Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383620154> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4383620154 abstract "OBJECTIVE Implement and evaluate a quality assurance workflow that leverages NLP to rapidly resolve inadvertent discordance between radiologist and AI DSS in the interpretation of high acuity CTs when the radiologist does not engage with AI DSS output. METHODS All consecutive high acuity adult CTs performed in our health system between March 1, 2020 through September 20, 2022 were interpreted alongside AI DSS (Aidoc, Tel Aviv, Israel) for intracranial hemorrhage (ICH), cervical spine fracture, and pulmonary embolus (PE). CTs were flagged for this QA workflow if they met three criteria: 1) negative by radiologist report, 2) high probability positive by AI DSS, and 3) unviewed AI DSS output. In these cases, an automated email notification was sent to our quality team. If discordance was confirmed on secondary review - an initially missed diagnosis - addendum and communication documentation was performed. RESULTS Of 111,674 high acuity CTs interpreted alongside AI DSS over this 2.5 year time period, the frequency of missed diagnoses (ICH, PE, and cervical spine fracture) uncovered by this workflow was 0.02% (n=26). Of 12,412 CTs prioritized as positive by AI DSS, 0.4% (n=46) were discordant, unengaged, and flagged for QA. Among these discordant cases, 57% (26/46) were determined to be true positives. Addendum/communication documentation was performed within 24 hours from the initial report signing in 85%. DISCUSSION Inadvertent discordance between radiologist and AI DSS occurs in a small number of cases. This QA workflow leveraged NLP to rapidly detect, notify, and resolve these discrepancies and prevent potential missed diagnoses." @default.
- W4383620154 created "2023-07-09" @default.
- W4383620154 creator A5024759760 @default.
- W4383620154 creator A5029329050 @default.
- W4383620154 creator A5054307107 @default.
- W4383620154 date "2023-07-01" @default.
- W4383620154 modified "2023-10-01" @default.
- W4383620154 title "Cross-Check QA: A Quality Assurance Workflow to Prevent Missed Diagnoses by Alerting Inadvertent Discordance Between the Radiologist and Artificial Intelligence in the Interpretation of High-Acuity CT Scans" @default.
- W4383620154 cites W2971937838 @default.
- W4383620154 cites W2971940192 @default.
- W4383620154 cites W3005891124 @default.
- W4383620154 cites W3008956992 @default.
- W4383620154 cites W3045833980 @default.
- W4383620154 cites W3087496930 @default.
- W4383620154 cites W3097143232 @default.
- W4383620154 cites W3132742545 @default.
- W4383620154 cites W3134138028 @default.
- W4383620154 cites W3156550296 @default.
- W4383620154 cites W3161335554 @default.
- W4383620154 cites W4210630473 @default.
- W4383620154 cites W4210943902 @default.
- W4383620154 cites W4212961538 @default.
- W4383620154 cites W4285391660 @default.
- W4383620154 cites W4296156589 @default.
- W4383620154 cites W4308683075 @default.
- W4383620154 cites W4319023457 @default.
- W4383620154 doi "https://doi.org/10.1016/j.jacr.2023.06.010" @default.
- W4383620154 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37423347" @default.
- W4383620154 hasPublicationYear "2023" @default.
- W4383620154 type Work @default.
- W4383620154 citedByCount "0" @default.
- W4383620154 crossrefType "journal-article" @default.
- W4383620154 hasAuthorship W4383620154A5024759760 @default.
- W4383620154 hasAuthorship W4383620154A5029329050 @default.
- W4383620154 hasAuthorship W4383620154A5054307107 @default.
- W4383620154 hasConcept C106436119 @default.
- W4383620154 hasConcept C126838900 @default.
- W4383620154 hasConcept C142724271 @default.
- W4383620154 hasConcept C154945302 @default.
- W4383620154 hasConcept C177212765 @default.
- W4383620154 hasConcept C19527891 @default.
- W4383620154 hasConcept C199360897 @default.
- W4383620154 hasConcept C2778618615 @default.
- W4383620154 hasConcept C41008148 @default.
- W4383620154 hasConcept C534262118 @default.
- W4383620154 hasConcept C56666940 @default.
- W4383620154 hasConcept C71924100 @default.
- W4383620154 hasConcept C77088390 @default.
- W4383620154 hasConceptScore W4383620154C106436119 @default.
- W4383620154 hasConceptScore W4383620154C126838900 @default.
- W4383620154 hasConceptScore W4383620154C142724271 @default.
- W4383620154 hasConceptScore W4383620154C154945302 @default.
- W4383620154 hasConceptScore W4383620154C177212765 @default.
- W4383620154 hasConceptScore W4383620154C19527891 @default.
- W4383620154 hasConceptScore W4383620154C199360897 @default.
- W4383620154 hasConceptScore W4383620154C2778618615 @default.
- W4383620154 hasConceptScore W4383620154C41008148 @default.
- W4383620154 hasConceptScore W4383620154C534262118 @default.
- W4383620154 hasConceptScore W4383620154C56666940 @default.
- W4383620154 hasConceptScore W4383620154C71924100 @default.
- W4383620154 hasConceptScore W4383620154C77088390 @default.
- W4383620154 hasLocation W43836201541 @default.
- W4383620154 hasLocation W43836201542 @default.
- W4383620154 hasOpenAccess W4383620154 @default.
- W4383620154 hasPrimaryLocation W43836201541 @default.
- W4383620154 hasRelatedWork W1530026816 @default.
- W4383620154 hasRelatedWork W2157030199 @default.
- W4383620154 hasRelatedWork W2318994466 @default.
- W4383620154 hasRelatedWork W2461248931 @default.
- W4383620154 hasRelatedWork W2556712653 @default.
- W4383620154 hasRelatedWork W3154922179 @default.
- W4383620154 hasRelatedWork W3205676765 @default.
- W4383620154 hasRelatedWork W3211833219 @default.
- W4383620154 hasRelatedWork W4319030840 @default.
- W4383620154 hasRelatedWork W596584015 @default.
- W4383620154 isParatext "false" @default.
- W4383620154 isRetracted "false" @default.
- W4383620154 workType "article" @default.