Patient Information
Enter your health metrics to assess diabetes risk using our advanced ensemble model.
Prediction Results
Ensemble Model
0.72
probability
Random Forest
0.68
probability
XGBoost
0.75
probability
Neural Network
0.71
probability
Feature Importance Analysis
SHAP waterfall plot will appear here after prediction
Most Influential Features
Recommendations
Model Performance Comparison
Our ensemble combines the strengths of three powerful machine learning models:
Random Forest
An ensemble of decision trees that reduces overfitting and provides robust predictions.
Accuracy:
84.2%
Precision:
82.5%
Recall:
85.7%
XGBoost
A gradient boosting framework optimized for speed and performance with regularization.
Accuracy:
86.1%
Precision:
84.3%
Recall:
87.9%
Neural Network
A deep learning model that captures complex non-linear relationships in the data.
Accuracy:
83.7%
Precision:
81.9%
Recall:
84.2%
Ensemble Performance
Our weighted ensemble achieves 88.3% accuracy by combining the predictions of all three models.
