The interpretation of diagnostic tests

Abstract

Laboratory diagnostic tests are central in the practice of modern medicine. Common uses include screening a specific population for evidence of disease and confirming or ruling out a tentative diagnosis in an individual patient. The interpretation of a diagnostic test result depends on both the ability of the test to distinguish diseased from nondiseased subjects and the particular characteristics of the patient and setting in which the test is being used. This article reviews statistical methodology for assessing laboratory diagnostic test accuracy and interpreting individual test results, with an emphasis on diagnostic tests that yield a continuous measurement. The article begins with a summary of basic concepts and terminology, then briefly discusses study design and reviews methods for assessing the accuracy of a single diagnostic test, comparing the accuracy of two or more diagnostic tests and interpreting individual test results.

Screening of Mental Disorders Among Clients with Addictions. The Need for Population-Specific Validation

“…The higher the sensitivity, the larger the number of false positives; and the higher the specificity, the larger the number of false negatives. The importance or clinical significance of those differences depends on the context of use of the screening test (Shapiro 1999). If the cost (or risk) of the next step for a client who scores positive in the screening test is high, the acceptability of false positives should be low; if the cost (or risk) of missing a true case is high, then the acceptability of false negatives should be low.…”

“…The area under the curve (AUC) was determined as a summary of the test's accuracy and can be understood as the probability that a randomly selected diseased individual has a test result that indicates greater suspicion than a randomly chosen non-diseased individual (Shapiro 1999). The ROC is a plot of sensitivity (hits) by 1-specificity (false alarms) across all possible cutoffs and is very informative on choosing the cutoff score for a screening test.…”

Chromogranin A as circulating marker for diagnosis and management of neuroendocrine neoplasms: more flaws than fame

“…The most critical discrepancies were (a) the composition of the case groups, with the strongest difference being represented by the fact that some studies included NEN from all sites (Bernini et al 2001, Donica et al 2010, Molina et al 2011, Korse et al 2012, Marotta et al 2012, Tohmola et al 2014, whereas some others tried to analyze more homogeneous set of patients, mainly selecting gastroenteropancreatic tumors (Tomassetti et al 2001a, Peracchi et al 2003, Nehar et al 2004, Zatelli et al 2007, Belli et al 2009, Modlin et al 2013 (Table 1); (b) the composition of the control groups: although the majority of studies used healthy subjects as controls (Bernini et al 2001, Tomassetti et al 2001b, Peracchi et al 2003, Nehar et al 2004, Campana et al 2007, Zatelli et al 2007, Belli et al 2009, Donica et al 2010, Molina et al 2011, Korse et al 2012, which represents the best approach to assess the diagnostic performance of a marker (Shapiro 1999), some researchers determined the metrics of circulating CgA by comparing NEN with non-NEN tumors (Nobels et al 1998, Panzuto et al 2004 or active versus diseasefree NEN (Bajetta et al 1999, Panzuto et al 2004; (c) the consideration of interfering factors: some authors tried to clean up the control group from those conditions with known effect on CgA levels, thus obtaining a more pristine evaluation of marker specificity (Bernini et al 2001, Tomassetti et al 2001b, Nehar et al 2004, Campana et al 2007…”

Hyperosmolar conjunctival provocation for the evaluation of nonspecific hyperreactivity in healthy patients and patients with allergy

“…A receiver operating characteristic (ROC) curve (MedCalc 7.30, MedCalc Software, Mariakerke, Belgium) was generated to identify the best cutoff value to differentiate between subjects with ocular discomfort from those without. 28 The Spearman r test was used to relate the ocular discomfort score to the provoking dose (SPSS Ver 8, Chicago, Ill). One-way ANOVA test was used to compare the results of the rechallenge to the results of the previous provocation test.…”