Training sample selection: Impact on screening automation in diagnostic test accuracy reviews.
Ontology highlight
ABSTRACT:
SUBMITTER: van Altena AJ
PROVIDER: S-EPMC9292892 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundThe large and increasing number of new studies published each year is making literature identification in systematic reviews ever more time-consuming and costly. Technological assistance has been suggested as an alternative to the conventional, manual study identification to mitigate the cost, but previous literature has mainly evaluated methods in terms of recall (search sensitivity) and workload reduction. There is a need to also evaluate whether screening prioritization methods leads to the same results and conclusions as exhaustive manual screening. In this study, we examined the impact of one screening prioritization method based on active learning on sensitivity and specificity estimates in systematic reviews of diagnostic test accuracy.MethodsWe simulated the screening process in 48 Cochrane reviews of diagnostic test accuracy and re-run 400 meta-analyses based on a least 3 studies. We compared screening prioritization (with technological assistance) and screening in randomized order (standard practice without technology assistance). We examined if the screening could have been stopped before identifying all relevant studies while still producing reliable summary estimates. For all meta-analyses, we also examined the relationship between the number of relevant studies and the reliability of the final estimates.ResultsThe main meta-analysis in each systematic review could have been performed after screening an average of 30% of the candidate articles (range 0.07 to 100%). No systematic review would have required screening more than 2308 studies, whereas manual screening would have required screening up to 43,363 studies. Despite an average 70% recall, the estimation error would have been 1.3% on average, compared to an average 2% estimation error expected when replicating summary estimate calculations.ConclusionScreening prioritization coupled with stopping criteria in diagnostic test accuracy reviews can reliably detect when the screening process has identified a sufficient number of studies to perform the main meta-analysis with an accuracy within pre-specified tolerance limits. However, many of the systematic reviews did not identify a sufficient number of studies that the meta-analyses were accurate within a 2% limit even with exhaustive manual screening, i.e., using current practice.
| S-EPMC6819363 | biostudies-literature
Project description:In 1996, shortly after the founding of The Cochrane Collaboration, leading figures in test evaluation research established a Methods Group to focus on the relatively new and rapidly evolving methods for the systematic review of studies of diagnostic tests. Seven years later, the Collaboration decided it was time to develop a publication format and methodology for Diagnostic Test Accuracy (DTA) reviews, as well as the software needed to implement these reviews in The Cochrane Library. A meeting hosted by the German Cochrane Centre in 2004 brought together key methodologists in the area, many of whom became closely involved in the subsequent development of the methodological framework for DTA reviews. DTA reviews first appeared in The Cochrane Library in 2008 and are now an integral part of the work of the Collaboration.
| S-EPMC3851548 | biostudies-literature
Project description:BackgroundSystematic review is an indispensable tool for optimal evidence collection and evaluation in evidence-based medicine. However, the explosive increase of the original literatures makes it difficult to accomplish critical appraisal and regular update. Artificial intelligence (AI) algorithms have been applied to automate the literature screening procedure in medical systematic reviews. In these studies, different algorithms were used and results with great variance were reported. It is therefore imperative to systematically review and analyse the developed automatic methods for literature screening and their effectiveness reported in current studies.MethodsAn electronic search will be conducted using PubMed, Embase, ACM Digital Library, and IEEE Xplore Digital Library databases, as well as literatures found through supplementary search in Google scholar, on automatic methods for literature screening in systematic reviews. Two reviewers will independently conduct the primary screening of the articles and data extraction, in which nonconformities will be solved by discussion with a methodologist. Data will be extracted from eligible studies, including the basic characteristics of study, the information of training set and validation set, and the function and performance of AI algorithms, and summarised in a table. The risk of bias and applicability of the eligible studies will be assessed by the two reviewers independently based on Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). Quantitative analyses, if appropriate, will also be performed.DiscussionAutomating systematic review process is of great help in reducing workload in evidence-based practice. Results from this systematic review will provide essential summary of the current development of AI algorithms for automatic literature screening in medical evidence synthesis and help to inspire further studies in this field.Systematic review registrationPROSPERO CRD42020170815 (28 April 2020).
