https://github.com/sunilvarma-l/liver-disease-prediction

This project focuses on predicting liver disease using machine learning techniques. The dataset includes 615 records with 13 features, such as blood and urine analysis measurements. The target variable is categorical, with five classes: No Disease, Suspect Disease, Hepatitis C, Fibrosis, and Cirrhosis.
https://github.com/sunilvarma-l/liver-disease-prediction

machine-learning numpy pandas python scikit-learn statistics streamlit tensorflow

Last synced: about 1 month ago
JSON representation

This project focuses on predicting liver disease using machine learning techniques. The dataset includes 615 records with 13 features, such as blood and urine analysis measurements. The target variable is categorical, with five classes: No Disease, Suspect Disease, Hepatitis C, Fibrosis, and Cirrhosis.

• Host: GitHub
• URL: https://github.com/sunilvarma-l/liver-disease-prediction
• Owner: Sunilvarma-l
• Created: 2024-12-12T16:01:41.000Z (about 1 month ago)
• Default Branch: main
• Last Pushed: 2024-12-12T16:14:36.000Z (about 1 month ago)
• Last Synced: 2024-12-12T17:23:44.056Z (about 1 month ago)
• Topics: machine-learning, numpy, pandas, python, scikit-learn, statistics, streamlit, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 1.74 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Liver Disease Classification Project

## Overview

This project aims to classify liver disease into one of the following categories:

No Disease

Suspect Disease

Hepatitis C

Fibrosis

Cirrhosis

The project utilizes patient data, including blood and urine analysis measurements, to predict liver disease. The model is built and evaluated using machine learning techniques, and the results are deployed using a Streamlit application.

## Dataset Details

The dataset contains:

Instances (Rows): 615

Features (Columns): 13

## Key Features:

age: Patient age (0–100 years).

sex: Patient gender (male or female).

albumin: Protein levels in the blood (34–54 g/L).

alkaline_phosphatase: Enzyme levels to check liver damage (40–129 U/L).

alanine_aminotransferase (ALT): Liver enzyme levels (7–55 U/L).

aspartate_aminotransferase (AST): Another liver enzyme level (8–48 U/L).

bilirubin: Substance formed during red blood cell breakdown (1–12 mg/L).

cholinesterase: Enzyme levels affecting the nervous system (8–18 U/L).

cholesterol: Fat-like substance levels (<5.2 mmol/L).

creatinina: Creatinine levels to evaluate kidney function.

gamma_glutamyl_transferase (GGT): Enzyme indicating liver damage (0–30–50 IU/L).

protein: Protein levels in urine (<80 mg).

category (diagnose): Target variable (No Disease, Suspect Disease, etc.).

# Key Machine Learning Techniques Used

## Supervised Learning Algorithms:

Logistic Regression

Decision Trees

Random Forest

Support Vector Machines (SVM)

k-Nearest Neighbors (KNN)

Gradient Boosting (XGBoost, LightGBM)

## Unsupervised Learning Algorithms:

Clustering

Principal Component Analysis (PCA)

## Other Techniques:

Neural Networks

Time Series Analysis

Text Mining

## Deployment

The model is deployed as a web application using Streamlit, making it easy to input data and view predictions interactively.