Liver Disease Prediction

Model Performance Metrics

Model: LightGBM Classifier

Accuracy

74.0%

Overall prediction accuracy

Precision

76.53%

Positive prediction accuracy

Recall

90.36%

Ability to find all positive cases

F1 Score

82.87%

Balanced accuracy measure

Enter Patient Details or Try Example:

Liver Disease Examples:

No Liver Disease Examples:

Age:

Gender (0=Female, 1=Male):

Total Bilirubin:

Direct Bilirubin:

Alkaline Phosphotase:

Alamine Aminotransferase:

Aspartate Aminotransferase:

Total Protiens:

Albumin:

Albumin and Globulin Ratio:

Analyzing patient data...

Prediction

Confidence: 0%

Probabilities

Disease

Healthy

SHAP Explainability Analysis

Red: Higher feature value (pushes toward disease).

Blue: Lower feature value (pushes toward healthy).

The length of each bar indicates the strength of the contribution.

⚠️ Disclaimer This prediction is generated based on a machine learning model trained on the Indian Liver Patient dataset. It should not be considered as a substitute for professional medical advice, diagnosis, or treatment. Liver diseases are complex conditions requiring expert clinical assessment. Please consult with a qualified healthcare professional or hepatologist for accurate diagnosis and appropriate medical guidance. Always prioritize professional medical consultation over automated predictions.