








USMLE Step 2 CK Forum USMLE Step 2 CK Discussion Forum: Let's talk about anything related to USMLE Step 2 CK exam 

Thread Tools  Search this Thread  Display Modes 
#1




Calculate the Likelihood Ratio
The table below summarizes the results of a new test to identify patients with an acute myocardial infarction (AMI).
The test was performed on 400 subjects. Acute Myocardial Infarction...... Present............ Absent................. Total Test Result ...................Positive................ 120.................. 30....................... 150 ..................Negative................. 80.................... 170 ................... 250 .......................Total............... 200..................... 200..................... 400 If one of the 400 subjects in the study is randomly chosen, what is the likelihood that an abnormal test indicates that the individual has an AMI? A. 0.50 B. 0.60 C. 0.68 D. 0.80 E. 0.85 
The above post was thanked by:  
cingulate.gyrus (08062012) 
#2




Positive predictive value....C...0.68

#3




Explanation:
The correct answer is D. The likelihood of an abnormal test indicating disease, or the positive predictive value of a test (PV+), is expressed with the following formula: PV+ = TP/(TP + FP) where a true positive (TP) is an abnormal test result in an individual with disease, while a false positive (FP) is an abnormal test result in a healthy person. Note that as the FP rate decreases, the PV+ approaches 100%. The FP rate reflects the test's specificity, or the chance that a test is normal in a healthy individual. As the FP rate of a test decreases, the test's specificity approaches 100%. Therefore, a test with 100% specificity always has a PV+ of 100%. This underscores why tests with high specificity are used to confirm disease, since an abnormal test is more likely to represent a TP rather than a FP. From the table we can see the following: TP = 120, FN = 80, TN = 170, and FP = 30. The likelihood of an abnormal test indicating an AMI is therefore: PV+ = 120/(120 + 30) = 0.80 Thus there is an 80% chance that an abnormal test is a TP and a 20% chance that it is a FP. Choice A is the prevalence of AMI in this study. Prevalence refers to the number of subjects with disease (TP + FN) divided by the total number of subjects in the study. Hence, the prevalence of an AMI in this study is (120 + 80)/(120 + 80 + 170 + 30) = 0.50, or 50%. As expected, the higher the prevalence of disease, the greater the PV+ , since the number of individuals with disease (TPs) is increased. Choice B is the test's sensitivity [TP/(TP + FN)], which is calculated as follows: 120/(120 + 80) = 0.60, or 60%. The test's sensitivity is too low to be useful as a screening test for an AMI. Choice C is the negative predictive value (PV) = [TN/(TN + FN)], which is calculated as follows: 170/(170 + 80) = 0.68, or 68%. This percentage indicates that there is a 68% chance that a normal test is a TN and a 32% chance that it is a FN. The higher the prevalence of disease, the lower the PV, since a greater number of FNs are present. Choice E is the test's specificity [TN/(TN + FP)], which is calculated as follows: 170/(170 + 30) = 0.85, or 85%. Although this test's specificity is higher than its sensitivity, its specificity is not high enough for it to be useful as a confirmatory test for an AMI. 


#4




seems am sleepy calculated the wrong thing...its 0.8....still PPV as i mentioned earlier....

#5




Quote:

The above post was thanked by:  
riya rai (08062012) 
#6




Quote:
http://www.usmleforums.com/usmlest...ttsquare.html 
#7




?????? please explain this for me

#8




Sorry I was calculating The Likelihood Ratio . Seeing the word likelihood i jumped into conclusion of calculating likelihood ratio..
Sorry in this case we are supposed to calculate positive predictive value. Likelihood ratio is the likelihood that a given test result would be expected in a patient with the target disorder compared to the likelihood that that same result would be expected in a patient without the target disorder. Likelihood ratio for +ve result and ve result are calculated by the formula. LR+ = sensitivity / (1specificity) = (a/(a+c)) / (b/(b+d)) LR = (1sensitivity) / specificity = (c/(a+c)) / (d/(b+d) 
The above post was thanked by:  
riya rai (08072012) 
Tags 
BiostatisticsEpidemiology, Step2Questions 
Thread Tools  Search this Thread 
Display Modes  

Similar Threads  
Thread  Thread Starter  Forum  Replies  Last Post 
Estimating the likelihood of cancer?  meka  USMLE Step 2 CK Forum  7  04182017 03:00 PM 
Likelihood Ratio  kalpana  USMLE Step 1 Forum  2  02172016 11:24 AM 
The likelihood that the difference is due to chance  nativedoc2  USMLE Step 1 Forum  11  08302011 08:07 PM 
The likelihood that he has the disease?  thunderbolt  USMLE Step 2 CK Forum  15  05172011 10:28 AM 
The likelihood that the patient is having cancer  achistikbenny  USMLE Step 1 Forum  4  06292010 01:13 AM 
