EXPECTED VALUE OF PERFECT INFORMATION - EVPI
 

(c) Health Decision Strategies, LLC.
 
  Beta Test - Not for Official Use
  Data Entry Form
 
  You can enter new values in the yellow boxes.  
  Calculated results will appear in the blue boxes.  
     
  Disease Probability   Variable Value  
  Prob_Strep   Basic_Test  
  Prob_NoStrep   Perfect_Test  
  No_Test  
  No_Treat  
  Treat  
  Treat_Later  
 
  Outcome  
      Value  
  Strep            
         
  No_Treat and No_Test   EV=  
      C    
  EV=    
      No Strep            
         
      EV=  
     
       
      Test Positive(TP)_Treat  
               
        Strep       EV=  
          C    
        EV=    
          Test Negative(FN)_NoTreat  
             
  Basic_Test       EV=  
      C    
  EV=        
          Test Positive(FP)_Treat  
                 
        No Strep       EV=  
Sore       C    
Throat   D     EV=    
        Test Negative(TN)_NoTreat  
  =EV      
      EV=  
     
       
      Strep            
             
  Treat_Without_Test     EV=  
      C    
  EV=    
      No Strep            
         
      EV=  
     
      1.0  
      Test Positive(TP)_Treat  
               
      Strep       EV=  
          C    
      EV=   0.0  
          Test Negative(FN)_NoTreat  
             
  Perfect Test         EV=  
  C    
  EV=       0.0  
      Test Positive(FP)_Treat  
           
  No Strep       EV=  
  C    
  EV=   1.0  
  Test Negative(TN)_NoTreat  
     
  EV=  
Example of bar graph generated by EVPI calculator:    
     
 
Example of bar graph generated by EVPI calculator>
      
     
     
     
     
     
     
     
     
     
     
     
                               


Bar Graph Data Explanation:
  Options EV Of Treatment Plan Option EV of Option Minus Perfect Test                
1 << Compared to Option 1, the Perfect Test is Worth This Value  
2 << Compared to Option 2, the Perfect Test is Worth This Value  
3 << Compared to Option 3, the Perfect Test is Worth This Value  
                 
 
         

Test Statistics can be modified in yellow boxes.  
Patient Status
Patient Status
Sensivitty = TP/(TP+FP)
 
Has
Has No
This value is modified if you change the TP for the Basic Test above.
 
Disease
Disease
Specificity = TN/(TN+FN)
    Pos Neg This value is modified if you change the TN for the Basic Test above.
Test Result
Pos
Sensitivity is the proportion of patients who have this disease
  Neg
and who had a positive test result.
       
Specificity is the proportion of patients who have no disease, who had a negative test result.
       
             
             
Definitions   Patient Status Patient Status      
        TP = True Positive = test is positive and patient has disease
        TN = True Negative = test is negative and patient does not disease.
    D+ D- FP = False Positive = test is positive but patient does not have disease.
Test Result T+ TP [a] FP [b] FN = False Negative = test is negative,  but patient has the disease.
  T- FN [c] TN [d]  
             
             
             



Developed By HDS
 

References:

1. Hunink M et al. Decision making is health and medicine. 2001 Cambridge University Press.
2. DATA Treeage tutorials - www.treeage.com
3. TreePlan tutorials - www.treeplan.com
4. Ebell MH, An introduction to information mastery - decision analyses - www.poems.msu.edu/infomastery.