Medisen
GitHubProject Overview
Medisen is an AI-powered web application designed to assist users in identifying potential health conditions based on self-reported symptoms. Leveraging machine learning, the platform predicts the top 5 most likely diseases and displays the relevant symptoms associated with each, helping users better understand their condition before seeking professional advice.
The model was trained using three algorithms—K-Nearest Neighbors, Decision Tree, and Random Forest—with Random Forest selected as the final model due to its superior accuracy and robustness in classification.
⚠️ Disclaimer: Medisen is intended for informational and educational purposes only and does not replace professional medical diagnosis or treatment.
Key Features
- 🧠 Top 5 Disease Predictions: Accurately predicts the five most probable diseases based on input symptoms.
- 📋 Symptom Association: Displays key matching symptoms for each predicted disease to improve clarity and user trust.
- 🧪 Trained on Multiple ML Algorithms: Uses Random Forest Classifier for optimal accuracy (87%), outperforming KNN and Decision Tree.
- 💬 Responsive UI: Designed for smooth user experience across both desktop and mobile devices.
- ✅ User Safety Disclaimer: Clearly communicates the non-medical nature of the tool.
Tech Stack
ReactCSSAxiosFlaskPython 3.8+PandasScikit-learnRandom Forest ClassifierFlask-CORS
Snapshots
