model-liver-disease-prediction Open Source Liver Disease Prediction Model - Predict Liver Disease Risk Based on Physiological Indicators

Model Liver Disease Prediction

Developed by gianlab

This is a liver disease prediction model based on ExtraTreesClassifier, used to predict whether a patient has liver disease based on the patient's physiological indicators.

Molecular Model Open Source License:Apache-2.0 #Liver disease prediction #Medical classification #Biochemical index analysis

Downloads 0

Release Time : 3/7/2024

Model Overview

This model is trained on a dataset from a Kaggle competition. It uses the patient's age, gender, and multiple blood test indicators as inputs to predict whether the patient has liver disease. The accuracy of the model is 83.65%.

Model Features

High accuracy

The model achieves an accuracy and F1 score of 83.65% on the test set

Interpretability

The model structure based on decision trees provides a certain degree of feature importance interpretation

Lightweight

The model is stored in pickle format, with low resource requirements for deployment and use

Model Capabilities

Medical prediction

Tabular data classification

Binary classification task

Use Cases

Medical and health

Liver disease screening

Rapidly screen potential liver disease patients through the patient's physiological indicators

Accuracy: 83.65%, Recall: 83.62%

Health risk assessment

Assess the patient's liver disease risk to assist clinical decision - making

🚀 Sklearn Model for Tabular Classification

This model is designed for tabular classification tasks, specifically predicting whether a patient is a liver patient or not. It provides a practical solution for medical data analysis based on specific predictors.

🚀 Quick Start

To use the AI model, run the following code on Google Colab: Google Colab Link

✨ Features

Predictive Capability: The model can classify patients into 'Non liver patient' and 'Liver patient' categories.
Based on Kaggle Notebook: It is created following the instructions in a Kaggle notebook, ensuring a certain level of reliability and replicability.

📦 Installation

No specific installation steps are provided in the original document.

📚 Documentation

Model description

This model was created following the instructions in the following Kaggle notebook: Kaggle Notebook

The possible classified predictions are: 'Non liver patient', 'Liver patient'

The predictors are: age, gender, total_bilirubin, alkaline_phosphotase, alamine_aminotransferase, albumin_and_globulin_ratio

Intended uses & limitations

This model follows the limitations of the Apache 2.0 license.

Hyperparameters

Click to expand

Hyperparameter	Value
bootstrap	False
ccp_alpha	0.0
class_weight
criterion	gini
max_depth
max_features	sqrt
max_leaf_nodes
max_samples
min_impurity_decrease	0.0
min_samples_leaf	1
min_samples_split	2
min_weight_fraction_leaf	0.0
n_estimators	100
n_jobs
oob_score	False
random_state	123
verbose	0
warm_start	False

Model Plot

ExtraTreesClassifier(random_state=123)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

Evaluation Results

Metric	Value
accuracy	0.836538
f1 score	0.836538

Model description/Evaluation Results/Classification report

index	precision	recall	f1-score	support
Liver patient	0.814159	0.87619	0.844037	105
Non liver patient	0.863158	0.796117	0.828283	103
macro avg	0.838659	0.836153	0.83616	208
weighted avg	0.838423	0.836538	0.836236	208

📄 License

This model is licensed under the Apache 2.0 license.

Property	Details
Model Type	sklearn ExtraTreesClassifier
Training Data	Not provided

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご