Sensitivity vs Specificity Calculator

Calculator Form

True Positives

False Negatives

True Negatives

False Positives

Expected Prevalence (%)

Confidence Level

Target Sensitivity (%)

Target Specificity (%)

False Negative Cost Weight

False Positive Cost Weight

Decimal Places

Reset

Example Data Table

Scenario	True Positives	False Negatives	True Negatives	False Positives	Main Reading
Screening test	92	8	170	30	High sensitivity, lower specificity
Confirmatory test	78	22	194	6	High specificity, lower sensitivity
Balanced test	85	15	180	20	Balanced performance

Formula Used

Sensitivity = TP / (TP + FN)

Specificity = TN / (TN + FP)

Positive Predictive Value = TP / (TP + FP)

Negative Predictive Value = TN / (TN + FN)

Accuracy = (TP + TN) / (TP + TN + FP + FN)

False Positive Rate = FP / (FP + TN)

False Negative Rate = FN / (FN + TP)

Positive Likelihood Ratio = Sensitivity / (1 − Specificity)

Negative Likelihood Ratio = (1 − Sensitivity) / Specificity

Youden Index = Sensitivity + Specificity − 1

Balanced Accuracy = (Sensitivity + Specificity) / 2

F1 Score = 2TP / (2TP + FP + FN)

MCC = (TP × TN − FP × FN) / √((TP + FP)(TP + FN)(TN + FP)(TN + FN))

Prevalence Adjusted PPV = Se × P / [Se × P + (1 − Sp) × (1 − P)]

Prevalence Adjusted NPV = Sp × (1 − P) / [(1 − Se) × P + Sp × (1 − P)]

Confidence intervals use the Wilson score method for binomial rates.

How to Use This Calculator

Enter true positives, false negatives, true negatives, and false positives.
Add expected prevalence when you want predictive values for another population.
Select a confidence level for sensitivity and specificity intervals.
Set target sensitivity and specificity values for quick review.
Add error cost weights when one mistake is more serious.
Press Calculate to show the result below the header.
Use CSV or PDF export for reporting.

Why Sensitivity and Specificity Matter

Sensitivity and specificity describe two sides of a diagnostic test. Sensitivity measures how well the test finds people who truly have the condition. Specificity measures how well the test clears people who truly do not have it. A strong review needs both values. One value alone can hide risk.

Reading the Confusion Matrix

The calculator starts with four counts. True positives are sick cases marked positive. False negatives are sick cases missed by the test. True negatives are healthy cases marked negative. False positives are healthy cases flagged by the test. These four cells create the full performance picture. They also support many secondary metrics.

Advanced Diagnostic View

High sensitivity is useful for screening. It reduces missed cases. High specificity is useful for confirmation. It reduces false alarms. The best balance depends on the cost of each mistake. Missing a serious disease may be worse than sending extra people for follow-up. In other settings, a false alarm may waste resources or cause anxiety.

Predictive Values and Prevalence

Positive predictive value tells how often a positive result is truly positive. Negative predictive value tells how often a negative result is truly negative. These values change when prevalence changes. A rare condition can produce many false positive alerts, even when specificity is high. A common condition can reduce the reassurance from a negative result.

Using the Results

Use this tool when auditing a test, comparing methods, or preparing a report. Enter clean counts from the same sample. Keep the case definition fixed. Do not mix time periods unless that is planned. Review confidence intervals before making a claim. Wide intervals show weak evidence. Larger samples give steadier rates.

Better Decisions

No calculator can decide policy alone. It helps organize evidence. Pair the numbers with clinical judgment, study design, and population context. Check the threshold used by the test. Changing a threshold can raise sensitivity while lowering specificity. The final choice should match the real decision and its risks.

Data Quality Tips

Small data errors can shift every metric. Check duplicate rows. Confirm labels before entry. Separate unknown results from negative results. Record exclusions. Keep raw counts available, so reviewers can reproduce the same calculation later without confusion.

FAQs

What is sensitivity?

Sensitivity is the share of real positive cases that the test correctly finds. It answers how often the test detects the condition.

What is specificity?

Specificity is the share of real negative cases that the test correctly clears. It answers how often the test avoids false alarms.

Is sensitivity more important than specificity?

It depends on the decision. Screening usually favors sensitivity because missed cases matter. Confirmation usually favors specificity because false positives matter.

Why do predictive values change with prevalence?

Predictive values depend on how common the condition is. The same test can have different PPV and NPV in different populations.

What is a false positive?

A false positive is a positive test result for someone who does not truly have the condition.

What is a false negative?

A false negative is a negative test result for someone who truly has the condition. It is often important in safety reviews.

What is Youden index?

Youden index combines sensitivity and specificity into one value. A higher value usually means stronger separation between positive and negative cases.

Can I export the result?

Yes. After calculation, use the CSV or PDF buttons to save the current result table for reporting or review.