Dataset Information

Performance and usability of machine learning for screening in systematic reviews: a comparative evaluation of three tools.

ABSTRACT: BACKGROUND:We explored the performance of three machine learning tools designed to facilitate title and abstract screening in systematic reviews (SRs) when used to (a) eliminate irrelevant records (automated simulation) and (b) complement the work of a single reviewer (semi-automated simulation). We evaluated user experiences for each tool. METHODS:We subjected three SRs to two retrospective screening simulations. In each tool (Abstrackr, DistillerSR, RobotAnalyst), we screened a 200-record training set and downloaded the predicted relevance of the remaining records. We calculated the proportion missed and workload and time savings compared to dual independent screening. To test user experiences, eight research staff tried each tool and completed a survey. RESULTS:Using Abstrackr, DistillerSR, and RobotAnalyst, respectively, the median (range) proportion missed was 5 (0 to 28) percent, 97 (96 to 100) percent, and 70 (23 to 100) percent for the automated simulation and 1 (0 to 2) percent, 2 (0 to 7) percent, and 2 (0 to 4) percent for the semi-automated simulation. The median (range) workload savings was 90 (82 to 93) percent, 99 (98 to 99) percent, and 85 (85 to 88) percent for the automated simulation and 40 (32 to 43) percent, 49 (48 to 49) percent, and 35 (34 to 38) percent for the semi-automated simulation. The median (range) time savings was 154 (91 to 183), 185 (95 to 201), and 157 (86 to 172) hours for the automated simulation and 61 (42 to 82), 92 (46 to 100), and 64 (37 to 71) hours for the semi-automated simulation. Abstrackr identified 33-90% of records missed by a single reviewer. RobotAnalyst performed less well and DistillerSR provided no relative advantage. User experiences depended on user friendliness, qualities of the user interface, features and functions, trustworthiness, ease and speed of obtaining predictions, and practicality of the export file(s). CONCLUSIONS:The workload savings afforded in the automated simulation came with increased risk of missing relevant records. Supplementing a single reviewer's decisions with relevance predictions (semi-automated simulation) sometimes reduced the proportion missed, but performance varied by tool and SR. Designing tools based on reviewers' self-identified preferences may improve their compatibility with present workflows. SYSTEMATIC REVIEW REGISTRATION:Not applicable.

SUBMITTER: Gates A

PROVIDER: S-EPMC6857345 | biostudies-literature | 2019 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Performance and usability of machine learning for screening in systematic reviews: a comparative evaluation of three tools.

Gates Allison A Guitard Samantha S Pillay Jennifer J Elliott Sarah A SA Dyson Michele P MP Newton Amanda S AS Hartling Lisa L

Systematic reviews 20191115 1

<h4>Background</h4>We explored the performance of three machine learning tools designed to facilitate title and abstract screening in systematic reviews (SRs) when used to (a) eliminate irrelevant records (automated simulation) and (b) complement the work of a single reviewer (semi-automated simulation). We evaluated user experiences for each tool.<h4>Methods</h4>We subjected three SRs to two retrospective screening simulations. In each tool (Abstrackr, DistillerSR, RobotAnalyst), we screened a ...[more]

PMID: 31727150

Similar Datasets

Project description:BackgroundWithin evidence-based practice (EBP), systematic reviews (SR) are considered the highest level of evidence in that they summarize the best available research and describe the progress in a determined field. Due its methodology, SR require significant time and resources to be performed; they also require repetitive steps that may introduce biases and human errors. Machine learning (ML) algorithms therefore present a promising alternative and a potential game changer to speed up and automate the SR process. This review aims to map the current availability of computational tools that use ML techniques to assist in the performance of SR, and to support authors in the selection of the right software for the performance of evidence synthesis.MethodsThe mapping review was based on comprehensive searches in electronic databases and software repositories to obtain relevant literature and records, followed by screening for eligibility based on titles, abstracts, and full text by two reviewers. The data extraction consisted of listing and extracting the name and basic characteristics of the included tools, for example a tool's applicability to the various SR stages, pricing options, open-source availability, and type of software. These tools were classified and graphically represented to facilitate the description of our findings.ResultsA total of 9653 studies and 585 records were obtained from the structured searches performed on selected bibliometric databases and software repositories respectively. After screening, a total of 119 descriptions from publications and records allowed us to identify 63 tools that assist the SR process using ML techniques.ConclusionsThis review provides a high-quality map of currently available ML software to assist the performance of SR. ML algorithms are arguably one of the best techniques at present for the automation of SR. The most promising tools were easily accessible and included a high number of user-friendly features permitting the automation of SR and other kinds of evidence synthesis reviews.

