EBM Day 4

Question 1

Variance

Answer 1

Average of squared differences from the mean

Question 2

SD

Answer 2

square root variance

Question 3

SE +meaning

Answer 3

SD/sqrtN

The SD of the distribution of mean value

Question 4

Central Limit Therom

Answer 4

When normal diet

More samples you take, more closer you get true mean

Question 5

CI calc + meaning

Answer 5

mean+/-Z(usually 1.96)*SE

this is where we think sample mean lies

Question 6

Point estimate

Answer 6

estimate of some value derived from study (mean, regression coeff etc)

Question 7

Z=+1.96
Z=-1.96
what %

Answer 7

both in 97.5% or 2.5% chance of not being in

total = 5%

Question 8

When to compare CI to 0 (2)or 1 (3)

Answer 8

0=correlation or dif
1-hazard ratio, relative risk, odds ratio (these all kinda same thing too)
ESSENTIALLY WHAT THE NULL IS

Question 9

Smaller CI

Answer 9

Higher precision and more n

Question 10

Marginally sig

Answer 10

A little bias either way can make sig or not sig

Question 11

2x2 false pos and negative chart

Answer 11

draw

Question 12

Misclassifcation

Answer 12

False positives and false negatives

Question 13

TN, FN, TP, FP chart and sensitivity

Answer 13

draw

Question 14

+PV and -PV and meaning

Answer 14

Predictive value

TP/TP+FP
TN/FN+TN

Probability that a patient with positive test result truly has disease

Probably that a patient with negative result does not have disease

Question 15

Sensitivity and meaning and when best

Answer 15

TP/TP+FN

No false negatives
Negative result=rule out
SNOUT
Sennstive, negative rules out disease

GOOD FOR cheap and initial procedures

Question 16

Specificity and meaning and when best

Answer 16

tN/FP+TN

No false positives
Positives-rule in
SPIN
Specific, positive rules in

GOOD FOR EXPENSIVE and dangerous PROCEDURES

Question 17

Draw cut off point table with TP, TN, FP, FN

Answer 17

draw

Question 18

Prevalence

Answer 18

TP+FN/TOTAL

Question 19

LR+ and meaning

Answer 19

Likelihood ratio

TP/TP+FN/
FP/FP+TN

how likely to have disease when test is positive

how many times more likely a (+) test result is to be found in people with disease compared to those without

Question 20

LR- and meaning

Answer 20

FN/TP+FN/
TN/TN+FP

how likely to have disease when test is negative

how many times more likely a (-) test result is to be found in people with disease compared to those without? i think

Question 21

TP=
FP=
FN=
TN=

Answer 21

SE
1-SP (false positive rate)
1-SE
SP

Question 22

1-SP

SEN

Answer 22

false postive rate

True positive rate

Question 23

ROC Curve

Answer 23

Senstivity (TP) on Y
1-Specifity (FP rate) on X

Upper left is where you wanna be

Question 24

Relationship between predictive value and prevalence

Answer 24

Lower prevalence, lower predictive value

Question 25

Post test probability

Answer 25

Probability of a disease after test result is known

Question 26

Natural Frequencies Approach

Answer 26

Choose large population Use sensitivity to find TP Use 1-spec to find FP TP/TP+FP=+PV

Question 27

Increase pretest probability

Answer 27

consider demograpics, presentation, clinical setting

Question 28

Nomogram

Answer 28

use Pretest prob (prevalance) and then find LR and draw line to Post test prob (PV)

Question 29

``` LR to change in disease prob % 10 5 2 .5 .1 ```

Answer 29

``` 45% 30% 15% -30% -45% ```

Question 30

Parallel testing and sens/spec relationship

Answer 30

Test A or B, or C positive makes all positive Sens up, spec down

Question 31

Serial testing and sens/spec relationship

Answer 31

Test A AND B AND C postiv Send down, Spec up

Question 32

Independent tests | as related to serial/parallel testing

Answer 32

Assumed by parallel and serial testing

Question 33

Index Test vs reference

Answer 33

new test when compared to gold standard

Question 34

Basic approach to evaluating diagnostic tests

Answer 34

``` select patients test all patients with index diagnose in series then do gold standard Compare results of index test to reference index results Look for sources of error ```

Question 35

5 challenges to establishing accuracy in diagnostic test

Answer 35

``` inappropraite ref standard spectrum bias verification bias observor bias chance ```

Question 36

Spectrum bias and big problem

Answer 36

including only highly selected patients (such as those who would benefit) - problem of including people who would benefit a lot, and very little and leaving out middle (where there would be a lot of false positives and false negatives - big change to specificity and sensitivity

Question 37

verification bias

Answer 37

work up bias | not giving both tests reference may be too invasive to give if respond to index

Question 38

Observor bias (5 reasons why occur)

Answer 38

Ref standard is subjective Index and reference standard not evaluated independently Evaluators not blinded to results of other test Evaluators not blidned to patient characteristics

Question 39

Must design index test without out this value

Answer 39

Reference standard-leads to bias if don't do this