Epidemiology made easy orLies damn lies and statistics

Epidemiology made easy -or“Lies, damn lies, and statistics” Steven I Mc. Laughlin DVM, MPH, ACVPM steve@zukureview. com www. zukureview. com

“Epidemiology is just common sense, …made complicated” Dr. Jerry Gibson, State epidemiologist, South Carolina Dept. of Health and Environmental Control

Lies, damn lies, and statistics • You WILL see a couple questions on: – Sens, Spec – Predictive Val Pos, Predictive Val Neg • The key is to draw a 2 x 2 table • And remember your “ABCs”

The only table that matters: The 2 x 2 “Truth” or “Gold Std” test Your test Pos Neg a b c d Remember: You are comparing TWO TESTS when you calculate Sens, Spec, PVP, PVN You are comparing your test to a gold standard

For reference: • Sensitivity- a/a+c % true pos, correctly identified by my test a/a+c • Specificity- d/b+d % true neg, correctly identified by my test • Predictive Value Pos - a/a+b Of those my test says are pos, how many are truly pos ? a/a+b • Predictive Value Neg - d/c+d Of those my test says are neg, how many are truly neg?

You serologically test 140 wallabies for a disease. 35 wallabies test seropositive and 105 test seronegative. However, postmortem data reveals 5/35 of the seropositive wallabies are disease free and 4/105 of the seronegative wallabies are diseased. What is the predictive value positive (PVP) of this serologic test? A. 39/101 B. 35/39 C. 105/140 D. 30/35 E. 101/105 PVP/PVN PVP=a/(a+b)=30/35 “Gold Std” test Pos Neg Pos Your test Neg 30 a 4 a+c 5 35 PVP = 86% b a+b 105 c 101 d c+d b+d 140 a+b+c+d

You serologically test 100 Siberian box turtles for galloping halitosis. 27 turtles test seropositive and 73 test seronegative. However, molecular testing reveals 3/27 of the seropositive turtles are disease free and 10/73 of the seronegative turtles are diseased. What is the sensitivity of your serologic test? Sens=a/(a+c)=24/34 “Gold Std” test Pos Neg Sens/Spec A. 66/73 B. 63/66 C. 27/100 D. 10/63 E. 24/34 Pos Your test Neg Sens = 70% 27 24 a 3 b a+b 10 c 63 d c+d a+c 34 b+d 66 73 100 a+b+c+d

You serologically test 140 wallabies for a disease. 35 wallabies test seropositive and 105 test seronegative. However, postmortem data reveals 5/35 of the seropositive wallabies are disease free and 4/105 of the seronegative wallabies are diseased. What is the specificity of this serologic test? Spec=d/(b+d)=101/106 “Gold Std” test Pos Neg Sens/Spec A. 101/106 B. 105/140 C. 30/34 D. 30/35 E. 106/140 Pos Your test Neg 30 a 4 a+c 5 35 Spec = 95% b a+b 105 c 101 d c+d b+d 140 a+b+c+d

You serologically test 100 Siberian box turtles for galloping halitosis. 27 turtles test seropositive and 73 test seronegative. However, molecular testing reveals 3/27 of the seropositive turtles are disease free and 10/73 of the seronegative turtles are diseased. What is the predictive value negative (PVN) of your serologic test? A. 91% B. 89% C. 86% D. 73% E. 70 % PVP/PVN PVN=d/(c+d)=63/73 “Gold Std” test Pos Neg Pos Your test Neg PVN = 86% 27 24 a 3 b a+b 10 c 63 d c+d a+c 34 b+d 66 73 100 a+b+c+d

You are using a SLAP® heartworm antigen test with a reported sensitivity 96% and specificity of 98%. Assuming the prevalence of heartworm in your area is 10%, what is the predictive value positive (PVP) of your test ? A. 886/900 B. 96/114 C. 882/886 D. 100/114 E. 882/1000 PVP/PVN PVP=a/(a+b)=96/114 “Gold Std” test Pos Neg Pos Your test Neg 96 a 4 c a+c 100 18 PVP = 84% 114 b a+b 886 882 d c+d b+d 900 1000 a+b+c+d

Correct: PVP is 92%. The trick with this kind of question is to pick an imaginary number of animals that you test, like 1000, and fill out your 2 x 2 table from there. Follow the links to see diagrams step by step. If prev is 10% then there must be 100/1000 dogs w/ heartworm and 900 dogs that are disease-free. A 96% sensitive test will correctly call 96/100 positive (box "a"), and INcorrectly call 4/100 negative, (box "c": these are the false negs). If 100/1000 animals are infected, then 900/1000 are Dz-free. Your 98% specific test will correctly call 882/900 Dz-free (box "d": 0. 98 X 900=882) and IN-correctly call 18/900 positive, (box "b": these are the false pos). Now your a, b, c, d boxes are all filled, it is easy to calculate PVP =a/(a+b)=96/(96+18)=84% Ref: Hennekens and Buring, Epidemiology in Medicine 5 th ed. , pp. 332 -39.

