ChatGPT as a rising force: Can AI bridge information gaps in Occupational Risk Prevention?
Gespeichert in:
| Titel: | ChatGPT as a rising force: Can AI bridge information gaps in Occupational Risk Prevention? |
|---|---|
| Autoren: | García-Rudolph A; Department of Research and Innovation, Institut Guttmann, Institut Universitari de Neurorehabilitació adscrit a la UAB, Barcelona, Spain.; Universitat Autònoma de Barcelona, Spain.; Fundació Institut d'Investigació en Ciències de la Salut Germans Trias i Pujol, Barcelona, Spain., Sanchez-Pinsach D; Department of Research and Innovation, Institut Guttmann, Institut Universitari de Neurorehabilitació adscrit a la UAB, Barcelona, Spain.; Universitat Autònoma de Barcelona, Spain.; Fundació Institut d'Investigació en Ciències de la Salut Germans Trias i Pujol, Barcelona, Spain., Remacha J; Department of Research and Innovation, Institut Guttmann, Institut Universitari de Neurorehabilitació adscrit a la UAB, Barcelona, Spain.; Universitat Autònoma de Barcelona, Spain.; Fundació Institut d'Investigació en Ciències de la Salut Germans Trias i Pujol, Barcelona, Spain., Patricio S; Department of Research and Innovation, Institut Guttmann, Institut Universitari de Neurorehabilitació adscrit a la UAB, Barcelona, Spain.; Universitat Autònoma de Barcelona, Spain.; Fundació Institut d'Investigació en Ciències de la Salut Germans Trias i Pujol, Barcelona, Spain., Opisso E; Department of Research and Innovation, Institut Guttmann, Institut Universitari de Neurorehabilitació adscrit a la UAB, Barcelona, Spain.; Universitat Autònoma de Barcelona, Spain.; Fundació Institut d'Investigació en Ciències de la Salut Germans Trias i Pujol, Barcelona, Spain. |
| Quelle: | Work (Reading, Mass.) [Work] 2025 Dec; Vol. 82 (4), pp. 940-945. Date of Electronic Publication: 2025 Jun 12. |
| Publikationsart: | Journal Article |
| Sprache: | English |
| Info zur Zeitschrift: | Publisher: SAGE Publications Country of Publication: United States NLM ID: 9204382 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1875-9270 (Electronic) Linking ISSN: 10519815 NLM ISO Abbreviation: Work Subsets: MEDLINE |
| Imprint Name(s): | Publication: 2024- : [Thousand Oaks, CA] : SAGE Publications Original Publication: Reading, MA : Andover Medical Publishers, c1990- |
| MeSH-Schlagworte: | Occupational Health* , Artificial Intelligence*/trends, Humans ; Reproducibility of Results ; Surveys and Questionnaires ; Spain ; Generative Artificial Intelligence |
| Abstract: | BackgroundLack of information is a critical challenge in occupational health. With over 180 million users, ChatGPT has become a prominent trend, swiftly addressing a wide array of queries, yet it critically needs validation in occupational health.ObjectiveThis study evaluated GPT-3.5 (free version) and GPT-4 (paid version) on their ability to respond to Occupational Risk Prevention formal multiple-choice questions.MethodsA total of 303 questions were assessed, categorized across four levels of complexity-task-specific, national, European, and global-within various Spanish regions.ResultsGPT-3.5 achieved an overall accuracy of 56.8%, while GPT-4 reached 73.9% (p < 0.001). GPT-3.5 showed particularly limited performance on domain-specific content. Both models shared similar error patterns, with incorrect response rates ranging from 18-24% across regions.ConclusionDespite GPT-4's improved performance, both models display notable limitations in occupational health applications. To enhance reliability, four strategies are proposed: formal validation, continuous training, error analysis, and regional adaptation. |
| Contributed Indexing: | Keywords: artificial intelligence; computer-assisted instruction; educational technology; natural language processing; occupational health; validation studies as topic |
| Entry Date(s): | Date Created: 20250613 Date Completed: 20251203 Latest Revision: 20251203 |
| Update Code: | 20251204 |
| DOI: | 10.1177/10519815251348355 |
| PMID: | 40509779 |
| Datenbank: | MEDLINE |
Nájsť tento článok vo Web of Science | Abstract: | BackgroundLack of information is a critical challenge in occupational health. With over 180 million users, ChatGPT has become a prominent trend, swiftly addressing a wide array of queries, yet it critically needs validation in occupational health.ObjectiveThis study evaluated GPT-3.5 (free version) and GPT-4 (paid version) on their ability to respond to Occupational Risk Prevention formal multiple-choice questions.MethodsA total of 303 questions were assessed, categorized across four levels of complexity-task-specific, national, European, and global-within various Spanish regions.ResultsGPT-3.5 achieved an overall accuracy of 56.8%, while GPT-4 reached 73.9% (p < 0.001). GPT-3.5 showed particularly limited performance on domain-specific content. Both models shared similar error patterns, with incorrect response rates ranging from 18-24% across regions.ConclusionDespite GPT-4's improved performance, both models display notable limitations in occupational health applications. To enhance reliability, four strategies are proposed: formal validation, continuous training, error analysis, and regional adaptation. |
|---|---|
| ISSN: | 1875-9270 |
| DOI: | 10.1177/10519815251348355 |