Table 0 - uploaded by Chunxiao Zhou

Content may be subject to copyright.

Source publication

Evaluating the accuracy (ie, estimating the sensitivity and specificity) of new diagnostic tests without the presence of a gold standard is of practical meaning and has been the subject of intensive study for several decades. Existing methods use 2 or more diagnostic tests under several basic assumptions and then estimate the accuracy parameters vi...

## Similar publications

Purposes: The purposes of this review were to compare sensitivity and specificity of the new generation tympanic thermometry under different cutoffs and to give the optimal cutoff. Methods: Articles were derived from a systematic search in PubMed, Web of science, and Embase, and were assessed for internal validity by QUADAS-Ⅱ. The figure of risk of...

## Citations

... Since the true disease status is likely unknown, indirect methods are often used for the evaluation of diagnostic sensitivity and specificity. Methods and problems regarding the assumptions of such approaches have been widely discussed [10][11][12][13][14][15][16][17][18][19][20]. ...

Efficacy estimations in clinical trials are based on case definitions. Commonly, they are a more or less complex set of conditions that have to be fulfilled in order to define a clinical case. In the simplest variant, such a case is identical with a single positive diagnostic test result. Frequently, however, case definitions are more complex. Further, their conditions often ignore the inherent logical structure of symptoms and disease: A symptom or a set of symptoms may be necessary but not sufficient for the unambiguous identification of a case. After describing the structure of case definitions and its impact on efficacy estimations, we exemplify this impact using data from two clinical trials dealing with the effectiveness of the vaginal application of tenofovir gel for the prevention of HIV infections and with the therapeutic effects of fecal transplantation on recurrent Clostridium difficile infections. We demonstrate that the diagnostic performance of case definitions affects efficacy estimations for interventions in clinical trials. The potential risk of bias and uncertainty is high, irrespective of the complexity of the case definition. Accordingly, case definitions in clinical trials should focus on specificity in order to avoid the risk of bias.

... Combining the test results of the two diagnostic tests applied in the Hui & Walter approach on the two assessed populations allows estimation of the sensitivity and specificity of each diagnostic test as well as of the prevalence in each population. For the common case that conditional independence cannot be assumed, Lu and colleagues recently presented an approach with reduced bias (Lu et al., 2018). ...

Diagnostic testing in the infectious disease laboratory facilitates decision-making by physicians at the bedside as well as epidemiological assessments and surveillance at study level. Problems may arise if test results are uncritically considered as being the same as the unknown true value. To allow a better understanding, the influence of external factors on the interpretation of test results is introduced with the example of prevalence, followed by the presentation of strengths and weaknesses of important techniques in the infectious disease laboratory like microscopy, cultural diagnostics, serology, mass spectrometry, nucleic acid amplification and hypothesis-free metagenomic sequencing with focus on basic, high-technology and potential future approaches. Special problems like multiplex testing as well as uncertainty of test evaluations, if no gold standard is available, are also stressed with a final glimpse on emerging future technologies for the infectious disease laboratory. In the conclusions, suitability for point-of-care-testing and field laboratory applications is summarized. The aim is to illustrate the limitations of diagnostic accuracy to both clinicians and study planners and to stress the importance of close cooperation with experts in laboratory disciplines so as to avoid potentially critical misunderstandings due to inappropriate interpretation of diagnostic test results.

... Thus, in order to use LCA in situations where violations of standard assumptions are anticipated, re searchers have developed a variety of alternative approaches such as introducing dependence structure into LCA (e.g. Jones et al. 2010), modifying comparisons to remove the assumptions entirely (Lu et al. 2018), integrating copula functions (Tovar & Achcar 2012), and/or utilizing Bayesian approaches to incorporate a priori knowledge (e.g. Fablet et al. 2010) (reviewed by Collins & Huynh 2014). ...

Latent class analysis (LCA) is a common method to evaluate the diagnostic sensitivity (DSe) and specificity (DSp) for pathogen detection assays in the absence of a perfect reference standard. Here we used LCA to evaluate the diagnostic accuracy of 3 tests for the detection of Mikrocytos mackini in Pacific oysters Crassostrea gigas : conventional polymerase chain reaction (PCR), real-time quantitative PCR (qPCR), and histopathology. A total of 802 Pacific oysters collected over 12 sampling events from 9 locations were assessed. Preliminary investigations indicated that standard LCA assumptions of test independence and constant detection accuracy across locations were likely unrealistic. This was mitigated by restructuring the LCA in a Bayesian framework to include test-derived knowledge about pathogen prevalence and load for categorizing populations into 2 classes of infection severity (low or high) and assessing separate DSe and DSp estimates for each class. Median DSp estimates were high (>96%) for all 3 tests in both population classes. DSe estimates varied between tests and population classes but were consistently highest for qPCR (87-99%) and lowest for histopathology (21-51%). Acknowledging that detection of M. mackini may be fitted to multiple diagnostic and management purposes, qPCR had the highest DSe while maintaining similar DSp to both conventional PCR and histopathology and thus is generally well-suited to most applications.

This article considers how to estimate the accuracy of a diagnostic test when there are repeated observations, but without the availability of a gold standard or reference test. We identify conditions under which the structure of the observed data is rich enough to provide sufficient degrees of freedom, such that a suitable latent class model can be fitted with identifiable accuracy parameters. We show that a Rule of Three applies, specifying that accuracy can be evaluated as long as there are at least three observations per individual with the given test. This rule also applies if the three observations arise from combinations of different test methods, or from a sequential design in which individuals are tested for a maximum number of times with the same test but stopping if a positive (or negative) result occurs. The rule pertains to tests having an arbitrary number of response categories. Accuracy is evaluated by parameters reflecting rates of misclassification among the response categories, and the model also provides estimates of the underlying distribution of the true disease state. These ideas are illustrated by data from two medical studies. Issues discussed include the advantages and disadvantages of analyzing the response variable as binary or multinomial, as well as the feasibility of testing goodness of fit when the model incorporates a large number of parameters. Comparisons are possible between models that do or do not assume equal accuracy rates for the observations, and between models where certain misclassification parameters are or are not assumed to be zero.