Tips for learners of evidence-based medicine: 3. Measures of observer variability (kappa statistic)

McGinn, Thomas; Wyer, Peter C.; Newman, Thomas B.; Keitz, Sheri A.; Leipzig, Rosanne M.; for, Gordon Guyatt

doi:10.1503/cmaj.1031981

Cited by 433 publications

(315 citation statements)

References 11 publications

Supporting

Mentioning

310

Contrasting

Order By: Relevance

“…The Cohen's value was used as a measurement of the level of agreement beyond chance between the diagnoses made by physical examination and angiography (9,10). The details of the qualitative classification of values as degree of agreement beyond chance can be appreciated elsewhere (9,10).…”

Section: Statistical Analysesmentioning

confidence: 99%

See 1 more Smart Citation

Accuracy of Physical Examination in the Detection of Arteriovenous Fistula Stenosis

Asif

León

Orozco-Vargas

et al. 2007

Clinical Journal of the American Society of Nephrology

126

View full text Add to dashboard Cite

Background and objectives: Physical examination has been highlighted to detect vascular access stenosis; however, its accuracy in the identification of stenoses when compared with the gold standard (angiography) has not been validated in a systematic manner.Design, setting, participants, & measurements: A prospective study was conducted of 142 consecutive patients who were referred for an arteriovenous fistula dysfunction to examine the accuracy of physical examination in the detection of stenotic lesions when compared with angiography. The findings of a preprocedure physical examination and diagnosis were recorded and secured in a sealed envelope. Angiography from the feeding artery to the right atrium was then performed. The images were reviewed by an independent interventionalist who had expertise in endovascular dialysis access procedures and was blinded to the physical examination, and the diagnosis was rendered. Cohen's was used as a measurement of the level of agreement beyond chance between the diagnosis made by physical examination and angiography.Results: There was strong agreement between physical examination and angiography in the diagnosis of outflow (agreement 89.4%, ‫؍‬ 0.78) and inflow stenosis (agreement 79.6%, ‫؍‬ 0.55). The sensitivity and specificity for the outflow and inflow stenosis were 92 and 86% and 85 and 71%, respectively. There was strong agreement beyond chance regarding the diagnosis of coexisting inflow-outflow lesions between physical examination and angiography (agreement 79%, ‫؍‬ 0.54).Conclusions: The findings of this study demonstrate that physical examination can accurately detect and localize stenoses in a great majority of arteriovenous fistulas.

show abstract

Section: Statistical Analysesmentioning

confidence: 99%

“…values between 0.4 and 0.6 denote a moderate agreement. Finally, values Ͼ0.6 denote a substantial agreement beyond chance (9). The sensitivity, specificity, positive predictive value, and negative predictive value of the physical examination in the diagnosis of AVF stenosis were also calculated.…”

Section: Statistical Analysesmentioning

confidence: 99%

Accuracy of Physical Examination in the Detection of Arteriovenous Fistula Stenosis

Asif

León

Orozco-Vargas

et al. 2007

Clinical Journal of the American Society of Nephrology

126

View full text Add to dashboard Cite

show abstract

“…The kappa index analysis evaluated the reproducibility by the degree of agreement between the results of the two observations, taking into account the proportion of observed in relation to the expected agreement. The identified kappa index of 0.96 is regarded as almost perfect agreement between both tests (McGinn et al, 2004).…”

Section: Discussionmentioning

confidence: 95%

ELISA r-p24: optimization and validation of an enzyme immunoassay for the diagnosis of Feline Immunodeficiency Virus infections

Sidoni¹,

Nascimento²,

Miguez³

et al. 2017

BJVM

View full text Add to dashboard Cite

“…While often used to measure classification performance, P o does not take into account the classification agreement that might be due to chance, [30]. A more conservative classification performance measure is the κ score [31,32], a chance-corrected measure of agreement between the desired and predicted class assignments, κ = (P o -P r )/(1 -P r ). If the classification agreement is due strictly to chance, κ = 0.…”

Section: Measuring Performancementioning

confidence: 99%

Mapping Software Metrics to Module Complexity: A Pattern Classification Approach

Pizzi

2011

JSEA

View full text Add to dashboard Cite

A desirable software engineering goal is the prediction of software module complexity (a qualitative concept) using automatically generated software metrics (quantitative measurements). This goal may be couched in the language of pattern classification; namely, given a set of metrics (a pattern) for a software module, predict the class (level of complexity) to which the module belongs. To find this mapping from metrics to complexity, we present a classification strategy, stochastic metric selection, to determine the subset of software metrics that yields the greatest predictive power with respect to module complexity. We demonstrate the effectiveness of this strategy by empirically evaluating it using a publicly available dataset of metrics compiled from a medical imaging system and comparing the prediction results against several classification system benchmarks.

show abstract

Tips for learners of evidence-based medicine: 3. Measures of observer variability (kappa statistic)

Cited by 433 publications

References 11 publications

Accuracy of Physical Examination in the Detection of Arteriovenous Fistula Stenosis

Accuracy of Physical Examination in the Detection of Arteriovenous Fistula Stenosis

ELISA r-p24: optimization and validation of an enzyme immunoassay for the diagnosis of Feline Immunodeficiency Virus infections

Mapping Software Metrics to Module Complexity: A Pattern Classification Approach

Contact Info

Product

Resources

About