Scribd Logo
Upload

Welcome to Scribd!

  • 56 views

    Screening Test (Adv) : Rizwanul Karim Nipsom

    Uploaded by

    Rizwan Shameem
    This document discusses key concepts related to diagnostic test evaluation including: - Sensitivity and specificity measure the performance of a dichotomous diagnostic test - Sensitivity is the probability that a test is positive when the disease is present, specificity is the probability that a test is negative when the disease is absent - Likelihood ratios (LR) quantify how much a test result will raise or lower the probability of disease, where LR+ uses sensitivity and 1-specificity and LR- uses 1-sensitivity and specificity - LRs allow changing pre-test probabilities to post-test probabilities using simple calculations based on the likelihood ratio and pre-test odds

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPTX, PDF, TXT or read online from Scribd

    Screening Test (Adv) : Rizwanul Karim Nipsom

    Uploaded by

    Rizwan Shameem
    56 views37 pages
    This document discusses key concepts related to diagnostic test evaluation including: - Sensitivity and specificity measure the performance of a dichotomous diagnostic test - Sensitivity is the probability that a test is positive when the disease is present, specificity is the probability that a test is negative when the disease is absent - Likelihood ratios (LR) quantify how much a test result will raise or lower the probability of disease, where LR+ uses sensitivity and 1-specificity and LR- uses 1-sensitivity and specificity - LRs allow changing pre-test probabilities to post-test probabilities using simple calculations based on the likelihood ratio and pre-test odds

    Original Title

    Screening LR Kappa Faculty

    Copyright

    © Attribution Non-Commercial (BY-NC)

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses key concepts related to diagnostic test evaluation including: - Sensitivity and specificity measure the performance of a dichotomous diagnostic test - Sensitivity is the probability that a test is positive when the disease is present, specificity is the probability that a test is negative when the disease is absent - Likelihood ratios (LR) quantify how much a test result will raise or lower the probability of disease, where LR+ uses sensitivity and 1-specificity and LR- uses 1-sensitivity and specificity - LRs allow changing pre-test probabilities to post-test probabilities using simple calculations based on the likelihood ratio and pre-test odds

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    56 views37 pages

    Screening Test (Adv) : Rizwanul Karim Nipsom

    Uploaded by

    Rizwan Shameem
    This document discusses key concepts related to diagnostic test evaluation including: - Sensitivity and specificity measure the performance of a dichotomous diagnostic test - Sensitivity is the probability that a test is positive when the disease is present, specificity is the probability that a test is negative when the disease is absent - Likelihood ratios (LR) quantify how much a test result will raise or lower the probability of disease, where LR+ uses sensitivity and 1-specificity and LR- uses 1-sensitivity and specificity - LRs allow changing pre-test probabilities to post-test probabilities using simple calculations based on the likelihood ratio and pre-test odds

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    You are on page 1of 37

    Screening test (adv)

    Rizwanul karim NIPSOM

    The relationship between a diagnostic test result and the occurrence of disease

    Disease
    Present Positive True positive + ve Negative False negative - ve Absent False positive

    Test

    True negative

    Comparison of the Results of a Dichotomous Test with Disease Status

    True Characteristics In The population


    Test results Positive Negative With Disease True Positive (TP) = Have disease and Have positive Test False negative (FN) = Have disease, but have negative test Without Disease False positive (FP) = No disease, but have positive test True negative (TN) = No disease and have negative test

    Sensitivity =

    TP TP FN

    Specificity =

    TN TN FP

    TN

    FP

    FP

    TP F N
    TP FN

    a c

    FP
    TN

    b d

    Sensitivity and specificity


    Disease
    Present
    Positive

    Absent

    a c
    a Se ac

    b d
    d Sp bd

    Test
    Negative

    a PV ab
    d PV cd

    ac p abcd

    The true positive probability (sensitivity) The false negative probability (1-sensitivity)

    The true negative probability (specicity) The false positive probability (1-specicity)

    Diagnostic test
    Disease
    Present
    Positive

    Absent

    PV

    a ab
    d cd

    Test
    Negative
    Se = Sensitivity; Sp = Specificity P = Prevalence; PV = Predictive value; LR = Likelihood ratio, LR+ same as Se/(1-Sp) LR - same as (1-Se)/Sp

    c
    a Se ac

    d
    Sp d bd

    PV

    a LR a c b bd

    c LR a c d bd

    ac p abcd

    example
    The true positive probability (sensitivity) The false negative probability (1-sensitivity)

    The true negative probability (specicity) The false positive probability (1-specicity)

    Pathology present absent Total + positive Liver scan - negative Total 231 27 258 32 54 86 263 81 344

    a 231 Sensitivity .895 a c 258

    d 54 Specificity .627 c d 86

    example
    The probability of having disease if you have a positive test is called the positive predictive value (PPV) The probability of not having disease if you have a negative test is called the negative predictive value (NPV)

    Pathology present absent Total + positive Liver scan - negative Total 231 27 258 32 54 86 263 81 344

    a 231 PPV .878 a b 263 d 54 NPV .666 c d 81

    KAPPA
    Kappa percent observed agreement - percent agreement expected by chance alone 100% - percent agreement expected by chance alone

    Kappa
    Pathologist A Grade II Grade II 41 Grade III 3 Totals by B 44 (58.7%)

    Pathologist B

    Grade III Totals by A

    4
    45 (60%)

    27
    30 (40%)

    31 (41.3%)
    75 (100%)

    kappa
    Pathologist A Grade II Grade II 41 Grade III 3 Totals by B 44 (58.7%)

    Pathologist B

    Grade III

    4
    45 (60%)

    27
    30 (40%)

    31 (41.3%)
    75 (100%)

