Estimating Diagnostic Accuracy from Multiple Conflicting Reports

Littenberg, Benjamin; Moses, Lincoln E.

doi:10.1177/0272989x9301300408

Cited by 405 publications

(286 citation statements)

References 10 publications

Supporting

Mentioning

284

Contrasting

Unclassified

Order By: Relevance

“…Given that in diagnostic test studies it is very common that the variability of results does not result merely from chance, since variability may be explicitly or implicitly caused by variation of the cut-off point, the variability estimates provided by the random effects model are particularly important 10 . Using random effects methods more frequently, the forms of metaanalysis of studies on diagnostic tests or prognostic factors are shown in Table 3.…”

Section: Calculate the Results By Means Of Metaanalysis Estimating Dmentioning

confidence: 99%

“…Meta-analyses of studies on prognostic factors or diagnostic tests, in turn, face different challenges, such as different cut-off points for the positive or negative result of a test, or assessment of tests that were performed in prospective studies for the analysis of therapeutic interventions. In the 1990's, new statistical techniques of combination of studies on diagnostic tests were developed [9][10][11] . Since 1994, when a guideline for meta-analysis of studies on diagnostic tests 12 was published, several different publications with criticisms and propositions on specific aspects of each stage of the process came up.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Revisão sistemática e meta-análise de estudos de diagnóstico e prognóstico: um tutorial

Sousa¹,

Ribeiro²

2009

Arq. Bras. Cardiol.

View full text Add to dashboard Cite

SummarySystematic reviews with meta-analysis of studies on diagnostic tests or prognostic factors are research tools that are still being developed. The objective of the present paper is to describe the methodology of systematic review and meta-analysis of this type of studies, step by step. A literature review on the subject was made, the recommendations were compiled and the paper was organized in: a) Introduction, b) Details on the eight steps to be followed, c) Form of publication of a systematic review with metaanalysis, andThe systematic review methods were thoroughly described with a critical analysis of the methods of statistical compilation of results, with emphasis on the utilization of the Summary Receiver Operator Characteristic curve. References for the details of each statistical technique used were provided in the meta-analysis. We concluded that systematic reviews with meta-analysis of diagnostic tests or prognostic factors are useful in data compilation of various studies on the same subject, since they reduce biases and increase the statistical power of the primary research.

show abstract

Section: Calculate the Results By Means Of Metaanalysis Estimating Dmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Revisão sistemática e meta-análise de estudos de diagnóstico e prognóstico: um tutorial

Sousa¹,

Ribeiro²

2009

Arq. Bras. Cardiol.

View full text Add to dashboard Cite

show abstract

“…Publication bias was assessed by Begg s and Egger s tests 13 . To avoid undefined values that would have arisen due to zero values, 0.5 was added to any zero cell 14 . Statistical signi cance was set at P 0.05.…”

Section: Discussionmentioning

confidence: 99%

A Comparison of Magnifying Chromoendoscopy Versus Narrow Band Imaging in the Diagnosis of Depth of Invasion for Early Colorectal Cancers

Kobayashi

Kudo

Miyachi

et al. 2011

Showa Univ J Med Sci

View full text Add to dashboard Cite

: Although chromoendoscopy and narrow band imaging NBI are widely used in diagnosing the invasion depth of colorectal cancers, comparative studies of these modalities are lacking. This meta-analysis compared the performance of these two modalities in colorectal cancer diagnosis. MEDLINE, EMBASE, and Cochrane Library were searched for relevant original articles published up to December 20 th , 2010. Major criteria for article inclusion were : i magnifying chromoendoscopy or NBI was used as a diagnostic modality and pit pattern or vascular pattern was used as a diagnostic classi cation ; ii sensitivity and speci city were reported ; iii absolute numbers of true-positive, false-positive, true-negative, and false-negative cases, or their equivalent, were provided ; and iv pathology of biopsy, endoscopy, or surgical treatment was used as the reference standard. Sensitivity and speci city were pooled using a random effects model. Regression analysis was performed to compare the discriminatory power between chromoendoscopy and NBI by including a dummy variable. We made the assumption that a positive regression coef cient implied a better discriminatory power for NBI, and vice versa. Of 1846 screened articles, 16 ful lled all inclusion criteria. Pooled sensitivity for chromoendoscopy and NBI was 0.85 95 CI : 0.82-0.87 and 0.80 0.76-0.85 , respectively, and specificity was 0.98 0.97-0.99 and 0.98 0.97-0.99 , respectively. The regression coef cient for chromoendoscopy versus NBI was 0.02 95 CI : 1.18-1.71 . These results indicate that chromoendoscopy and NBI may have similar power for the diagnostic assessment of colonic neoplasms. However, other factors such as convenience, time, and cost still must be taken into account in making the nal diagnostic choice.

show abstract

“…The summary receiver operating characteristic (SROC) method, introduced by Littenberg and Moses [2,3], has been widely used by authors of published meta-analyses that examine diagnostic test accuracy. However, the SROC method has some inherent limitations that could affect its validity and usefulness.…”

Section: Introductionmentioning

confidence: 99%

“…true positives (TP), false positives (FP), true negatives (TN), and false negatives (FN). The continuity correction method, i.e., adding one half to each count in calculating the true-positive rate and the false-positive rate, introduces non-negligible downward bias to the estimated SROC curve [2,3,4]. An additional problem with the SROC method is that confidence intervals are based on large sample theory approximations and the appropriate sample size for a meta-analysis is the number of studies which may not be large enough for the approximation to be accurate.…”

Section: Introductionmentioning

confidence: 99%

Bayesian meta-analysis of Papanicolaou smear accuracy

Cong

Cox

Cantor

2007

Gynecologic Oncology

View full text Add to dashboard Cite

Objective-To perform a Bayesian analysis of data from a previous meta-analysis of Papanicolaou (Pap) smear accuracy (Fahey et al. Am J Epidemiol 1995; 141:680-689) and compare the results.Methods-We considered two Bayesian models for the same dataset used in the Fahey et al study.Model I was a beta-binomial model which considered the number of true positives and false negatives as independent binomial random variables with probability parameters β (sensitivity) and a (one minus specificity), respectively. We assumed that β and a are independent, each following a beta distribution with exponential priors. Model II considered sensitivity and specificity jointly through a bivariate normal distribution on the logits of the sensitivity and specificity. We performed sensitivity analysis to examine the effect of prior selection on the parameter estimates.Results-We compared the estimates of average sensitivity and specificity from the Bayesian models with those from Fahey et al.'s SROC approach. Model I produced results similar to those of the SROC approach. Model II produced point estimates higher than those of the SROC approach, although the credible intervals overlapped and were wider. Sensitivity analysis showed that the Bayesian models are somewhat sensitive to the variance of the prior distribution, but their point estimates are more robust than those of the SROC approach. Conclusions-TheBayesian approach has advantages over the SROC approach in that it accounts for between-study variation and allows for estimating the sensitivity and specificity for a particular trial, taking into consideration the results of other trials, i.e., "borrowing strength" from other trials.

show abstract

Estimating Diagnostic Accuracy from Multiple Conflicting Reports

Cited by 405 publications

References 10 publications

Revisão sistemática e meta-análise de estudos de diagnóstico e prognóstico: um tutorial

Revisão sistemática e meta-análise de estudos de diagnóstico e prognóstico: um tutorial

A Comparison of Magnifying Chromoendoscopy Versus Narrow Band Imaging in the Diagnosis of Depth of Invasion for Early Colorectal Cancers

Bayesian meta-analysis of Papanicolaou smear accuracy

Contact Info

Product

Resources

About