Diagnostic Testing. Ethan Cowan, MD, MS Department of Emergency Medicine Jacobi Medical Center Department of Epidemiology and Population Health Albert Einstein College of Medicine. The Provider Dilemma.
Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.
Diagnostic Testing
Ethan Cowan, MD, MS
Department of Emergency Medicine
Jacobi Medical Center
Department of Epidemiology and Population Health
Albert Einstein College of Medicine
Why Order a Diagnostic Test?
Probability of Disease
0%
100%
Testing Zone
P(+)
P()
Pauker and Kassirer, 1980, Gallagher, 1998
Probability of Disease
0%
100%
Testing Zone
P(+)
P()
Pauker and Kassirer, 1980, Gallagher, 1998
Reliability
Inter observer
Intra observer
Correlation
B&A Plot
Simple Agreement
Kappa Statistics
Validity
Sensitivity
Specificity
NPV
PPV
ROC Curves
Not Reliable
Reliable
O1
O1 = O2
O2
Bland & Altman, 1986
O1
r = 0.8
O1 = O2
O2
Bland & Altman, 1986
O1 – O2
10
0
10
[O1 + O2] / 2
Bland & Altman, 1986
a
b
c
d
Rater 1
Rater 2

+
total

a + b
+
c + d
total
a + c
b + d
N
a
b
c
d
Rater 1
Rater 2

+
total

a + b
+
c + d
total
a + c
b + d
N
K=1
K > 0.80
0.60 < K < 0.80
0.40 < K < 0.60
0 < K < 0.40
K = 0
K < 0
Perfect
Excellent
Good
Fair
Poor
Chance (pa = p0)
Less than chance
n11
n12
...
n1C
n21
n22
...
n2C
. .
. .
...
...
. .
nC1
nC2
...
nCC
Rater 1
Rater 2
1
2
...
C
total
1
n1.
2
n2.
. .
. .
C
nC.
total
n.1
n.2
...
n.C
N
Valid, not reliable
Reliable and Valid
Disease Status
TP = True Positives
FP = False Positives
total
noncases
cases
positives
Test Result
+
TP
FP
negatives

FN
TN
total
cases
noncases
N
TN = True Negatives
FN = False Negatives
Disease Status
total
noncases
cases
positives
Test Result
+
TP
FP
negatives

FN
TN
total
cases
noncases
N
Sackett & Straus, 1998
Disease Status
total
noncases
cases
positives
Test Result
+
TP
FP
negatives

FN
TN
total
cases
noncases
N
Sackett & Straus, 1998
Gallagher, 1998
Disease Status
total
noncases
cases
positives
Test Result
+
TP
FP
negatives

FN
TN
total
cases
noncases
N
Sackett & Straus, 1998
Disease Status
total
noncases
cases
positives
Test Result
+
TP
FP
negatives

FN
TN
total
cases
noncases
N
Sackett & Straus, 1998
Vulnerable to Disease Prevalence (P) Shifts
Do not remain constant over patient populations
As PPPV NPV
As PPPV NPV
Gallagher, 1998
ED AMI Prevalence 6%
SN = 3 / 6 = 50%SP = 47 / 94 = 50%
PPV= 3 / 50 = 6%NPV = 47 / 50 = 94%
Worster, 2002
CCU AMI Prevalence 90%
SN = 45 / 90 = 50% SP = 5 / 10 = 50%
PPV= 45 / 50 = 90%NPV = 5 / 50 = 10%
Worster, 2002
1.0
Sensitivity
(TPR)
0.0
0.0
1.0
1Specificity (FPR)
Sepsis
Effect
No Effect
WBC Count
Gallagher, 1998
1.0
Sensitivity
(TPR)
0.0
0.0
1.0
1Specificity (FPR)
Gryzybowski, 1997
Physical Exam
+
OR
CT Scan


+
No Appy
Appy
Cardall, 2004
SN 76% (65%84%)
SP 52% (45%60%)
PPV 42% (35%51%)
NPV 82% (74%89%)
Cardall, 2004
Physical Exam
+
OR
CT Scan


+
No Appy
Appy
Cardall, 2004
But, was WBC necessary?
Answer given in talk on Likelihood Ratios