NO! That's not true. That's impossible
Why so sensitive?
Never tell me the odds
I'm just a positive kinda person
Negative is good right?
100

The measure of the ability of a test to detect a condition

Sensitivity

100

The measure of the ability to determine that a disease is not present.

Specificity

100

The probability that a positive test result represents a true positive.

Positive predictive value

100

The probability that a Negative test result represents a true negative.

Negative predictive value

100

These 2 probabilities are affected by the prevalence of the condition being tested for.

Positive and negative predictive values

200

The decreased likelihood of something happening based on population likelihood.

Absolute risk reduction

200

The number of people who have a negative test and in fact have the condition.

False negative

200

Number of people you need to treat to cause 1 undesired outcome. 

Number needed to harm

200

The number of people who need to receive a treatment to prevent 1 undesired outcome.

Number needed to treat


May also see number needed to screen

200

The number of people who have a positive test and truly don't have the condition.

False positives

300

The decreased likelihood of something happening compared to the base likelihood of that thing happening.

Relative risk reduction

300

The number of people who have a positive test and truly have the condition.

True positives

300

These 2 innate measures of a test are not affect by disease prevalence.

Sensitivity and Specificty

300

The likelihood of something happening after an exposure relative to it happening without the exposure

Odds ratio

300

The number of people who have a negative test and truly don't have the condition.

True negatives

400

                     1                      

   absolute risk reduction

Number needed to treat

400

                     TN                     

 TN+FP

Specificity

400

Results of a clinical study show a relative risk reduction (RR 0.67) of 33% and an absolute risk reduction (AR = 0.8) of 20%. There are 1000 patient each in the treatment and control groups. To help determine the potential benefit of the treatment, it is necessary to identify the number needed to treat (NNT).

1/20% = 5

400

The negative predictive value of the following situation:

A home urine test is designed to detect a type of cancer. The gold standard for this cancer is a biopsy. The biopsy is more costly, invasive, and associated with lots of adverse side effects.

To test the effectiveness of the home urine test, 104 people took the test and then agreed to a biopsy. When the study was concluded, 77 people tested negative and 27 tested positive on the urine test. Biopsies were positive in 18 individuals, 8 of whom tested negative on the urine test.

90%

400

               TP(FN+TN)               

 FN(TP+FP)

Relative risk reduction

500

                     TP                    

  TP+FN

Sensitivity

500

                     TP/FP                     

FN/TN

Odds ratio

500

                     TP                     

TP+FP

Positive predictive value

500

                     TN                     

TN+FN

Negative predictive value

500

The specificity of the following scenario:

In a study to evaluate a test as a screen for the presence of a disease, 235 of the 250 people with the disease had a positive test and 600 of the 680 people without the disease had a negative test.

600/680

88%