Hello and welcome to this article where we will be taking a look at sensitivity and specificity. We’ll take a look at what they are, how they are calculated and two related measurements – positive and negative predictive values. Tests are important tools that can help us identify the presence or absence of disease. But. they are not always perfect.


Sensitivity and specificity are measures that can be used to determine how good a test is at correctly identifying the presence or absence of disease. Let’s take a closer look.

Let’s use a table of the outcome of the test and disease status to learn about some of the terms that are used. There are people with a disease and those without the disease When we do a test on someone, it can be either positive or negative. 

If the test is positive, it should mean that the person has the disease. This is called a true positive It correctly identifies a person with the disease Similarly, if a test is negative, it should mean that a person does not have the disease. This is called a true negative. It correctly identifies a  person without the disease, however, because tests are not always perfect.

A test can be positive even though the person does not have the disease. This is called a false positive. This is not ideal because it could lead to further testing or treatment that is not necessary,  negative psychological impacts and may come with an economic cost or added risk.

On the other hand, a test can sometimes be negative even though the person has the disease. This is called a false negative. Again, this is not ideal because the test has not picked up the person despite them having the disease.

This may lead to delays in diagnosing the disease and therefore delays in treatment which could lead to a negative health outcome. An incorrectly negative test may also lead to a false sense of security and the continuation of risky behaviours that may worsen the disease or even place others at risk, in the case of a communicable disease. Missing a diagnosis may also have legal consequences.

Using these terms, we can calculate the sensitivity and specificity of the test. These are indicators of how good a test is and guides us on how to determine the appropriateness of a test and interpret its outcome.

Sensitivity is the proportion of people with the disease who test positive for it. A high sensitivity means that the proportion of true positives is high,  and the proportion of false negatives is low. Specificity on the other hand is the proportion of people without the disease who test negative for it. 

High specificity means that the proportion of true negatives is high, and the proportion of false positives is low. Let’s work through an example. Let’s say we have a group of 600 people. Let’s assume that 100 people have a disease and 500 people don’t. First, we’ll focus on the 100  people who have the disease.

Let’s say that we do a test on people with the disease. Now if the test was perfect, we would have 100 positive tests. However, let’s assume that the test is positive in only 90 people – in other words,  there are 90 true positive cases. 

This leaves us with 10 people with the disease who have negative test results. These are false negatives. We know that the sensitivity of the test is a proportion of people with the disease who test positive for it. 

Therefore, in this example, the sensitivity of the test is 0.9 or 90%. Now let’s do the test on the  500 people without the disease. Ideally, we will have 500 negative results. But let’s assume that the test was negative in only 400 people. These are true negatives. This would then mean that in 100 people without the disease, the test was positive. 

These are false positives. We know that the specificity of the test is the proportion of people without the disease who test negative for it So, in this example, the specificity of the test is 0.8 or 80%And that’s how sensitivity and specificity are calculated.

Tests with high sensitivity are good for screening tests because the proportion of false negatives is low. On the other hand, tests with high specificity are good for confirmatory rests because the proportion of false positives is low. 

The perfect test will have a sensitivity of 100% and a specificity of 100%. The closer a test’s sensitivity and specificity are to 100%,  the better the test is in confirming or excluding the disease. Finally, let’s have a quick look at two related measurements - Positive  Predictive Value and Negative Predictive Value. It uses the same information but looks at it from a testing point of view. 

Let’s use the same values that we used in our previous example. 190 people test positive and 410 people who test negative The Positive Predictive Value is the proportion of people with a positive test who actually have the disease.

In this example,  the positive predictive value is 47.4 %. The negative predictive value is the proportion of people with a negative test who do not have the disease. 

In this case, the negative predictive value is 97.6%Positive and Negative Predictive Values depend on the prevalence of disease,  or in other words, how much disease there is in the population. 

In general, an increase in disease prevalence is associated with an increase in positive predictive value and a decrease in the negative predictive value and that’s an overview of sensitivity and specificity and a quick look at positive and negative predictive values.