https://github.com/kasraskari/diabetics-prediction
Predicting whether the person is having diabetics or not
https://github.com/kasraskari/diabetics-prediction
diabetes-prediction jupyter-notebook k-nearest-neighbors knn machine-learning python
Last synced: 11 days ago
JSON representation
Predicting whether the person is having diabetics or not
- Host: GitHub
- URL: https://github.com/kasraskari/diabetics-prediction
- Owner: KasrAskari
- Created: 2024-05-28T18:15:18.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-12-02T18:38:58.000Z (11 months ago)
- Last Synced: 2025-01-05T03:10:04.380Z (9 months ago)
- Topics: diabetes-prediction, jupyter-notebook, k-nearest-neighbors, knn, machine-learning, python
- Language: Jupyter Notebook
- Homepage:
- Size: 46.9 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Diabetics Prediction
## Overview
This project aims to predict the likelihood of diabetes in individuals using machine learning models trained on medical datasets. By analyzing key health metrics such as glucose levels, blood pressure, and BMI, the system provides an accurate risk assessment to support early diagnosis and treatment planning.
---
## Features
- Diabetes risk prediction using supervised machine learning models.
- Data preprocessing and feature engineering for improved model performance.
- Visualization of correlations between health metrics and diabetes risk.
- Interactive interface or scripts for prediction based on user input.
---
## Project Structure
```
Diabetics-Prediction/
├── data/ # Dataset used for training and testing
├── notebooks/ # Jupyter notebooks for data analysis and model training
├── models/ # Saved machine learning models
├── scripts/ # Python scripts for predictions
├── README.md # Project documentation
└── LICENSE # License information
```
---
## Dataset
The dataset used in this project is sourced from [Kaggle - diabetes2]( https://www.kaggle.com/datasets/kandij/diabetes-dataset) (or another dataset source). It contains medical data such as:
- Glucose levels
- Blood pressure
- BMI
- Insulin levels
- Family history of diabetes
---
## Algorithms Used
1. **Logistic Regression**
2. **Random Forest**
3. **Support Vector Machines (SVM)**
4. **K-Nearest Neighbors (KNN)**
---
## Results
The best-performing model achieved an accuracy of approximately **85-90%** on the test dataset, demonstrating its reliability in diabetes prediction.