Editing Physicians' Responses Using GPT-4 for Academic Research...dHealth 2024, 18th Health Informatics Meets Digital Health Conference, May 7-8, 2024, Vienna, Austria.
The integration of Artificial Intelligence (AI) into digital healthcare, particularly in the anonymisation and processing of health information, holds considerable potential. Objectives: To develop a methodology using Generative Pre-trained Transformer (GPT) models to preserve the essence of medical...
| Publicado en: | Studies in Health Technology & Informatics Vol. 313; pp. 101 - 107 |
|---|---|
| Autores principales: | , , , , , |
| Formato: | pictorial proceedings research tables/charts Journal Article |
| Publicado: |
Sage Publications Inc.
2024
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=176981683&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 176981683 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 09269630 U1V jtl: Studies in Health Technology & Informatics issn: 09269630 maglogo: N pubinfo: dt: 2024 vid: 313 pid: 344 pub: Sage Publications Inc. place: Thousand Oaks, California artinfo: ui: 176981683 176981683 176981683 10.3233/SHTI240019 176981683 ppf: 101 ppct: 6 formats: tig: atl: Editing Physicians' Responses Using GPT-4 for Academic Research...dHealth 2024, 18th Health Informatics Meets Digital Health Conference, May 7-8, 2024, Vienna, Austria. aug: au: WEBER, Magdalena T. SCHAAF, Jannik STORF, Holger WAGNER, Thomas O. F. BERGER, Alexandra NOLL, Richard affil: Institute of Medical Informatics, Goethe University Frankfurt, University Hospital Frankfurt, Frankfurt, Germany sug: subj: Education, Medical Research, Medical Health Education Health Information Physicians Edit and Review Methods Artificial Intelligence Human Congresses and Conferences Austria Austria Language Respiratory Tract Diseases Rare Diseases Digital Health Data Security Privacy and Confidentiality Natural Language Processing Medical Informatics ab: The integration of Artificial Intelligence (AI) into digital healthcare, particularly in the anonymisation and processing of health information, holds considerable potential. Objectives: To develop a methodology using Generative Pre-trained Transformer (GPT) models to preserve the essence of medical advice in doctors' responses, while editing them for use in scientific studies. Methods: German and English responses from EXABO, a rare respiratory disease platform, were processed using iterative refinement and other prompt engineering techniques, with a focus on removing identifiable and irrelevant content. Results: Of 40 responses tested, 31 were accurately modified according to the developed guidelines. Challenges included misclassification and incomplete removal, with incremental prompting proving more accurate than combined prompting. Conclusion: GPT-4 models show promise in medical response editing, but face challenges in accuracy and consistency. Precision in prompt engineering is essential in medical contexts to minimise bias and retain relevant information. pubtype: Academic Journal doctype: pictorial proceedings research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|