Log Loss (Cross-Entropy) Calculator

Compute binary cross-entropy log loss = −(1/N)Σ[y·log(p) + (1−y)·log(1−p)] from predicted probabilities and true labels. Lower log loss indicates a better calibrated model

Each component has a specific meaning:

• Predicted probabilities — The predicted probabilities recorded for the patient or scenario being assessed.
• True labels — The true labels recorded for the patient or scenario being assessed.

Note: Interpret the log loss result against the clinical thresholds and context described above.

Enter the predicted probabilities, true labels for the patient or scenario you are assessing. Compute binary cross-entropy log loss = −(1/N)Σ[y·log(p) + (1−y)·log(1−p)] from predicted probabilities and true labels. Lower log loss indicates a better calibrated model. Use the log loss result to inform your clinical assessment.