Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387394008> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4387394008 endingPage "13" @default.
- W4387394008 startingPage "1" @default.
- W4387394008 abstract "OBJECTIVE The objective was to assess the performance of a context-enriched large language model (LLM) compared with international neurosurgical experts on questions related to the management of vestibular schwannoma. Furthermore, another objective was to develop a chat-based platform incorporating in-text citations, references, and memory to enable accurate, relevant, and reliable information in real time. METHODS The analysis involved 1) creating a data set through web scraping, 2) developing a chat-based platform called neuroGPT-X, 3) enlisting 8 expert neurosurgeons across international centers to independently create questions (n = 1) and to answer (n = 4) and evaluate responses (n = 3) while blinded, and 4) analyzing the evaluation results on the management of vestibular schwannoma. In the blinded phase, all answers were assessed for accuracy, coherence, relevance, thoroughness, speed, and overall rating. All experts were unblinded and provided their thoughts on the utility and limitations of the tool. In the unblinded phase, all neurosurgeons provided answers to a Likert scale survey and long-answer questions regarding the clinical utility, likelihood of use, and limitations of the tool. The tool was then evaluated on the basis of a set of 103 consensus statements on vestibular schwannoma care from the 8th Quadrennial International Conference on Vestibular Schwannoma. RESULTS Responses from the naive and context-enriched Generative Pretrained Transformer (GPT) models were consistently rated not significantly different in terms of accuracy, coherence, relevance, thoroughness, and overall performance, and they were often rated significantly higher than expert responses. Both the naive and content-enriched GPT models provided faster responses to the standardized question set than expert neurosurgeon respondents (p < 0.01). The context-enriched GPT model agreed with 98 of the 103 (95%) consensus statements. Of interest, all expert surgeons expressed concerns about the reliability of GPT in accurately addressing the nuances and controversies surrounding the management of vestibular schwannoma. Furthermore, the authors developed neuroGPT-X, a chat-based platform designed to provide point-of-care clinical support and mitigate the limitations of human memory. neuroGPT-X incorporates features such as in-text citations and references to enable accurate, relevant, and reliable information in real time. CONCLUSIONS The present study, with its subspecialist-level performance in generating written responses to complex neurosurgical problems for which evidence-based consensus for management is lacking, suggests that context-enriched LLMs show promise as a point-of-care medical resource. The authors anticipate that this work will be a springboard for expansion into more medical specialties, incorporating evidence-based clinical information and developing expert-level dialogue surrounding LLMs in healthcare." @default.
- W4387394008 created "2023-10-07" @default.
- W4387394008 creator A5006848706 @default.
- W4387394008 creator A5031529877 @default.
- W4387394008 creator A5037506643 @default.
- W4387394008 creator A5043783211 @default.
- W4387394008 creator A5044195004 @default.
- W4387394008 creator A5044363422 @default.
- W4387394008 creator A5048395808 @default.
- W4387394008 creator A5048624729 @default.
- W4387394008 creator A5055460485 @default.
- W4387394008 creator A5063516601 @default.
- W4387394008 creator A5076132435 @default.
- W4387394008 creator A5079713113 @default.
- W4387394008 creator A5083573815 @default.
- W4387394008 creator A5091828448 @default.
- W4387394008 date "2023-10-01" @default.
- W4387394008 modified "2023-10-07" @default.
- W4387394008 title "neuroGPT-X: toward a clinic-ready large language model" @default.
- W4387394008 cites W1878893887 @default.
- W4387394008 doi "https://doi.org/10.3171/2023.7.jns23573" @default.
- W4387394008 hasPublicationYear "2023" @default.
- W4387394008 type Work @default.
- W4387394008 citedByCount "0" @default.
- W4387394008 crossrefType "journal-article" @default.
- W4387394008 hasAuthorship W4387394008A5006848706 @default.
- W4387394008 hasAuthorship W4387394008A5031529877 @default.
- W4387394008 hasAuthorship W4387394008A5037506643 @default.
- W4387394008 hasAuthorship W4387394008A5043783211 @default.
- W4387394008 hasAuthorship W4387394008A5044195004 @default.
- W4387394008 hasAuthorship W4387394008A5044363422 @default.
- W4387394008 hasAuthorship W4387394008A5048395808 @default.
- W4387394008 hasAuthorship W4387394008A5048624729 @default.
- W4387394008 hasAuthorship W4387394008A5055460485 @default.
- W4387394008 hasAuthorship W4387394008A5063516601 @default.
- W4387394008 hasAuthorship W4387394008A5076132435 @default.
- W4387394008 hasAuthorship W4387394008A5079713113 @default.
- W4387394008 hasAuthorship W4387394008A5083573815 @default.
- W4387394008 hasAuthorship W4387394008A5091828448 @default.
- W4387394008 hasBestOaLocation W43873940081 @default.
- W4387394008 hasConcept C119857082 @default.
- W4387394008 hasConcept C151730666 @default.
- W4387394008 hasConcept C154945302 @default.
- W4387394008 hasConcept C158154518 @default.
- W4387394008 hasConcept C177264268 @default.
- W4387394008 hasConcept C17744445 @default.
- W4387394008 hasConcept C19527891 @default.
- W4387394008 hasConcept C199360897 @default.
- W4387394008 hasConcept C199539241 @default.
- W4387394008 hasConcept C204321447 @default.
- W4387394008 hasConcept C2779343474 @default.
- W4387394008 hasConcept C41008148 @default.
- W4387394008 hasConcept C71924100 @default.
- W4387394008 hasConcept C86803240 @default.
- W4387394008 hasConceptScore W4387394008C119857082 @default.
- W4387394008 hasConceptScore W4387394008C151730666 @default.
- W4387394008 hasConceptScore W4387394008C154945302 @default.
- W4387394008 hasConceptScore W4387394008C158154518 @default.
- W4387394008 hasConceptScore W4387394008C177264268 @default.
- W4387394008 hasConceptScore W4387394008C17744445 @default.
- W4387394008 hasConceptScore W4387394008C19527891 @default.
- W4387394008 hasConceptScore W4387394008C199360897 @default.
- W4387394008 hasConceptScore W4387394008C199539241 @default.
- W4387394008 hasConceptScore W4387394008C204321447 @default.
- W4387394008 hasConceptScore W4387394008C2779343474 @default.
- W4387394008 hasConceptScore W4387394008C41008148 @default.
- W4387394008 hasConceptScore W4387394008C71924100 @default.
- W4387394008 hasConceptScore W4387394008C86803240 @default.
- W4387394008 hasLocation W43873940081 @default.
- W4387394008 hasOpenAccess W4387394008 @default.
- W4387394008 hasPrimaryLocation W43873940081 @default.
- W4387394008 hasRelatedWork W1835907303 @default.
- W4387394008 hasRelatedWork W2049612369 @default.
- W4387394008 hasRelatedWork W2085384747 @default.
- W4387394008 hasRelatedWork W2088166309 @default.
- W4387394008 hasRelatedWork W2106071040 @default.
- W4387394008 hasRelatedWork W2276587472 @default.
- W4387394008 hasRelatedWork W2615795876 @default.
- W4387394008 hasRelatedWork W4238976562 @default.
- W4387394008 hasRelatedWork W4248323080 @default.
- W4387394008 hasRelatedWork W4312133475 @default.
- W4387394008 isParatext "false" @default.
- W4387394008 isRetracted "false" @default.
- W4387394008 workType "article" @default.