Epidemiology

Question 1

How to mitigate selection bias

Answer 1

Randomization

Question 2

How to mitigate ascertainment bias

Answer 2

Blinding

Question 3

Converting pre-test prob to post-test prob

Answer 3

Pretest probability = prevalence = 15% = 0.15
Pretest odds = pretest probability/(1-pretest probability) = 0.15/(1-0.15) = 0.18
LR+ = sens/(1-spec) = 0.96/(1-0.8) = 4.8
Posttest odds = pretest odds x LR+ = 4.8 x 0.18 = 0.85
Posttest probability = posttest odds/(posttest odds +1) = 0.85 / (0.85+1) = 0.46 = 46%

Question 4

NNT, NNH

RRI, RRR, ARR, ARI

Answer 4

1. Relative Risk (aka risk ratio) = EER (exposed event rate) / CER (control event rate)
2. Relative risk reduction (RRR) = (CER – EER) / CER
3. Absolute risk reduction (ARR) = CER – EER
   Number needed to treat = 1 / ARR

ARI = EER-CER
RRI = ARI/CER
NNH = 1/ARI

Question 5

OR vs RR and which studies are which

Answer 5

OR = case control
RR = cohort study

Question 6

Clinical Trial phases

Answer 6

Phase 1: Safety and dosage (can be healthy volunteers)

Phase 2: Efficacy and side effects (patients with the disease/condition)

Phase 3: Long term efficacy and monitoring & COMPARED TO GOLD STANDARD (patients with the disease/condition but wider demographic)

Phase 4: Safety and efficacy (gather more information about the risks and benefits of the drugs that may not have presented earlier)