https://github.com/jatharva04/ml-parkinsons-predictor
This web application predicts whether a patient is affected by Parkinson’s Disease and estimates its severity using machine learning. It combines an SVM classifier for diagnosis with Random Forest models for severity analysis based on UPDRS scores.
https://github.com/jatharva04/ml-parkinsons-predictor
bootstrap5 flask machine-learning
Last synced: 12 months ago
JSON representation
This web application predicts whether a patient is affected by Parkinson’s Disease and estimates its severity using machine learning. It combines an SVM classifier for diagnosis with Random Forest models for severity analysis based on UPDRS scores.
- Host: GitHub
- URL: https://github.com/jatharva04/ml-parkinsons-predictor
- Owner: jatharva04
- Created: 2025-06-20T05:24:58.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-06-20T06:46:38.000Z (about 1 year ago)
- Last Synced: 2025-06-20T07:24:00.774Z (about 1 year ago)
- Topics: bootstrap5, flask, machine-learning
- Language: Jupyter Notebook
- Homepage:
- Size: 7.2 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🧠 Parkinson's Disease Prediction Web Application
A machine learning-powered web application to predict Parkinson’s Disease and estimate its severity using patient vocal features. This project was developed as part of an academic ML project with additional improvements for better usability and performance.
---
## 📌 About the Project
This project uses **three machine learning models**:
1️⃣ **SVM Classifier** → Predicts if the patient has Parkinson’s (Yes / No) using vocal features.
2️⃣ **Random Forest Regressor** → Predicts the **Total UPDRS** score (Unified Parkinson's Disease Rating Scale) for severity estimation.
3️⃣ **Random Forest Classifier** → Predicts **Severity Levels** (Mild / Moderate / Severe) based on the predicted UPDRS score.
Severity levels are calculated using the following range:
- 🟢 **Mild**: 0 - 20
- 🟡 **Moderate**: 21 - 40
- 🔴 **Severe**: 41 - 60
---
## 🌐 Features
- 🎯 Predict Parkinson’s Disease (Yes / No)
- 📊 Predict UPDRS score (severity score)
- 🚦 Display of severity level (Mild, Moderate, Severe)
- 🖥️ Clean & modern Bootstrap-based UI with interactive elements
- 🌀 Loading spinner for prediction feedback
---
## 📋 Technologies Used
- Python (Flask)
- HTML, CSS (Bootstrap 5)
- Machine Learning (Scikit-learn)
---
## 🤖 Models Training Notebook
You can find the model training code and approach in the provided Colab notebook inside this repository.
---
## 📂 Datasets Used
- [Parkinson’s Disease Dataset (for Diagnosis)](https://www.kaggle.com/datasets/vikasukani/parkinsons-disease-data-set)
- [Parkinson’s Telemonitoring Dataset (for Severity & UPDRS Score)](https://archive.ics.uci.edu/dataset/174/parkinsons)
---
## 📑 Citation
M. Little. "Parkinsons," UCI Machine Learning Repository, 2007. [Online]. Available: https://doi.org/10.24432/C59C74.
---
## 📎 License
This project is for academic and educational purposes.
---