-) Diabetes Prediction Model using Machine Learning
📌 Overview
This project is a Diabetes Prediction System built using Support Vector Machine (SVM) to analyze patient health metrics such as glucose levels, BMI, and insulin levels to determine diabetes risk. Machine learning in healthcare has immense potential, and this model is a step toward AI-driven diagnostics for early detection and better decision-making.
🚀 Features
✅ Data Preprocessing: Handled missing values and standardized data using Pandas for better performance. ✅ Model Training: Utilized Support Vector Classifier (SVC) for classification. ✅ Accuracy: Achieved 78.66% on training data and 77.27% on test data. ✅ Real-time Predictions: The model takes new patient data and predicts the likelihood of diabetes.
🛠️ Technologies Used
- Python
- Pandas & NumPy (Data Preprocessing)
- Scikit-Learn (Machine Learning Model)
- Matplotlib & Seaborn (Data Visualization)
📊 Dataset
The dataset used is the Pima Indians Diabetes Dataset from Kaggle. It contains diagnostic measurements from patients and has the following key features: -> Glucose Level -> BMI (Body Mass Index) -> Insulin Level -> Blood Pressure -> Age -> Diabetes Pedigree Function -> Outcome (0 - No Diabetes, 1 - Diabetes)
📈 Model Performance (Dataset Accuracy)
-) Training - 78.66%
-) Testing - 77.27%
🚀 Future Enhancements
🔹 Try different algorithms like Random Forest, XGBoost, or Neural Networks to improve accuracy. 🔹 Enhance feature engineering to identify the most relevant health indicators. 🔹 Convert the model into an API using Flask, FastAPI, or Streamlit for easy access. 🔹 Integrate with a mobile application to allow users to input data and get instant diabetes risk analysis.
💡 Contributing
-> Contributions are welcome! Feel free to fork the repository and submit pull requests.
📜 License
-> This project is licensed under the MIT License.
📧 Connect with Me
-> If you have any suggestions or feedback, feel free to reach out! 😊
LinkedIn - https://www.linkedin.com/in/sakshamsaxena108