Leveraging GPT-4 for identifying cancer phenotypes in electronic health records: a performance comparison between GPT-4, GPT-3.5-turbo, Flan-T5, Llama-3-8B, and spaCy's rule-based and machine learning-based methods.
Saved in:
| Title: | Leveraging GPT-4 for identifying cancer phenotypes in electronic health records: a performance comparison between GPT-4, GPT-3.5-turbo, Flan-T5, Llama-3-8B, and spaCy's rule-based and machine learning-based methods. |
|---|---|
| Authors: | Bhattarai K; Institute for Informatics, Data Science & Biostatistics, Washington University School of Medicine, St. Louis, MO 63110, United States.; Department of Computer Science, Washington University in St Louis, St. Louis, MO 63110, United States., Oh IY; Institute for Informatics, Data Science & Biostatistics, Washington University School of Medicine, St. Louis, MO 63110, United States., Sierra JM; Medical Scientist Training Program, Washington University School of Medicine, St. Louis, MO 63110, United States., Tang J; Department of Internal Medicine, Washington University School of Medicine, St. Louis, MO 63110, United States., Payne PRO; Institute for Informatics, Data Science & Biostatistics, Washington University School of Medicine, St. Louis, MO 63110, United States.; Department of Computer Science, Washington University in St Louis, St. Louis, MO 63110, United States., Abrams Z; Institute for Informatics, Data Science & Biostatistics, Washington University School of Medicine, St. Louis, MO 63110, United States., Lai AM; Institute for Informatics, Data Science & Biostatistics, Washington University School of Medicine, St. Louis, MO 63110, United States.; Department of Computer Science, Washington University in St Louis, St. Louis, MO 63110, United States. |
| Source: | JAMIA open [JAMIA Open] 2024 Jul 03; Vol. 7 (3), pp. ooae060. Date of Electronic Publication: 2024 Jul 03 (Print Publication: 2024). |
| Publication Type: | Journal Article |
| Journal Info: | Publisher: Oxford University Press on behalf of the American Medical Informatics Association Country of Publication: United States NLM ID: 101730643 Publication Model: eCollection Cited Medium: Internet ISSN: 2574-2531 (Electronic) Linking ISSN: 25742531 NLM ISO Abbreviation: JAMIA Open Subsets: PubMed not MEDLINE |
| Database: | MEDLINE Ultimate |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: mdl DbLabel: MEDLINE Ultimate An: 38962662 AccessLevel: 2 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Leveraging GPT-4 for identifying cancer phenotypes in electronic health records: a performance comparison between GPT-4, GPT-3.5-turbo, Flan-T5, Llama-3-8B, and spaCy's rule-based and machine learning-based methods. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AU" term="%22Bhattarai+K%22">Bhattarai K</searchLink>; Institute for Informatics, Data Science & Biostatistics, Washington University School of Medicine, St. Louis, MO 63110, United States.; Department of Computer Science, Washington University in St Louis, St. Louis, MO 63110, United States.<br /><searchLink fieldCode="AU" term="%22Oh+IY%22">Oh IY</searchLink>; Institute for Informatics, Data Science & Biostatistics, Washington University School of Medicine, St. Louis, MO 63110, United States.<br /><searchLink fieldCode="AU" term="%22Sierra+JM%22">Sierra JM</searchLink>; Medical Scientist Training Program, Washington University School of Medicine, St. Louis, MO 63110, United States.<br /><searchLink fieldCode="AU" term="%22Tang+J%22">Tang J</searchLink>; Department of Internal Medicine, Washington University School of Medicine, St. Louis, MO 63110, United States.<br /><searchLink fieldCode="AU" term="%22Payne+PRO%22">Payne PRO</searchLink>; Institute for Informatics, Data Science & Biostatistics, Washington University School of Medicine, St. Louis, MO 63110, United States.; Department of Computer Science, Washington University in St Louis, St. Louis, MO 63110, United States.<br /><searchLink fieldCode="AU" term="%22Abrams+Z%22">Abrams Z</searchLink>; Institute for Informatics, Data Science & Biostatistics, Washington University School of Medicine, St. Louis, MO 63110, United States.<br /><searchLink fieldCode="AU" term="%22Lai+AM%22">Lai AM</searchLink>; Institute for Informatics, Data Science & Biostatistics, Washington University School of Medicine, St. Louis, MO 63110, United States.; Department of Computer Science, Washington University in St Louis, St. Louis, MO 63110, United States. – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22101730643%22">JAMIA open</searchLink> [JAMIA Open] 2024 Jul 03; Vol. 7 (3), pp. ooae060. <i>Date of Electronic Publication: </i>2024 Jul 03 (<i>Print Publication: </i>2024). – Name: TypePub Label: Publication Type Group: TypPub Data: Journal Article – Name: TitleSource Label: Journal Info Group: Src Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22Oxford+University+Press+on+behalf+of+the+American+Medical+Informatics+Association%22">Oxford University Press on behalf of the American Medical Informatics Association </searchLink><i>Country of Publication: </i>United States <i>NLM ID: </i>101730643 <i>Publication Model: </i>eCollection <i>Cited Medium: </i>Internet <i>ISSN: </i>2574-2531 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2225742531%22">25742531 </searchLink><i>NLM ISO Abbreviation: </i>JAMIA Open <i>Subsets: </i>PubMed not MEDLINE |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=mdl&AN=38962662 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1093/jamiaopen/ooae060 Languages: – Code: eng Text: English PhysicalDescription: Pagination: StartPage: ooae060 Titles: – TitleFull: Leveraging GPT-4 for identifying cancer phenotypes in electronic health records: a performance comparison between GPT-4, GPT-3.5-turbo, Flan-T5, Llama-3-8B, and spaCy's rule-based and machine learning-based methods. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Bhattarai K – PersonEntity: Name: NameFull: Oh IY – PersonEntity: Name: NameFull: Sierra JM – PersonEntity: Name: NameFull: Tang J – PersonEntity: Name: NameFull: Payne PRO – PersonEntity: Name: NameFull: Abrams Z – PersonEntity: Name: NameFull: Lai AM IsPartOfRelationships: – BibEntity: Dates: – D: 03 M: 07 Text: 2024 Jul 03 Type: published Y: 2024 Identifiers: – Type: issn-electronic Value: 2574-2531 Numbering: – Type: volume Value: 7 – Type: issue Value: 3 Titles: – TitleFull: JAMIA open Type: main |
| ResultId | 1 |