| S-EPMC8760775 | biostudies-literature
Project description:ObjectiveTo evaluate the performance of the automated abstract screening tool Rayyan.MethodsThe records obtained from the search for three systematic reviews were manually screened in four stages. At the end of each stage, Rayyan was used to predict the eligibility score for the remaining records. At two different thresholds (≤2.5 and < 2.5 for exclusion of a record) Rayyan-generated ratings were compared with the decisions made by human reviewers in the manual screening process and the tool's accuracy metrics were calculated.ResultsTwo thousand fifty-four records were screened manually, of which 379 were judged to be eligible for full-text assessment, and 112 were eventually included in the final review. For finding records eligible for full-text assessment, at the threshold of < 2.5 for exclusion, Rayyan managed to achieve sensitivity values of 97-99% with specificity values of 19-58%, while at the threshold of ≤2.5 for exclusion it had a specificity of 100% with sensitivity values of 1-29%. For the task of finding eligible reports for inclusion in the final review, almost similar results were obtained.DiscussionAt the threshold of < 2.5 for exclusion, Rayyan managed to be a reliable tool for excluding ineligible records, but it was not much reliable for finding eligible records. We emphasize that this study was conducted on diagnostic test accuracy reviews, which are more difficult to screen due to inconsistent terminology.
| S-EPMC9161508 | biostudies-literature
Project description:ObjectivesTo compare the accuracy of trained level 1 diabetic retinopathy (DR) graders (nurses, endocrinologists and one general practitioner), level 2 graders (midlevel ophthalmologists) and level 3 graders (senior ophthalmologists) in Vietnam against a reference standard from the UK and assess the impact of supplementary targeted grader training.DesignDiagnostic test accuracy study.SettingSecondary care hospitals in Southern Vietnam.ParticipantsDR training was delivered to Vietnamese graders in February 2018 by National Health Service (NHS) UK graders. Two-field retinal images (412 patient images) were graded by 14 trained graders in Vietnam between August and October 2018 and then regraded retrospectively by an NHS-certified reference standard UK optometrist (phase I). Further DR training based on phase I results was delivered to graders in November 2019. After training, a randomised subset of images from January to October 2020 (115 patient images) was graded by six of the original cohort (phase II). The reference grader regraded all images from phase I and II retrospectively in masked fashion.Primary and secondary outcome measuresSensitivity was calculated at the two different time points, and χ2 was used to test significance.ResultsIn phase I, the sensitivity for detecting any DR for all grader groups in Vietnam was low (41.8-42.2%) and improved in phase II after additional training was delivered (51.3-87.2%). The greatest improvement was seen among level 1 graders (p<0.001), and the lowest improvement was observed among level 3 graders (p=0.326). There was a statistically significant improvement in sensitivity for detecting referable DR and referable diabetic macular oedema between all grader levels. The post-training values ranged from 40.0 to 61.5% (including ungradable images) and 55.6%-90.0% (excluding ungradable images).ConclusionsThis study demonstrates that targeted training interventions can improve accuracy of DR grading. These findings have important implications for improving service delivery in DR screening programmes in low-resource settings.
| S-EPMC9472142 | biostudies-literature
Project description:ImportanceSystematic reviews of medical imaging diagnostic test accuracy (DTA) studies are affected by between-study heterogeneity due to a range of factors. Failure to appropriately assess the extent and causes of heterogeneity compromises the interpretability of systematic review findings.ObjectiveTo assess how heterogeneity has been examined in medical imaging DTA studies.Evidence reviewThe PubMed database was searched for systematic reviews of medical imaging DTA studies that performed a meta-analysis. The search was limited to the 40 journals with highest impact factor in the radiology, nuclear medicine, and medical imaging category in the InCites Journal Citation Reports of 2021 to reach a sample size of 200 to 300 included studies. Descriptive analysis was performed to characterize the imaging modality, target condition, type of meta-analysis model used, strategies for evaluating heterogeneity, and sources of heterogeneity identified. Multivariable logistic regression was performed to assess whether any factors were associated with at least 1 source of heterogeneity being identified in the included meta-analyses. Methodological quality evaluation was not performed. Data analysis occurred from October to December 2022.FindingsA total of 242 meta-analyses involving a median (range) of 987 (119-441 510) patients across a diverse range of disease categories and imaging modalities were included. The extent of heterogeneity was adequately described (ie, whether it was absent, low, moderate, or high) in 220 studies (91%) and was most commonly assessed using the I2 statistic (185 studies [76%]) and forest plots (181 studies [75%]). Heterogeneity was rated as moderate to high in 191 studies (79%). Of all included meta-analyses, 122 (50%) performed subgroup analysis and 87 (36%) performed meta-regression. Of the 242 studies assessed, 189 (78%) included 10 or more primary studies. Of these 189 studies, 60 (32%) did not perform meta-regression or subgroup analysis. Reasons for being unable to investigate sources of heterogeneity included inadequate reporting of primary study characteristics and a low number of included primary studies. Use of meta-regression was associated with identification of at least 1 source of variability (odds ratio, 1.90; 95% CI, 1.11-3.23; P = .02).Conclusions and relevanceIn this systematic review of assessment of heterogeneity in medical imaging DTA meta-analyses, most meta-analyses were impacted by a moderate to high level of heterogeneity, presenting interpretive challenges. These findings suggest that, despite the development and availability of more rigorous statistical models, heterogeneity appeared to be incomplete, inconsistently evaluated, or methodologically questionable in many cases, which lessened the interpretability of the analyses performed; comprehensive heterogeneity assessment should be addressed at the author level by improving personal familiarity with appropriate statistical methodology for assessing heterogeneity and involving biostatisticians and epidemiologists in study design, as well as at the editorial level, by mandating adherence to methodologic standards in primary DTA studies and DTA meta-analyses.
| S-EPMC10905313 | biostudies-literature
Project description:IntroductionSystemic lupus erythematosus (SLE) is a chronic autoimmune disease with multiorgan inflammatory involvement and a mortality rate that is 2.6-fold higher than individuals of the same age and sex in the general population. Approximately 50% of patients with SLE develop renal impairment (lupus nephritis). Delayed diagnosis of lupus nephritis is associated with a higher risk of progression to end-stage renal disease, the need for replacement therapy, and mortality. The initial clinical manifestations of lupus nephritis are often discrete or absent and are usually detected through complementary tests. Although widely used in clinical practice, their accuracy is limited. A great scientific effort has been exerted towards searching for new, more sensitive, and specific biomarkers in recent years. Some systematic reviews have individually evaluated new serum and urinary biomarkers tested in patients with lupus nephritis. This overview aimed to summarize systematic reviews on the accuracy of novel serum and urinary biomarkers for diagnosing lupus nephritis in patients with SLE, discussing how our results can guide the clinical management of the disease and the direction of research in this area.MethodsThe research question is "What is the accuracy of the new serum and urinary biomarkers studied for the diagnosis of LN in patients with SLE?". We searched for systematic reviews of observational studies evaluating the diagnostic accuracy of new serum or urinary biomarkers of lupus nephritis. The following databases were included: PubMed, EMBASE, BIREME/LILACS, Scopus, Web of Science, and Cochrane, including gray literature found via Google Scholar and PROQUEST. Two authors assessed the reviews for inclusion, data extraction, and assessment of the risk of bias (ROBIS tool).ResultsTen SRs on the diagnostic accuracy of new serum and urinary BMs in LN were selected. The SRs evaluated 7 distinct BMs: (a) antibodies (anti-Sm, anti-RNP, and anti-C1q), (b) cytokines (TWEAK and MCP-1), (c) a chemokine (IP-10), and (d) an acute phase glycoprotein (NGAL), in a total of 20 review arms (9 that analyzed serum BMs, and 12 that analyzed BMs in urine). The population evaluated in the primary studies was predominantly adults. Two SRs included strictly adults, 5 reviews also included studies in the paediatric population, and 4 did not report the age groups. The results of the evaluation with the ROBIS tool showed that most of the reviews had a low overall risk of bias.ConclusionsThere are 10 SRs of evidence relating to the diagnostic accuracy of serum and urinary biomarkers for lupus nephritis. Among the BMs evaluated, anti-C1q, urinary MCP-1, TWEAK, and NGAL stood out, highlighting the need for additional research, especially on LN diagnostic panels, and attempting to address methodological issues within diagnostic accuracy research. This would allow for a better understanding of their usefulness and possibly validate their clinical use in the future.RegistrationThis project is registered on the International Prospective Registry of Systematic Reviews (PROSPERO) database (CRD42020196693).
| S-EPMC9550089 | biostudies-literature
Project description:The Spurling test, although a highly specific provocative test of the cervical spine in cervical radiculopathy (CR), has low to moderate sensitivity. Thus, we introduced the neck tornado test (NTT) to examine the neck and the cervical spine in CR.The aim of this study was to introduce a new provocative test, the NTT, and compare the diagnostic accuracy with a widely accepted provocative test, the Spurling test.Retrospective study.Medical records of 135 subjects with neck pain (CR, n = 67; without CR, n = 68) who had undergone cervical spine magnetic resonance imaging and been referred to the pain clinic between September 2014 and August 2015 were reviewed. Both the Spurling test and NTT were performed in all patients by expert examiners. Sensitivity, specificity, and accuracy were compared for both the Spurling test and the NTT.The sensitivity of the Spurling test and the NTT was 55.22% and 85.07% (P < 0.0001); specificity, 98.53% and 86.76% (P = 0.0026); accuracy, 77.04% and 85.93% (P = 0.0423), respectively.The NTT is more sensitive with superior diagnostic accuracy for CR diagnosed by magnetic resonance imaging than the Spurling test.
| S-EPMC5562117 | biostudies-other
Project description:The standard item response theory (IRT) model assumption of a single homogenous population may be violated in real data. Mixture extensions of IRT models have been proposed to account for latent heterogeneous populations, but these models are not designed to handle multilevel data structures. Ignoring the multilevel structure is problematic as it results in lower-level units aggregated with higher-level units and yields less accurate results, because of dependencies in the data. Multilevel data structures cause such dependencies between levels but can be modeled in a straightforward way in multilevel mixture IRT models. An important step in the use of multilevel mixture IRT models is the fit of the model to the data. This fit is often determined based on relative fit indices. Previous research on mixture IRT models has shown that performances of these indices and classification accuracy of these models can be affected by several factors including percentage of class-variant items, number of items, magnitude and size of clusters, and mixing proportions of latent classes. As yet, no studies appear to have been reported examining these issues for multilevel extensions of mixture IRT models. The current study aims to investigate the effects of several features of the data on the accuracy of model selection and parameter recovery. Results are reported on a simulation study designed to examine the following features of the data: percentages of class-variant items (30, 60, and 90%), numbers of latent classes in the data (with from 1 to 3 latent classes at level 1 and 1 and 2 latent classes at level 2), numbers of items (10, 30, and 50), numbers of clusters (50 and 100), cluster size (10 and 50), and mixing proportions [equal (0.5 and 0.5) vs. non-equal (0.25 and 0.75)]. Simulation results indicated that multilevel mixture IRT models resulted in less accurate estimates when the number of clusters and the cluster size were small. In addition, mean Root mean square error (RMSE) values increased as the percentage of class-variant items increased and parameters were recovered more accurately under the 30% class-variant item conditions. Mixing proportion type (i.e., equal vs. unequal latent class sizes) and numbers of items (10, 30, and 50), however, did not show any clear pattern. Sample size dependent fit indices BIC, CAIC, and SABIC performed poorly for the smaller level-1 sample size. For the remaining conditions, the SABIC index performed better than other fit indices.
| S-EPMC7033749 | biostudies-literature
Project description:Objective: The diagnostic efficiency of the quantitative fecal immunochemical test (qFIT) has large variations in colorectal cancer (CRC) screening. We aimed to explore whether the practical sample collection operant training could improve the diagnostic accuracy of the qFIT in CRC screening. Methods: Moderate-/high-risk individuals aged 50-75 years old were invited to participate in a prospective observational study between July 2020 and March 2021. Participants took a qFIT sample without fecal sample collection operant training in advance and then completed another qFIT sample after the operant training. The primary outcome was the sensitivity and specificity of the qFITs for CRC and advanced colorectal neoplasia (ACRN). The secondary outcome was the difference in the area under the curves (AUCs) and the concentrations of the fecal hemoglobin (Hb) between the qFIT without and after the operant training. Results: Out of 913 patients, 81 (8.9%) patients had ACRN, including 25 (2.7%) patients with CRC. For CRC, the sensitivities of the qFIT without and after the operant training at 10 μg/g were 80.4 and 100.0%, respectively, and the specificities were 90.1 and 88.4%, respectively. For ACRN, the sensitivities were 49.4 and 69.1% and the specificities were 91.7 and 91.3%, respectively. The AUC of the qFIT after the operant training was significantly higher than that without the operant training for CRC (p = 0.027) and ACRN (p = 0.001). After the operant training, the concentration of the fecal Hb was significantly higher than that without the operant training (p = 0.009) for ACRN, but there was no significant difference for CRC (p = 0.367). Conclusion: Practical sample collection operant training improves the diagnostic accuracy of the qFIT, which increases the detection of the low concentrations of fecal Hb. Improving the quality of the sample collection could contribute to the diagnostic efficiency of the qFIT in CRC screening.
| S-EPMC8575757 | biostudies-literature