You are using a SLAP® heartworm antigen test with a reported sensitivity 96% and specificity of 98%. Assuming the prevalence of heartworm in your area is 10%, what is the predictive value negative (PVN) of your test ? A. 80% B. 85% C. 88% D. 92% E. 99% PVN=d/(c+d)=882/886 PVP/PVN “Gold Std” test Pos Neg Pos Your test Neg PVN = 99% 96 a 18 b 114 a+b 4 c 886 882 d c+d a+c 100 b+d 900 1000 a+b+c+d

Correct: PVN is 99%. The trick with this kind of question is to pick an imaginary number of animals that you test, like 1000, and fill out your 2 x 2 table from there. Follow the links to see diagrams step by step. If prev is 10% then there must be 100/1000 dogs w/ heartworm and 900 dogs that are disease-free. A 96% sensitive test will correctly call 96/100 positive (box "a"), and INcorrectly call 4/100 negative, (box "c": these are the false negs). If 100/1000 animals are infected, then 900/1000 are Dz-free. Your 98% specific test will correctly call 882/900 Dz-free (box "d": 0. 98 X 900=882) and IN-correctly call 18/900 positive, (box "b": these are the false pos). Now your a, b, c, d boxes are all filled, it is easy to calculate PVN =d/(c+d)=882/(882+4)=99% Ref: Hennekens and Buring, Epidemiology in Medicine 5 th ed. , pp. 332 -39.

Congratulations! You can now handle the most common epi questions you are likely to see All you need is a 2 x 2 table “Gold Std” test Pos Neg Pos Your test Neg And these 4 equations Sensitivity - a/a+c Specificity- d/b+d Predictive Val Pos (PVP) - a/a+b Predictive Val Neg (PVN) - d/c+d a+c a b a+b c d c+d b+d a+b+c+d

Three extra concepts (In case your brain hasn’t exploded yet. ) If your head is about to pop, just try to remember the next slide. Then go home and pet your dog

You suspect hyperadrenocorticism in a 9 -year old female spayed dog with a twomonth history of increased appetite, thirst and urinary accidents. Which diagnostic test do you trust the most if it has a positive result? Urine Cortisol Creatinine Ratio (UCCR). Sensitivity=90% , Specificity =25% ACTH Stimulation. Sensitivity=80% , Specificity =85% Low Dose Dexamethasone Suppression. Sensitivity=95% , Specificity =50% A - Cannot say without knowing the predictive value negative B - Low Dose Dexamethasone Suppression (LDDS) C - Urine Cortisol Creatinine Ratio D - ACTH Stimulation E - Cannot say without knowing the predictive value positive Remember your Ps and Ns. ACTH Stim is most s. Pecific (fewer false Pos, so trust a POS test more). LDDS is more se. Nsitive (fewer false Negs, so trust NEG test more).

Why high SPECIFICITY means you can trust a POSITIVE test result: Because false pos are LOW “Truth” or “Gold Std” test Pos Your test Neg True Pos a False Negs c a+c Where did that 900 come from ? Neg False Pos (1) 0. 10 prev X 1000= 100 infected b True Negs (899) d a+b c+d b+d 900 SENS Sens = a a+c Spec = d b+d 1000 -100= 900 Dz-free Total a+b+c+d If Spec =99. 9%; Prev = 10% and test 1000 animals Spec =d/(b+d)=899/(900) Only 1 False Pos A positive result by your test is likely correct

Why high SENSITIVITY means you can trust a NEGATIVE test result : Because false negs are LOW “Truth” or “Gold Std” test Pos Your test Neg True Pos (99) False Pos False Negs (1) True Negs a c a+c 0. 10 prev X 1000= 100 infected b a+b d c+d b+d 100 SENS Sens = a a+c Spec = d b+d Where did that 100 come from ? Neg 1000 -100= 900 Dz-free Total a+b+c+d If Sens =99%; Prev = 10% and test 1000 animals Sens =a/(a+c)=99/(100) Only 1 False Neg A negative result by your test is likely correct

