Lecture 5 - Bias, Dx tests, & risk calculations

Question 1

Expresses the relationship between two numbers

Answer 1

ratio (I.e., 100 pts with heart disease, 50 are diagnosed, ratio is 100:50 or 2:1)

Question 2

Type of ratio indicating the probability or percentage of a total sample that experienced an event without time implications

Answer 2

proportion (100 patients with heart disease, 50 diagnosed, proportion is 50%)

Question 3

type of proportion that includes a specific study period; used to assess speeds at which the outcome is developing

Answer 3

rate (100 patients with heart disease, 50 are diagnosed within 2 years. So 50 diagnosed in 2 years or a rate of 25 per year)

Question 4

risk of developing a new disease, symptom, or problem; number of new cases that develop in a population at risk

Answer 4

incidence

Question 5

Probability of having a disease at a point in time; reflects EXISTING disease in a population

Answer 5

prevalence

Question 6

Have to be able to meaningfully classify individuals as ____ or ____

Answer 6

diseased; non-diseased

Question 7

Diagnostic tests are required for useful _____ and ______ measures

Answer 7

incidence; prevalence

Question 8

Identifying ____, ____, and ___ to classify the usefulness of tests

Answer 8

specificity; sensitivity; predictive values

Question 9

The ability of a diagnostic test to correctly identify individuals with the disease

Answer 9

sensitivity

Question 10

Sensitivity is described through ______ rate and ______ rate

Answer 10

true positive (the likelihood of a positive when a positive exists); false negative

Question 11

As the sensitivity of a test increases, the false negative rate ____

Answer 11

decreases

Question 12

T/F Highly sensitive tests do not miss identifying many patients who actually have the disease

Answer 12

T

Question 13

How is sensitivity calculated?

Answer 13

sensitivity = true positive / (true positive + false negative)

Question 14

The ability of a diagnostic test to correctly identify individuals without disease; proportion of individuals without the disease who are correctly identified by a test as disease-free

Answer 14

specificity

Question 15

Specificity is described as the _____ rate and ____ rate.

Answer 15

true negative (the likelihood of a negative when a negative exists); false positive

Question 16

Tests with high specificity have ____ false positive rates.

Answer 16

low

Question 17

What is the calculation for specificity?

Answer 17

specificity = true negative / (true negative + false positive)

Question 18

____ - describes how likely it is that the individual does or does not have a disease given the test result.

Answer 18

predictive value

Question 19

____ - the probability that a patient has a disease given a positive test result

Answer 19

positive predictive value

Question 20

___ - the probability that a patient does not have a disease given a negative test result

Answer 20

negative predictive value

Question 21

Predictive values are affected by the ____ of disease in a target population.

Answer 21

prevalence

Question 22

Absolute risk (AR) = ?

Answer 22

number of patients with outcome / # of total patients

Question 23

Calculation that provides a numerical value for outcomes (positive outcomes = NNT; negative outcomes = NNH)

Answer 23

Number needed to treat/harm

Question 24

NNT => always round ____
NNH => always round ____

Answer 24

up; down

Question 25

How do you calculate absolute risk reduction?

Answer 25

ARR = AR of control - AR of intervention

Question 26

How do you calculate relative risk (RR)?

Answer 26

RR = AR intervention/AR control

Question 27

How do you calculate relative risk reduction?

Answer 27

1 - RR

Question 28

How to calculate number needed to treat?

Answer 28

NNT = 1/ARR

Question 29

How to calculate number needed to harm?

Answer 29

NNH = 1/ARI (absolute risk increase = AR control - AR intervention)