Back to Module 3
Module 3 - Lesson 3

Effect Sizes That Matter

NNT, absolute vs relative risk, and what to report to patients

The Drug Rep's Favorite Trick

A familiar scene

A pharmaceutical rep shows you data for a new statin. They announce excitedly:

"Our drug reduces heart attacks by 50%!"

Sounds impressive. Should you prescribe it to your at-risk patients?

Before you decide, you ask: "What were the actual event rates?"

What they said

50%

Relative risk reduction

The full picture

Placebo: 2% had heart attacks

Drug: 1% had heart attacks

Absolute reduction: 1%

The trick: Relative risk makes tiny effects look huge. A change from 2% to 1% is a 50% relative reduction, but only a 1% absolute reduction.

Absolute vs Relative Risk

The same data can tell very different stories depending on how you frame it.

Cancer screening study

Screening reduces cancer deaths from 4 per 10,000 to 3 per 10,000

Metric Value Sounds like...
Relative Risk Reduction 25% "Huge benefit!"
Absolute Risk Reduction 0.01% "Quite small..."
Number Needed to Screen 10,000 "For 1 life saved"
Relative Risk Reduction = (Old Rate - New Rate) / Old Rate
(4 - 3) / 4 = 0.25 = 25%
Absolute Risk Reduction = Old Rate - New Rate
0.0004 - 0.0003 = 0.0001 = 0.01%
Red flag: When a paper only reports relative risk reduction, ask yourself why they're hiding the absolute numbers.

Number Needed to Treat (NNT)

The most patient-friendly way to communicate treatment effects.

NNT = 1 / Absolute Risk Reduction

If ARR = 1% (0.01), then NNT = 1 / 0.01 = 100

Translation: You need to treat 100 patients to prevent 1 event.

NNT = 10 (treat 10 to help 1)

Green = helped by treatment | Gray = treated but no benefit

Putting NNT in context

Treatment NNT Interpretation
Aspirin for MI (acute) 42 Very effective
Statins (primary prevention) 100-200 Modest benefit
Mammography (50-59y, 10yr) 1,000+ Small absolute benefit
Clinical pearl: NNT lets you have honest conversations with patients. "If I treat 100 people like you, 1 will benefit and 99 won't notice a difference."

Number Needed to Harm (NNH)

Benefits don't exist in isolation. Every treatment has a cost.

NNH = 1 / Absolute Risk Increase (for side effect)

If a drug causes GI bleeding in 2% vs 0.5% with placebo:
NNH = 1 / (0.02 - 0.005) = 1 / 0.015 = 67

The risk-benefit calculation

Consider a blood thinner for stroke prevention:

Benefit

25

NNT to prevent 1 stroke

Harm

50

NNH for major bleed

For every 2 strokes prevented, there's 1 major bleed caused

The NNT/NNH ratio

Ideally: NNT << NNH (help many, harm few)

Danger zone: NNT ≈ NNH (helping as many as harming)

Never acceptable: NNT > NNH (harming more than helping)

Shared decision-making: Present both numbers. Let patients weigh stroke vs bleeding risk based on their values.

The Odds Ratio Trap

Odds ratios are not risk ratios, but they're often treated as if they are.

Study result

A case-control study reports: OR = 2.5 for the association between a medication and falls in elderly patients.

Does this mean the medication doubles fall risk?

Risk Ratio (RR)

Probability of event in exposed / Probability in unexposed

Intuitive: "2x more likely"

Odds Ratio (OR)

Odds of event in exposed / Odds in unexposed

Less intuitive but necessary for case-control studies

The trap: OR ≈ RR only when the outcome is rare (<10%). For common outcomes, OR dramatically overstates the relative risk.

When outcome is common (50% baseline):

Group Events Odds
Control 50% 50/50 = 1.0
Exposed 75% 75/25 = 3.0

OR = 3.0, but actual risk increase = 1.5x (not 3x!)

Clinical translation: When reading case-control studies with common outcomes, remember that the OR exaggerates the true relative risk.

Telling Patients What Matters

Same data, different framings - which helps patients make informed decisions?

Discussing a preventive medication

The drug reduces cardiovascular events from 8% to 6% over 5 years.

Less helpful framings:

"This drug reduces your risk by 25%!"

Relative risk - sounds bigger than it is

"The p-value was highly significant at 0.001."

Statistical jargon - meaningless to patients

More helpful framings:

"Without treatment: 8 out of 100 people like you will have a heart attack or stroke in 5 years."

"With treatment: 6 out of 100 will."

Natural frequencies - intuitive

"If I treat 50 people like you for 5 years, 1 person will avoid a heart attack or stroke. The other 49 would have been fine anyway or will have one despite treatment."

NNT framing - honest about limitations

The best practice

Use natural frequencies (X out of 100) and NNT. Add context about side effects and NNH. Let patients weigh the trade-offs.

Test Your Understanding

For each scenario, identify the best interpretation or catch the misleading statistic.

Key Takeaways

1. Absolute > Relative

Always ask for absolute risk reduction. A 50% relative reduction could be 10% → 5% (big deal) or 0.002% → 0.001% (trivial).

2. NNT for communication

Number Needed to Treat is the most patient-friendly metric. "I'd need to treat X people for 1 to benefit."

3. Don't forget NNH

Every benefit has a cost. Compare NNT to NNH for a complete picture.

4. Odds ratio caution

OR ≈ RR only when outcomes are rare. For common outcomes, OR overstates the effect.

5. Natural frequencies win

Tell patients "X out of 100" rather than percentages or relative risks.