Project description:BackgroundTo meet the growing importance of real-word data analysis, clinical data and biosamples must be timely made available. Feasibility platforms are often the first contact point for determining the availability of such data for specific research questions. Therefore, a user-friendly interface should be provided to enable access to this information easily. The German Medical Informatics Initiative also aims to establish such a platform for its infrastructure. Although some of these platforms are actively used, their tools still have limitations. Consequently, the Medical Informatics Initiative consortium MIRACUM (Medical Informatics in Research and Care in University Medicine) committed itself to analyzing the pros and cons of existing solutions and to designing an optimized graphical feasibility user interface.ObjectiveThe aim of this study is to identify the system that is most user-friendly and thus forms the best basis for developing a harmonized tool. To achieve this goal, we carried out a comparative usability evaluation of existing tools used by researchers acting as end users.MethodsThe evaluation included three preselected search tools and was conducted as a qualitative exploratory study with a randomized design over a period of 6 weeks. The tools in question were the MIRACUM i2b2 (Informatics for Integrating Biology and the Bedside) feasibility platform, OHDSI's (Observational Health Data Sciences and Informatics) ATLAS, and the Sample Locator of the German Biobank Alliance. The evaluation was conducted in the form of a web-based usability test (usability walkthrough combined with a web-based questionnaire) with participants aged between 26 and 63 years who work as medical doctors.ResultsIn total, 17 study participants evaluated the three tools. The overall evaluation of usability, which was based on the System Usability Scale, showed that the Sample Locator, with a mean System Usability Scale score of 77.03 (SD 20.62), was significantly superior to the other two tools (Wilcoxon test; Sample Locator vs i2b2: P=.047; Sample Locator vs ATLAS: P=.001). i2b2, with a score of 59.83 (SD 25.36), performed significantly better than ATLAS, which had a score of 27.81 (SD 21.79; Wilcoxon test; i2b2 vs ATLAS: P=.005). The analysis of the material generated by the usability walkthrough method confirmed these findings. ATLAS caused the most usability problems (n=66), followed by i2b2 (n=48) and the Sample Locator (n=22). Moreover, the Sample Locator achieved the highest ratings with respect to additional questions regarding satisfaction with the tools.ConclusionsThis study provides data to develop a suitable basis for the selection of a harmonized tool for feasibility studies via concrete evaluation and a comparison of the usability of three different types of query builders. The feedback obtained from the participants during the usability test made it possible to identify user problems and positive design aspects of the individual tools and compare them qualitatively.

Project description:BACKGROUND:Machine learning tools can expedite systematic review (SR) processes by semi-automating citation screening. Abstrackr semi-automates citation screening by predicting relevant records. We evaluated its performance for four screening projects. METHODS:We used a convenience sample of screening projects completed at the Alberta Research Centre for Health Evidence, Edmonton, Canada: three SRs and one descriptive analysis for which we had used SR screening methods. The projects were heterogeneous with respect to search yield (median 9328; range 5243 to 47,385 records; interquartile range (IQR) 15,688 records), topic (Antipsychotics, Bronchiolitis, Diabetes, Child Health SRs), and screening complexity. We uploaded the records to Abstrackr and screened until it made predictions about the relevance of the remaining records. Across three trials for each project, we compared the predictions to human reviewer decisions and calculated the sensitivity, specificity, precision, false negative rate, proportion missed, and workload savings. RESULTS:Abstrackr's sensitivity was > 0.75 for all projects and the mean specificity ranged from 0.69 to 0.90 with the exception of Child Health SRs, for which it was 0.19. The precision (proportion of records correctly predicted as relevant) varied by screening task (median 26.6%; range 14.8 to 64.7%; IQR 29.7%). The median false negative rate (proportion of records incorrectly predicted as irrelevant) was 12.6% (range 3.5 to 21.2%; IQR 12.3%). The workload savings were often large (median 67.2%, range 9.5 to 88.4%; IQR 23.9%). The proportion missed (proportion of records predicted as irrelevant that were included in the final report, out of the total number predicted as irrelevant) was 0.1% for all SRs and 6.4% for the descriptive analysis. This equated to 4.2% (range 0 to 12.2%; IQR 7.8%) of the records in the final reports. CONCLUSIONS:Abstrackr's reliability and the workload savings varied by screening task. Workload savings came at the expense of potentially missing relevant records. How this might affect the results and conclusions of SRs needs to be evaluated. Studies evaluating Abstrackr as the second reviewer in a pair would be of interest to determine if concerns for reliability would diminish. Further evaluations of Abstrackr's performance and usability will inform its refinement and practical utility.

Project description:BackgroundConnecting parents to research evidence is known to improve health decision making. However, guidance on how to develop effective knowledge translation (KT) tools that synthesize child-health evidence into a form understandable by parents is lacking.ObjectiveThe aim of this study was to conduct a comparative usability analysis of three Web-based KT tools to identify differences in tool effectiveness, identify which format parents prefer, and better understand what factors affect usability for parents.MethodsWe evaluated a Cochrane plain language summary (PLS), Blogshot, and a Wikipedia page on a specific child-health topic (acute otitis media). A mixed method approach was used involving a knowledge test, written usability questionnaire, and a semistructured interview. Differences in knowledge and usability questionnaire scores for each of the KT tools were analyzed using Kruskal-Wallis tests, considering a critical significance value of P=.05. Thematic analysis was used to synthesize and identify common parent preferences among the semistructured interviews. Key elements parents wanted in a KT tool were derived through author consensus using questionnaire data and parent interviews.ResultsIn total, 16 parents (9 female) with a mean age of 39.6 (SD 11.9) years completed the study. Parents preferred the Blogshot over the PLS and Wikipedia page (P=.002) and found the Blogshot to be the most aesthetic (P=.001) and easiest to use (P=.001). Knowledge questions and usability survey data also indicated that the Blogshot was the most preferred and effective KT tool at relaying information about the topic. Four key themes were derived from thematic analysis, describing elements parents valued in KT tools. Parents wanted tools that were (1) simple, (2) quick to access and use, and (3) trustworthy, and which (4) informed how to manage the condition. Out of the three KT tools assessed, Blogshots were the most preferred tool by parents and encompassed these four key elements.ConclusionsIt is important that child health evidence be available in formats accessible and understandable by parents to improve decision making, use of health care resources, and health outcomes. Further usability testing of different KT tools should be conducted involving broader populations and other conditions (eg, acute vs chronic) to generate guidelines to improve KT tools for parents.

