |
| Machine Learning | Scikit-learn, Pandas, NumPy |
| NLP | TF-IDF Vectorization, Cosine Similarity |
| Algorithm | Multinomial Naive Bayes Classifier |
| Frontend | HTML5, CSS3, Jinja2 Templates |
| Database | SQLite, SQLAlchemy ORM |
| Dataset | augmented_diseases_extended.csv |
WellnessWise/
├── app.py # Flask application entry point
├── model.py # Machine learning model implementation
├── models.py # Database models (SQLAlchemy)
├── Models.ipynb # Jupyter notebook for model experimentation
├── augmented_diseases_extended.csv # Disease and symptom dataset
├── requirements.txt # Python dependencies
├── templates/ # HTML templates
│ ├── index.html
│ ├── login.html
│ ├── signup.html
│ ├── symptom_checker.html
│ └── results.html
├── static/ # Static assets (CSS, JavaScript, images)
│ └── style.css
├── Model Details/ # Model documentation and analysis
├── README.md # This file
└── LICENSE # License information
User Input → Normalization → TF-IDF Vectorization → Similarity Matching
Symptom Vectors → Naive Bayes Classifier → Disease Scores → Ranking
Demographics (Age/Gender/Pregnancy) → Context Filtering → Refined Results
Disease ID → Treatment Data → Comorbidities → Lifestyle Recommendations
The system uses an augmented, curated dataset containing:
- Diseases: Comprehensive disease profiles across medical specialties
- Symptoms: Associated symptoms with relevance weights
- Treatments: Evidence-based treatment protocols and medications
- Comorbidities: Drug interactions and disease correlations
- Lifestyle Data: Diet and exercise recommendations
- Why: Fast inference, interpretable results, suitable for multi-class disease classification
- Input: TF-IDF vectorized symptom features
- Output: Probability scores for each disease
- Training: Supervised learning on symptom-disease pairs
- TF-IDF Vectorization: Semantic similarity between user input and known symptoms
- Cosine Similarity: Measures closeness of symptom vectors
- Demographic Weighting: Adjusts predictions based on age, gender, and pregnancy status
- User enters symptoms via natural language or structured selection
- Symptoms are normalized and converted to TF-IDF vectors
- Machine learning model predicts probable diseases with confidence scores
- Demographic context refines predictions for increased relevance
- System retrieves comprehensive medical information for top results
- Educational summaries are presented alongside treatment guidance
- Educational Purpose Only: This system provides informational support, not medical diagnosis
- Not a Substitute for Professional Care: Always consult qualified healthcare providers
- Limited by Data: Predictions based on curated dataset; rare conditions may be underrepresented
- Demographic Bias: System trained on specific populations; results may vary across groups
- No Emergency Support: Do not use for acute medical emergencies
This project is proprietary software. For inquiries regarding contributions, modifications, or licensing, please contact the authors.
Mahipal Chauhan | Dhruv Jani
B.Tech Computer Science Engineering
Batch 2022–2026
© 2025 Dhruv Jani and Mahipal Chauhan. All rights reserved.
Unauthorized use, reproduction, modification, or distribution is strictly prohibited without explicit written permission from the authors.
For licensing inquiries, please contact the authors directly.
For bug reports, questions, or suggestions, please reach out to the authors.
Disclaimer: This system is for educational purposes only and should never replace professional medical consultation.