“Gold Std” test Pos Neg Pos Your test Neg 270 a 30 c a+c 300 As Prevalence decreases, PVP decreases too If Prev=30%, Sens and Spec=90%, 1000 turtles 70 b 340 a+b PVP=a/(a+b)=270/(270+70) 660 630 d c+d b+d 700 1000 PVP = 79% a+b+c+d “Gold Std” test Pos Neg Pos If Prev DECREASES to 1%, Sens and Spec=90%, 1000 turtles PVP=a/(a+b)=9/(9+99) PVP decreases to ~1% Your test Neg ~9 a ~99 b 108 a+b ~1 c ~891 d 892 c+d a+c 10 b+d 990 1000 a+b+c+d

As prevalence of a disease goes DOWN, PVP of your serologic test also goes DOWN. That is, as your disease becomes more and more rare, the predictive value of your same old test gets WORSE. That’s all you need to know. Read more only if you want to see the math, (but you don’t need it. ) >>>> Lets say prevalence of pedunculated giblet disease is 30% in 1000 turtles (that’s 300 infected, 700 dz-free, then). A test w/ 90% sensitivity would correctly Dx 270 (cell "a") with the dz (true pos) and INcorrectly say 30 were negative (cell "c"); a test w/ 90% specificity would correctly Dx 630 (cell "d") as dz-free (true negs) and INcorrectly say 70 were positive (cell "b"): PVP=a/(a+b)=270/(270+70)= 79%. Now, do the same math on 1000 turtles, but assume prevalence is now only 1% (0. 01) after your vaccination program. You will see PVP goes down to ~1%. Ref: Hennekens and Buring, Epidemiology in Medicine 5 th ed. , pp. 332 -39.

You’re on your way! “The art of epidemiological thinking is to draw conclusions from imperfect data” George W. Comstock

Extra practice questions, if you want them

You serologically test 140 wallabies for a disease. 35 wallabies test seropositive and 105 test seronegative. However, postmortem data reveals 5/35 of the seropositive wallabies are disease free and 4/105 of the seronegative wallabies are diseased. What is the sensitivity of this serologic test? Sens=a/(a+c)=30/34 “Gold Std” test Pos Neg Sens/Spec A. 95% B. 96% C. 88% D. 86% E. 77 % Pos Your test Neg 30 a 4 a+c 5 35 Sens = 88% b a+b 105 c 101 d c+d b+d 140 a+b+c+d

You serologically test 100 Siberian box turtles for galloping halitosis. 27 turtles test seropositive and 73 test seronegative. However, molecular testing reveals 3/27 of the seropositive turtles are disease free and 10/73 of the seronegative turtles are diseased. What is the specificity of your serologic test? Spec=d/(b+d)=63/66 “Gold Std” test Pos Neg Sens/Spec A. 95% B. 91% C. 86% D. 73% E. 70 % Pos Your test Neg Spec = 95% 27 24 a 3 b a+b 10 c 63 d c+d a+c 34 b+d 66 73 100 a+b+c+d

You serologically test 100 Siberian box turtles for galloping halitosis. 27 turtles test seropositive and 73 test seronegative. However, molecular testing reveals 3/27 of the seropositive turtles are disease free and 10/73 of the seronegative turtles are diseased. What is the predictive value positive (PVP) of your serologic test? PVP=a/(a+b)=24/27 “Gold Std” test Pos Neg Sens/Spec A. 91% B. 89% C. 86% D. 73% E. 70 % Pos Your test Neg PVP = 89% 27 24 a 3 b a+b 10 c 63 d c+d a+c 34 b+d 66 73 100 a+b+c+d

You serologically test 140 wallabies for a disease. 35 wallabies test seropositive and 105 test seronegative. However, postmortem data reveals 5/35 of the seropositive wallabies are disease free and 4/105 of the seronegative wallabies are diseased. What is the predictive value negative (PVN) of this serologic test? A. 95% B. 96% C. 88% D. 86% E. 77 % PVP/PVN PVN=d/(c+d)=101/105 “Gold Std” test Pos Neg Pos Your test Neg 30 a 4 a+c 5 35 PVN = 96% b a+b 105 c 101 d c+d b+d 140 a+b+c+d

You are using an Fe. LV test with a sensitivity of 90% and a specificity of 95%. Assuming the prevalence of feline leukemia in your area is 5%, what is the predictive value positive (PVP) of your test ? A. 45% B. 48% C. 55% D. 88% E. 90% PVP/PVN PVP=a/(a+b)=45/93 “Gold Std” test Pos Neg Pos Your test Neg PVP = 48% 45 a 48 b 93 a+b 5 c 907 902 d c+d a+c 50 b+d 950 1000 a+b+c+d