Sensitivity
true positives / (true positives + false negatives)
Of everyone with the disease, how many did the test detect?
AKT statistics questions are usually simple once the table is set up correctly. Learn the formulas, then practise turning wordy scenarios into a 2x2 table or a pair of event rates.
Statistics formulas
The core AKT statistics formulas to know are sensitivity, specificity, PPV, NPV, ARR, RRR, NNT, NNH and basic interpretation of confidence intervals. Most calculation questions become straightforward if you build the 2x2 table first. For NNT and NNH, convert percentages to decimals before using 1 divided by the absolute risk difference.
true positives / (true positives + false negatives)
Of everyone with the disease, how many did the test detect?
true negatives / (true negatives + false positives)
Of everyone without the disease, how many did the test correctly exclude?
true positives / (true positives + false positives)
Of everyone with a positive test, how many truly have the disease?
true negatives / (true negatives + false negatives)
Of everyone with a negative test, how many truly do not have the disease?
events / total people in group
The actual event rate in one group.
control event rate - treatment event rate
The absolute difference in risk between control and treatment.
absolute risk reduction / control event rate
The proportional reduction in risk compared with the control group.
treatment event rate / control event rate
The proportional risk in one group compared with another.
1 / absolute risk reduction
How many people need treatment for one extra person to benefit.
1 / absolute risk increase
How many people need exposure for one extra person to be harmed.
Put disease status across the top and test result down the side. That gives you true positives, false positives, false negatives and true negatives. Sensitivity and specificity start with disease status. PPV and NPV start with the test result.
| Disease present | Disease absent | |
|---|---|---|
| Test positive | True positive | False positive |
| Test negative | False negative | True negative |
The core AKT statistics formulas are sensitivity, specificity, PPV, NPV, absolute risk, relative risk, absolute risk reduction, absolute risk increase, NNT and NNH. You also need to interpret confidence intervals, charts, forest plots and practice-level data.
Calculate the absolute risk reduction first, then use NNT = 1 / ARR. If control event rate is 20% and treatment event rate is 15%, ARR is 5% or 0.05, so NNT is 20.
Use the disease column first. Sensitivity is true positives divided by everyone with disease. Specificity is true negatives divided by everyone without disease. Then PPV and NPV start from the test result instead.
No. The AKT also tests interpretation: confidence intervals, graphs, prescribing dashboards, patient risk communication, study design and critical appraisal. Formulas are the base layer, not the whole section.
This is revision guidance, not official RCGP advice. Check RCGP, NICE CKS and the BNF for current exam and clinical guidance. Last reviewed June 2026.
Questions, mocks and explanations are free. Your first 2 hours of AKT audio are free. Full 4-month audio access is £79.