U01.06.005 Quantifying risk

Learning Objectives

  • Understand the structure and layout of the classic 2 $Latex\times$ 2 contingency table used to calculate epidemiological risk metrics.
  • Distinguish between key statistical measures including odds ratio (OR), relative risk (RR), attributable risk (AR), and absolute risk reduction (ARR).
  • Calculate and interpret clinical utility metrics such as number needed to treat (NNT), number needed to harm (NNH), case fatality rate (CFR), and attack rate.

1. The 2 \times 2 Contingency Table Layout

Epidemiological calculations are derived from a standard 2 \times 2 contingency table comparing disease or outcome status against exposure or intervention status.

Status Disease / Outcome (+) No Disease / Outcome (-)
Exposure / Intervention (+) a (True Positive) b (False Positive)
Control / Unexposed (-) c (False Negative) d (True Negative)

2. Core Quantifying Risk Metrics

Term Definition & Interpretation Formula
Odds Ratio (OR) Used in case-control studies. Odds of exposure among cases vs. controls. OR = 1 (no association), OR > 1 (greater exposure in cases), OR < 1 (greater exposure in controls). For rare diseases, OR approximates RR. OR = \frac{a/c}{b/d} = \frac{ad}{bc}
Relative Risk (RR) Used in cohort studies. Risk of developing disease in the exposed group divided by risk in the unexposed group. RR = 1 (no association), RR > 1 (increased risk), RR < 1 (decreased risk). RR = \frac{a / (a + b)}{c / (c + d)}
Relative Risk Reduction (RRR) The proportion of risk reduction attributable to the intervention/treatment (A_{RT}) as compared to a control (A_{RC}). RRR = 1 - RR = \frac{A_{RC} - A_{RT}}{A_{RC}}
Attributable Risk (AR) The absolute difference in risk between exposed and unexposed groups. AR = \frac{a}{a + b} - \frac{c}{c + d}
Absolute Risk Reduction (ARR) The absolute difference in risk attributable to the intervention compared to a control. ARR = \frac{c}{c + d} - \frac{a}{a + b}
Number Needed to Treat (NNT) Number of patients who need to be treated for 1 patient to benefit. Lower number = better treatment. NNT = \frac{1}{ARR}
Number Needed to Harm (NNH) Number of patients who need to be exposed to a risk factor for 1 patient to be harmed. Higher number = safer exposure. NNH = \frac{1}{AR}
Case Fatality Rate (CFR) Percentage of deaths occurring among those with the disease. CFR\% = \frac{\text{Deaths}}{\text{Cases}} \times 100
Mortality Rate Number of deaths (overall or cause-specific) within a population over a defined period. \text{Deaths} / 1,000 \text{ people per year}
Attack Rate Proportion of exposed people who become ill during an outbreak. \text{Attack Rate} = \frac{\text{People who become ill}}{\text{Total people exposed}}


Clinical Integration & Application Rules:

  • The Case-Control Trick: Remember “You take a case to the OR”—Odds Ratio is used exclusively for retrospective case-control study designs (OR = \frac{ad}{bc}).
  • Cohort Calculation: Cohort studies track exposure forward to incidence, using Relative Risk (RR).
  • Therapeutic Efficiency: For NNT, a lower number indicates a highly effective, beneficial intervention requiring fewer treated patients to see one successful clinical outcome.

Key Points & Memory Hooks:

  • Rare Disease Shortcut: When disease prevalence is very low, Odds Ratio approximates Relative Risk.
  • NNT vs NNH Direction: NNT uses ARR in the denominator (\frac{1}{ARR}), whereas NNH uses AR in the denominator (\frac{1}{AR}).

Activity