https://github.com/reputed-artist/liver-disease-prediction-using-ensemble-machine-learning-method

Master degree project for liver disease prediction. i have improved the code reaching its accuracy to 98-99% from 70%.
https://github.com/reputed-artist/liver-disease-prediction-using-ensemble-machine-learning-method

jypyternotebook lgbmclassifier machine machine-learning machine-learning-algorithms machinelearning machinelearning-python machinelearningprojects model-training-and-evaluation numpy pandas prediction python randomforestclassifier svm-classifier xgboost-classifier

Last synced: 3 months ago
JSON representation

Master degree project for liver disease prediction. i have improved the code reaching its accuracy to 98-99% from 70%.

• Host: GitHub
• URL: https://github.com/reputed-artist/liver-disease-prediction-using-ensemble-machine-learning-method
• Owner: reputed-artist
• Created: 2025-04-14T11:10:10.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2025-04-14T11:39:22.000Z (6 months ago)
• Last Synced: 2025-04-15T04:15:56.330Z (6 months ago)
• Topics: jypyternotebook, lgbmclassifier, machine, machine-learning, machine-learning-algorithms, machinelearning, machinelearning-python, machinelearningprojects, model-training-and-evaluation, numpy, pandas, prediction, python, randomforestclassifier, svm-classifier, xgboost-classifier
• Language: Jupyter Notebook
• Homepage:
• Size: 354 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Liver Disease Prediction using Ensemble Machine Learning Techniques

This repository contains the source code for my **M.Tech project**, focused on improving the prediction accuracy of liver disease using **ensemble machine learning algorithms**.

## 📌 Project Overview

Liver disease is a major cause of mortality worldwide. Early diagnosis can significantly improve patient outcomes. This project aims to develop a predictive model that uses patient data to accurately detect liver disease using an **ensemble of machine learning models**.

## 🎯 Objectives

- To analyze and preprocess liver disease datasets.

- To apply various machine learning models for classification.

- To implement **ensemble techniques** to improve predictive accuracy.

- To evaluate model performance using various metrics.

- Implement code in both scaled and unscaled data to test results.

## 🛠️ Technologies Used

- **Python 3**

- **Jupyter Notebook / Google Colab**

- **Pandas, NumPy** – for data handling

- **Matplotlib, Seaborn** – for visualization

- **Scikit-learn** – for machine learning models

- **XGBoost / Random Forest / LGBM (Light Gradient Boosting Machine Classifier)** – for ensemble modeling

## 🧠 Machine Learning Techniques

The following models were used and compared:

- Logistic Regression

- Support Vector Machine (SVM)

- Random Forest

- K-Nearest Neighbors (KNN)

### 🔁 Ensemble Models Implemented

- **Bagging** – Random Forest

- **Boosting** – XGBoost, LGBM

  

## 📊 Results [vary for scaled and unscaled data]

| Model             | Accuracy (%) |

|------------------|--------------|

| Logistic Regression | 74.3%     |

| SVM                 | 79.1%     |

| RF                  | 92.1%     |

| LGBM                | 71.1%     |

| XGBOOST             | **99.9%** |

> **Voting Classifier** with soft voting gave the best performance, showing that ensemble methods significantly improve the prediction accuracy over individual models.

## 📁 Dataset

- Dataset used: [Indian Liver Patient Dataset (ILPD)](https://www.kaggle.com/datasets/uciml/indian-liver-patient-records)

- Size: 583 records

- Features include: Age, Gender, Total Bilirubin, Alkphos Alkaline Phosphotase, etc.

## 🚀 How to Run

1. Clone this repository:

   ```bash

   git clone https://github.com/reputed-artist/Liver-Disease-Prediction-using-Ensemble-Machine-Learning-Method.git