FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3194687576> ?p ?o ?g. }

• W3194687576 endingPage "e554" @default.
• W3194687576 startingPage "e543" @default.
• W3194687576 abstract "BackgroundArtificial intelligence (AI) algorithms can be trained to recognise tuberculosis-related abnormalities on chest radiographs. Various AI algorithms are available commercially, yet there is little impartial evidence on how their performance compares with each other and with radiologists. We aimed to evaluate five commercial AI algorithms for triaging tuberculosis using a large dataset that had not previously been used to train any AI algorithms.MethodsIndividuals aged 15 years or older presenting or referred to three tuberculosis screening centres in Dhaka, Bangladesh, between May 15, 2014, and Oct 4, 2016, were recruited consecutively. Every participant was verbally screened for symptoms and received a digital posterior-anterior chest x-ray and an Xpert MTB/RIF (Xpert) test. All chest x-rays were read independently by a group of three registered radiologists and five commercial AI algorithms: CAD4TB (version 7), InferRead DR (version 2), Lunit INSIGHT CXR (version 4.9.0), JF CXR-1 (version 2), and qXR (version 3). We compared the performance of the AI algorithms with each other, with the radiologists, and with the WHO's Target Product Profile (TPP) of triage tests (≥90% sensitivity and ≥70% specificity). We used a new evaluation framework that simultaneously evaluates sensitivity, proportion of Xpert tests avoided, and number needed to test to inform implementers’ choice of software and selection of threshold abnormality scores.FindingsChest x-rays from 23 954 individuals were included in the analysis. All five AI algorithms significantly outperformed the radiologists. The areas under the receiver operating characteristic curve were 90·81% (95% CI 90·33–91·29) for qXR, 90·34% (89·81–90·87) for CAD4TB, 88·61% (88·03–89·20) for Lunit INSIGHT CXR, 84·90% (84·27–85·54) for InferRead DR, and 84·89% (84·26–85·53) for JF CXR-1. Only qXR (74·3% specificity [95% CI 73·3–74·9]) and CAD4TB (72·9% specificity [72·3–73·5]) met the TPP at 90% sensitivity. All five AI algorithms reduced the number of Xpert tests required by 50% while maintaining a sensitivity above 90%. All AI algorithms performed worse among older age groups (>60 years) and people with a history of tuberculosis.InterpretationAI algorithms can be highly accurate and useful triage tools for tuberculosis detection in high-burden regions, and outperform human readers.FundingGovernment of Canada." @default.
• W3194687576 created "2021-08-30" @default.
• W3194687576 creator A5010284171 @default.
• W3194687576 creator A5020423855 @default.
• W3194687576 creator A5021780089 @default.
• W3194687576 creator A5023847767 @default.
• W3194687576 creator A5037285420 @default.
• W3194687576 creator A5049662698 @default.
• W3194687576 creator A5060905069 @default.
• W3194687576 creator A5071937146 @default.
• W3194687576 creator A5084555755 @default.
• W3194687576 date "2021-09-01" @default.
• W3194687576 modified "2023-10-15" @default.
• W3194687576 title "Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms" @default.
• W3194687576 cites W1966716734 @default.
• W3194687576 cites W1972507183 @default.
• W3194687576 cites W2006617902 @default.
• W3194687576 cites W2061757011 @default.
• W3194687576 cites W2155653793 @default.
• W3194687576 cites W2514505281 @default.
• W3194687576 cites W2767236661 @default.
• W3194687576 cites W2885509905 @default.
• W3194687576 cites W2979533273 @default.
• W3194687576 cites W2980965120 @default.
• W3194687576 cites W2998175747 @default.
• W3194687576 cites W2999518791 @default.
• W3194687576 cites W3093602247 @default.
• W3194687576 cites W3106437781 @default.
• W3194687576 cites W3108029355 @default.
• W3194687576 cites W3120863491 @default.
• W3194687576 doi "https://doi.org/10.1016/s2589-7500(21)00116-3" @default.
• W3194687576 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34446265" @default.
• W3194687576 hasPublicationYear "2021" @default.
