User Rating 0.0 ★★★★★

Total Usage 0 times

Category Medicine & Tests

Contingency Matrix (2×2)

Enter the raw counts for your population sample.

Disease (Present)

Disease (Absent)

Test (Positive)

TP (True Pos)

FP (False Pos)

Test (Negative)

FN (False Neg)

TN (True Neg)

Total Population (N): 0 Prevalence: 0.00%

Diagnostic Metrics

            Sensitivity
            ?
          
--
True Positive Rate

            Specificity
            ?
          
--
True Negative Rate

PPV (Precision) ?

Positive Predictive Value

NPV ?

Negative Predictive Value

Accuracy

(TP + TN) / Total

F1 Score

Harmonic Mean

LR+ ?

LR- ?

Youden's J

False Disc. Rate

Is this tool helpful?

Your feedback helps us improve.

★ ★ ★ ★ ★

About

This Sensitivity and Specificity Calculator is a professional-grade biostatistical tool designed to evaluate the performance of binary classification tests. Whether analyzing a medical diagnostic test (e.g., Rapid Antigen, MRI) or a machine learning classification model, the validity of the results hinges on understanding the trade-offs between True Positives and False Negatives.

Accuracy alone is often a misleading metric, especially in datasets with class imbalance (low prevalence). This tool decomposes performance into granular metrics: Sensitivity (the ability to detect the condition), Specificity (the ability to exclude it), and Likelihood Ratios, which provide prevalence-independent measures of diagnostic utility. Correctly interpreting these values is critical for clinical decision-making, ensuring that patients are neither over-diagnosed (False Positives) nor missed (False Negatives).

Formulas

Sensitivity (True Positive Rate)

Sn = TPTP + FN

Measures the proportion of actual positives that are correctly identified. High sensitivity rules OUT disease (SnNOut).

Specificity (True Negative Rate)

Sp = TNTN + FP

Measures the proportion of actual negatives that are correctly identified. High specificity rules IN disease (SpPIn).

Positive Predictive Value (PPV)

PPV = TPTP + FP

Negative Predictive Value (NPV)

NPV = TNTN + FN

Likelihood Ratio Positive (LR+)

LR+ = Sensitivity1 − Specificity

Reference Data

Diagnostic Test	Condition	Sensitivity (Est.)	Specificity (Est.)
RT-PCR (Nasopharyngeal)	COVID-19	85% - 95%	> 99%
Rapid Antigen Test	COVID-19	60% - 80%	> 99%
Mammography	Breast Cancer	87%	89%
Pap Smear	Cervical Cancer	55% - 80%	90% - 98%
PSA (4.0 ng/mL cutoff)	Prostate Cancer	21%	91%
MRI	ACL Tear	90% - 98%	95% - 99%
D-Dimer	DVT (Thrombosis)	95% - 98%	40% - 60%
Troponin I	Myocardial Infarction	90% - 99%	85% - 95%

Frequently Asked Questions

Screening tests aim to catch every possible case of a disease, meaning they need to minimize False Negatives. A test with high Sensitivity (e.g., 99%) ensures that very few sick people are missed. However, high sensitivity often comes at the cost of lower specificity, leading to more False Positives which are then ruled out by confirmatory tests.

This is a critical concept. Even with a highly accurate test, if the disease prevalence is very low (rare), the Positive Predictive Value (PPV) will decrease drastically, meaning a positive result is more likely to be a False Positive. Conversely, in a high-prevalence setting, the PPV increases. This calculator determines PPV based on the sample prevalence provided in the matrix.

Accuracy is the ratio of correct predictions to the total count. It can be misleading if classes are imbalanced (e.g., 95% of people are healthy). The F1 Score is the harmonic mean of Precision (PPV) and Sensitivity, providing a better metric for the test's performance on the positive class specifically.

Likelihood Ratios are powerful because they are independent of prevalence. An LR+ > 10 indicates that a positive test result is excellent at confirming the disease. An LR- < 0.1 indicates that a negative test result is excellent at ruling out the disease.