    41 27 percent agreement X 100 90.7 % 75 observed

    kappa
    Pathologist A Grade II Grade II 41 Grade III 3 Totals by B 44 (58.7%)

    Pathologist B

    26.4

    Grade III

    4
    45 (60%)

    27

    12.4

    31 (41.3%)
    75 (100%)

    30 (40%)

    26.4 12.4 38.8 percent agreement X 100 51.7 % 75 75 expected by chance

    kappa
    90.7% - 51.7% kappa 100% - 51.7% 39% .81 48.3%

    .40 to .75 represents intermediate to good agreement

    Likelihood ratio

    Likelihood ratio
    The Likelihood Ratio (LR) 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.

    example
    For example, you have a patient with anaemia and a serum ferritin of 60mmol/l and you find in an article that 90 per cent of patients with iron deficiency anaemia have serum ferritins in the same range as your patient (= sensitivity) and that 15 per cent of patients with other causes for anaemia have serum ferritins in the same range as your patient (1 specificity). This means that your patient's result would be six times as likely (90/15) to be seen in someone with, as opposed to someone without, iron deficiency anaemia, and this is called the LR for a positive test result.

    sensitivity LR 1 - specificity

    LR

    Pr(T D) Pr(T D)

    "the probability of a person who has the disease testing positive divided by the probability of a person who does not have the disease testing positive.

    Likelihood Ratio
    " Here "T+" or "T" denote that the result of the test is positive or negative, respectively. Likewise, "D+" or "D" denote that the disease is present or absent, respectively. So "true positives" are those that test positive (T+) and have the disease (D+), and "false positives" are those that test positive (T+) but do not have the disease (D).

    1 - sensitivity LR specificity

    LR

    Pr(T D) Pr(T D)

    or "the probability of a person who has the disease testing negative divided by the probability of a person who does not have the disease testing negative."

    example
    LR is the increase in odds of disease after a positive test The likelihood ratio can be used to take any prior(pre-test) probability and convert it to a post-test probability. The post-test or posterior probability is the probability that a patient has the disease after a positive test.

    Diagnostic test
    Disease
    Present
    Positive

    Absent

    PV

    a ab
    d cd

    Test
    Negative
    Se = Sensitivity; Sp = Specificity P = Prevalence; PV = Predictive value; LR = Likelihood ratio, LR+ same as Se/(1-Sp) LR - same as (1-Se)/Sp

    c
    a Se ac

    d
    Sp d bd

    PV

    a LR a c b bd

    c LR a c d bd

    ac p abcd

    Pathology
    present absent Total + positive Liver scan - negative Total 231 27 258 32 54 86 263 81 344

    a sensitivity ac LR 1 - specificity 1 - d bd a 231 258 ac b 32 bd 86 .895 2.406 .372

    It is the increase in odds of disease after a positive test


    Pathology present absent Total

    + positive Liver scan - negative


    Total

    231 27
    258

    32 54
    86

    263 81
    344

    Pathology

    present absent Total + positive


    Liver scan - negative Total 231 a 27 c a+c 258 32 b

    54 d

    a+b 263 c+d 81

    b+d a+b+c+d 86 344

    ac Pr(D) a b c d ODDsprior bd Pr(D) ab c d ac bd 258 344 3 86 344

    Post test probability


    After a positive diagnostic test, the odds of disease are referred to as the post-test or posterior odds. ODDS posterior For a 2 X 2 table, it is a matter of simple algebra to show that ODDSposterior = LR+ X ODDSprior

    Pathology

    present absent Total + positive


    Liver scan - negative Total 231 a 27 c a+c 258
    P(D T ) P(D T )

    32 b

    54 d

    a+b 263 c+d 81

    b+d a+b+c+d 86 344

    ODDsposterior

    a/(a b) a/b b/(a b) 231/32 7.218

    Pathology

    present absent Total + positive


    Liver scan - negative Total 231 a 27 c a+c 258
    a/a c a c X b/b d b d a(b d) a c a X b(a c) b d b

    32 b

    54 d

    a+b 263 c+d 81

    b+d a+b+c+d 86 344

    ODDsposterior LR X ODDSprior

    ODDsposterior LR X ODDSprior 2.406 X 3 7.218

    The likelihood ratio can be used to take any prior(pre-test) probability and convert it to a post-test probability. This allows you to use the results from a diagnostic test and apply them to a population with a different prevalence.

    The odds can be changed back to probabilities by the simple equation

    ODDS P 1 ODDS
    The post-test or posterior probability is the probability that a patient has the disease after a positive test.

    Pathology present + positive Liver scan - negative Total absent a c Total b d a+b 263

    231 27

    32 54

    81c+d
    a+b+c+d 344

    a+c 258

    86b+d

    Disease
    Present Positive Absent

    Test

    Negative

    a c
    Se a ac

    b d
    Sp d bd

    PV
    PV

    a ab
    d cd

    a LR a c b bd c LR a c d bd

    ac p ab c d

    a 231 Sensitivity .895 a c 258

    d 54 Specificity .627 c d 86
    231 sensitivity 258 2.406 LR 32 1 - specificity 86

    Pr(D) 344 3 ODDsprior Pr(D) 86 344

    258

    ODDsposterior LR X ODDSprior 2.406 X 3 7.218

    Pposterior

    ODDSposterior 1 ODDSposterior

    7.218 0 : 878 1 7.218


    The likelihood ratio can be used to take any prior (pre-test) probability and convert it to a post-test probability.
    This allows you to use the results from a diagnostic test and apply them to a population with a different prevalence.

    Correspondingly, there is a LR negative

    1 sensitivity LR specificity
    This tells you the decrease in the odds of having disease if you have a negative test

    THANK YOU

    You might also like