1. What is Net Sensitivity?

Definition: Net Sensitivity is a weighted measure of a model's ability to correctly identify positive cases, accounting for an importance factor.

Purpose: It helps evaluate classification models in machine learning and statistics, especially when different cases have varying importance.

2. How Does the Calculator Work?

The calculator uses the formula:

Where:

• \( TP \) — True positives (correctly identified positive cases)
• \( FN \) — False negatives (missed positive cases)
• \( Weight \) — Importance factor for the positive class

Explanation: First calculates standard sensitivity (recall), then applies a weight to account for the relative importance of detecting positives.

3. Importance of Net Sensitivity

Details: Provides a more nuanced performance metric than standard sensitivity when different correct identifications have varying importance.

4. Using the Calculator

Tips: Enter the count of true positives, false negatives, and the weight factor (default 1.0). TP + FN must be > 0.

5. Frequently Asked Questions (FAQ)

Q1: When should I use net sensitivity instead of regular sensitivity?
A: Use when some positive cases are more important to identify correctly than others (e.g., medical diagnosis of severe vs mild cases).

Q2: What does a weight of 1.0 mean?
A: A weight of 1.0 makes net sensitivity equal to standard sensitivity (no weighting applied).

Q3: What's a good net sensitivity value?
A: Values closer to the weight factor are better, with 1.0 being perfect sensitivity (if weight=1).

Q4: Can net sensitivity be greater than 1?
A: Yes, if your weight factor is greater than 1 (though this is uncommon in practice).

Q5: How is this different from F1 score?
A: F1 combines precision and recall, while net sensitivity focuses only on recall (sensitivity) with case importance weighting.