• W3194687576 type Work @default.
• W3194687576 sameAs 3194687576 @default.
• W3194687576 citedByCount "85" @default.
• W3194687576 countsByYear W31946875762021 @default.
• W3194687576 countsByYear W31946875762022 @default.
• W3194687576 countsByYear W31946875762023 @default.
• W3194687576 crossrefType "journal-article" @default.
• W3194687576 hasAuthorship W3194687576A5010284171 @default.
• W3194687576 hasAuthorship W3194687576A5020423855 @default.
• W3194687576 hasAuthorship W3194687576A5021780089 @default.
• W3194687576 hasAuthorship W3194687576A5023847767 @default.
• W3194687576 hasAuthorship W3194687576A5037285420 @default.
• W3194687576 hasAuthorship W3194687576A5049662698 @default.
• W3194687576 hasAuthorship W3194687576A5060905069 @default.
• W3194687576 hasAuthorship W3194687576A5071937146 @default.
• W3194687576 hasAuthorship W3194687576A5084555755 @default.
• W3194687576 hasBestOaLocation W31946875761 @default.
• W3194687576 hasConcept C11413529 @default.
• W3194687576 hasConcept C119857082 @default.
• W3194687576 hasConcept C126322002 @default.
• W3194687576 hasConcept C126838900 @default.
• W3194687576 hasConcept C142724271 @default.
• W3194687576 hasConcept C151730666 @default.
• W3194687576 hasConcept C154945302 @default.
• W3194687576 hasConcept C2777120189 @default.
• W3194687576 hasConcept C2777267654 @default.
• W3194687576 hasConcept C2781069245 @default.
• W3194687576 hasConcept C41008148 @default.
• W3194687576 hasConcept C545542383 @default.
• W3194687576 hasConcept C58471807 @default.
• W3194687576 hasConcept C71924100 @default.
• W3194687576 hasConcept C86803240 @default.
• W3194687576 hasConceptScore W3194687576C11413529 @default.
• W3194687576 hasConceptScore W3194687576C119857082 @default.
• W3194687576 hasConceptScore W3194687576C126322002 @default.
• W3194687576 hasConceptScore W3194687576C126838900 @default.
• W3194687576 hasConceptScore W3194687576C142724271 @default.
• W3194687576 hasConceptScore W3194687576C151730666 @default.
• W3194687576 hasConceptScore W3194687576C154945302 @default.
• W3194687576 hasConceptScore W3194687576C2777120189 @default.
• W3194687576 hasConceptScore W3194687576C2777267654 @default.
• W3194687576 hasConceptScore W3194687576C2781069245 @default.
• W3194687576 hasConceptScore W3194687576C41008148 @default.
• W3194687576 hasConceptScore W3194687576C545542383 @default.
• W3194687576 hasConceptScore W3194687576C58471807 @default.
• W3194687576 hasConceptScore W3194687576C71924100 @default.
• W3194687576 hasConceptScore W3194687576C86803240 @default.
• W3194687576 hasIssue "9" @default.
• W3194687576 hasLocation W31946875761 @default.
• W3194687576 hasOpenAccess W3194687576 @default.
• W3194687576 hasPrimaryLocation W31946875761 @default.
• W3194687576 hasRelatedWork W125325933 @default.
• W3194687576 hasRelatedWork W1996729302 @default.
• W3194687576 hasRelatedWork W2033023095 @default.
• W3194687576 hasRelatedWork W2051773733 @default.
• W3194687576 hasRelatedWork W2144451503 @default.
• W3194687576 hasRelatedWork W2147580721 @default.
• W3194687576 hasRelatedWork W2909333182 @default.
• W3194687576 hasRelatedWork W2941176721 @default.
• W3194687576 hasRelatedWork W2944159687 @default.
• W3194687576 hasRelatedWork W3015660457 @default.
• W3194687576 hasVolume "3" @default.
• W3194687576 isParatext "false" @default.
• W3194687576 isRetracted "false" @default.
• W3194687576 magId "3194687576" @default.

• next