Project description:BackgroundSystematic reviews are vital to the pursuit of evidence-based medicine within healthcare. Screening titles and abstracts (T&Ab) for inclusion in a systematic review is an intensive, and often collaborative, step. The use of appropriate tools is therefore important. In this study, we identified and evaluated the usability of software tools that support T&Ab screening for systematic reviews within healthcare research.MethodsWe identified software tools using three search methods: a web-based search; a search of the online "systematic review toolbox"; and screening of references in existing literature. We included tools that were accessible and available for testing at the time of the study (December 2018), do not require specific computing infrastructure and provide basic screening functionality for systematic reviews. Key properties of each software tool were identified using a feature analysis adapted for this purpose. This analysis included a weighting developed by a group of medical researchers, therefore prioritising the most relevant features. The highest scoring tools from the feature analysis were then included in a user survey, in which we further investigated the suitability of the tools for supporting T&Ab screening amongst systematic reviewers working in medical research.ResultsFifteen tools met our inclusion criteria. They vary significantly in relation to cost, scope and intended user community. Six of the identified tools (Abstrackr, Colandr, Covidence, DRAGON, EPPI-Reviewer and Rayyan) scored higher than 75% in the feature analysis and were included in the user survey. Of these, Covidence and Rayyan were the most popular with the survey respondents. Their usability scored highly across a range of metrics, with all surveyed researchers (n =?6) stating that they would be likely (or very likely) to use these tools in the future.ConclusionsBased on this study, we would recommend Covidence and Rayyan to systematic reviewers looking for suitable and easy to use tools to support T&Ab screening within healthcare research. These two tools consistently demonstrated good alignment with user requirements. We acknowledge, however, the role of some of the other tools we considered in providing more specialist features that may be of great importance to many researchers.

Project description:BackgroundDiabetic retinopathy (DR), whose standard diagnosis is performed by human experts, has high prevalence and requires a more efficient screening method. Although machine learning (ML)-based automated DR diagnosis has gained attention due to recent approval of IDx-DR, performance of this tool has not been examined systematically, and the best ML technique for use in a real-world setting has not been discussed.ObjectiveThe aim of this study was to systematically examine the overall diagnostic accuracy of ML in diagnosing DR of different categories based on color fundus photographs and to determine the state-of-the-art ML approach.MethodsPublished studies in PubMed and EMBASE were searched from inception to June 2020. Studies were screened for relevant outcomes, publication types, and data sufficiency, and a total of 60 out of 2128 (2.82%) studies were retrieved after study selection. Extraction of data was performed by 2 authors according to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses), and the quality assessment was performed according to the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Meta-analysis of diagnostic accuracy was pooled using a bivariate random effects model. The main outcomes included diagnostic accuracy, sensitivity, and specificity of ML in diagnosing DR based on color fundus photographs, as well as the performances of different major types of ML algorithms.ResultsThe primary meta-analysis included 60 color fundus photograph studies (445,175 interpretations). Overall, ML demonstrated high accuracy in diagnosing DR of various categories, with a pooled area under the receiver operating characteristic (AUROC) ranging from 0.97 (95% CI 0.96-0.99) to 0.99 (95% CI 0.98-1.00). The performance of ML in detecting more-than-mild DR was robust (sensitivity 0.95; AUROC 0.97), and by subgroup analyses, we observed that robust performance of ML was not limited to benchmark data sets (sensitivity 0.92; AUROC 0.96) but could be generalized to images collected in clinical practice (sensitivity 0.97; AUROC 0.97). Neural network was the most widely used method, and the subgroup analysis revealed a pooled AUROC of 0.98 (95% CI 0.96-0.99) for studies that used neural networks to diagnose more-than-mild DR.ConclusionsThis meta-analysis demonstrated high diagnostic accuracy of ML algorithms in detecting DR on color fundus photographs, suggesting that state-of-the-art, ML-based DR screening algorithms are likely ready for clinical applications. However, a significant portion of the earlier published studies had methodology flaws, such as the lack of external validation and presence of spectrum bias. The results of these studies should be interpreted with caution.

Dataset Information

Performance and usability of machine learning for screening in systematic reviews: a comparative evaluation of three tools.

Publications

Performance and usability of machine learning for screening in systematic reviews: a comparative evaluation of three tools.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets