Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366603014> ?p ?o ?g. }
- W4366603014 endingPage "1166" @default.
- W4366603014 startingPage "1158" @default.
- W4366603014 abstract "ChatGPT, a tool based on natural language processing (NLP), is on everyone's mind, and several potential applications in healthcare have been already proposed. However, since the ability of this tool to interpret laboratory test results has not yet been tested, the EFLM Working group on Artificial Intelligence (WG-AI) has set itself the task of closing this gap with a systematic approach.WG-AI members generated 10 simulated laboratory reports of common parameters, which were then passed to ChatGPT for interpretation, according to reference intervals (RI) and units, using an optimized prompt. The results were subsequently evaluated independently by all WG-AI members with respect to relevance, correctness, helpfulness and safety.ChatGPT recognized all laboratory tests, it could detect if they deviated from the RI and gave a test-by-test as well as an overall interpretation. The interpretations were rather superficial, not always correct, and, only in some cases, judged coherently. The magnitude of the deviation from the RI seldom plays a role in the interpretation of laboratory tests, and artificial intelligence (AI) did not make any meaningful suggestion regarding follow-up diagnostics or further procedures in general.ChatGPT in its current form, being not specifically trained on medical data or laboratory data in particular, may only be considered a tool capable of interpreting a laboratory report on a test-by-test basis at best, but not on the interpretation of an overall diagnostic picture. Future generations of similar AIs with medical ground truth training data might surely revolutionize current processes in healthcare, despite this implementation is not ready yet." @default.
- W4366603014 created "2023-04-23" @default.
- W4366603014 creator A5016415491 @default.
- W4366603014 creator A5026641430 @default.
- W4366603014 creator A5029813939 @default.
- W4366603014 creator A5050549744 @default.
- W4366603014 creator A5059953910 @default.
- W4366603014 creator A5082094236 @default.
- W4366603014 creator A5082381238 @default.
- W4366603014 creator A5085273180 @default.
- W4366603014 creator A5088323703 @default.
- W4366603014 creator A5088520551 @default.
- W4366603014 date "2023-04-24" @default.
- W4366603014 modified "2023-10-09" @default.
- W4366603014 title "Potentials and pitfalls of ChatGPT and natural-language artificial intelligence models for the understanding of laboratory medicine test results. An assessment by the European Federation of Clinical Chemistry and Laboratory Medicine (EFLM) Working Group on Artificial Intelligence (WG-AI)" @default.
- W4366603014 cites W1972234604 @default.
- W4366603014 cites W2052851618 @default.
- W4366603014 cites W2291253625 @default.
- W4366603014 cites W2531664345 @default.
- W4366603014 cites W2560499204 @default.
- W4366603014 cites W2745394387 @default.
- W4366603014 cites W2765483530 @default.
- W4366603014 cites W2809036077 @default.
- W4366603014 cites W2908201961 @default.
- W4366603014 cites W2916185483 @default.
- W4366603014 cites W3018788396 @default.
- W4366603014 cites W3034137247 @default.
- W4366603014 cites W3121368818 @default.
- W4366603014 cites W3127007513 @default.
- W4366603014 cites W3132718350 @default.
- W4366603014 cites W3171123721 @default.
- W4366603014 cites W4229028034 @default.
- W4366603014 cites W4294805192 @default.
- W4366603014 cites W4307218738 @default.
- W4366603014 cites W4308181626 @default.
- W4366603014 cites W4308183660 @default.
- W4366603014 cites W4317390716 @default.
- W4366603014 cites W4319339070 @default.
- W4366603014 cites W4319662928 @default.
- W4366603014 cites W4321371665 @default.
- W4366603014 cites W4321459182 @default.
- W4366603014 cites W4322008312 @default.
- W4366603014 cites W4323360926 @default.
- W4366603014 cites W4361000349 @default.
- W4366603014 cites W4361289889 @default.
- W4366603014 doi "https://doi.org/10.1515/cclm-2023-0355" @default.
- W4366603014 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37083166" @default.
- W4366603014 hasPublicationYear "2023" @default.
- W4366603014 type Work @default.
- W4366603014 citedByCount "10" @default.
- W4366603014 countsByYear W43666030142023 @default.
- W4366603014 crossrefType "journal-article" @default.
- W4366603014 hasAuthorship W4366603014A5016415491 @default.
- W4366603014 hasAuthorship W4366603014A5026641430 @default.
- W4366603014 hasAuthorship W4366603014A5029813939 @default.
- W4366603014 hasAuthorship W4366603014A5050549744 @default.
- W4366603014 hasAuthorship W4366603014A5059953910 @default.
- W4366603014 hasAuthorship W4366603014A5082094236 @default.
- W4366603014 hasAuthorship W4366603014A5082381238 @default.
- W4366603014 hasAuthorship W4366603014A5085273180 @default.
- W4366603014 hasAuthorship W4366603014A5088323703 @default.
- W4366603014 hasAuthorship W4366603014A5088520551 @default.
- W4366603014 hasBestOaLocation W43666030141 @default.
- W4366603014 hasConcept C11413529 @default.
- W4366603014 hasConcept C142724271 @default.
- W4366603014 hasConcept C151730666 @default.
- W4366603014 hasConcept C154945302 @default.
- W4366603014 hasConcept C15744967 @default.
- W4366603014 hasConcept C158154518 @default.
- W4366603014 hasConcept C17744445 @default.
- W4366603014 hasConcept C199360897 @default.
- W4366603014 hasConcept C199539241 @default.
- W4366603014 hasConcept C204321447 @default.
- W4366603014 hasConcept C2777267654 @default.
- W4366603014 hasConcept C2781265381 @default.
- W4366603014 hasConcept C41008148 @default.
- W4366603014 hasConcept C44519122 @default.
- W4366603014 hasConcept C527412718 @default.
- W4366603014 hasConcept C55439883 @default.
- W4366603014 hasConcept C71924100 @default.
- W4366603014 hasConcept C77805123 @default.
- W4366603014 hasConcept C86803240 @default.
- W4366603014 hasConceptScore W4366603014C11413529 @default.
- W4366603014 hasConceptScore W4366603014C142724271 @default.
- W4366603014 hasConceptScore W4366603014C151730666 @default.
- W4366603014 hasConceptScore W4366603014C154945302 @default.
- W4366603014 hasConceptScore W4366603014C15744967 @default.
- W4366603014 hasConceptScore W4366603014C158154518 @default.
- W4366603014 hasConceptScore W4366603014C17744445 @default.
- W4366603014 hasConceptScore W4366603014C199360897 @default.
- W4366603014 hasConceptScore W4366603014C199539241 @default.
- W4366603014 hasConceptScore W4366603014C204321447 @default.
- W4366603014 hasConceptScore W4366603014C2777267654 @default.
- W4366603014 hasConceptScore W4366603014C2781265381 @default.
- W4366603014 hasConceptScore W4366603014C41008148 @default.
- W4366603014 hasConceptScore W4366603014C44519122 @default.
- W4366603014 hasConceptScore W4366603014C527412718 @default.
- W4366603014 hasConceptScore W4366603014C55439883 @default.