EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI versus human coding of NIH grant abstracts

Sarah A Alkhatib iD, Nadiya Jiwa iD, Dallin Judd, Justin M Luningham, Ginnie Sawyer-Morris, Merve Ulukaya, Todd Molfenter, Faye S Taxman, Scott T Walters

PLOS One · 2026

DOI: 10.1371/journal.pone.0343857 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Sarah A Alkhatib und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Population & Community Health, College of Public Health, University of North Texas Health, Fort Worth, Texas, United States of America. Hauptthemen laut MEDLINE: National Institutes of Health (U.S.), Abstracting and Indexing. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) are increasingly used for qualitative analysis in substance use research, yet their performance relative to human coders remains underexplored. This study compares ChatGPT-4.0 with human coders in performing qualitative coding tasks using NIH grant abstracts as a test case, focusing on the identification and description of research innovations. Using a sample of NIH HEAL Initiative grant abstracts related to opioid overdose prevention, a total of 125 abstracts were independently coded by ChatGPT and humans to generate innovation descriptions, which were then evaluated by both human raters and ChatGPT for depth/detail and relevance/completeness using 5-point Likert scales. Identical instructions were used across all coding and evaluation stages. ChatGPT-generated descriptions were consistently rated higher than human-generated descriptions on both dimensions. Human evaluators rated ChatGPT outputs at an average of 4.47 for both depth/detail and relevance/completeness, compared to 3.33 and 3.24 for human outputs, respectively (F(1,176)=133.9, p < 0.001). These findings suggest that LLMs, when carefully prompted, can enhance the efficiency and quality of qualitative research evaluation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

National Institutes of Health (U.S.)Abstracting and IndexingHumansUnited StatesLarge Language ModelsGenerative Artificial Intelligence

Autor:innen und Institutionen

  • Department of Population & Community Health, College of Public Health, University of North Texas Health, Fort Worth, Texas, United States of America.
  • Texas College of Osteopathic Medicine, University of North Texas Health, Fort Worth, Texas, United States of America.
  • College of Science & Engineering, Texas Christian University, Fort Worth, Texas, United States of America.
  • Friends Research Institute, Baltimore, Maryland, United States of America.
  • George Mason University, Schar School of Policy and Government, Fairfax, Virginia, United States of America.
  • University of Wisconsin Center for Health Enhancement Systems Studies, Department of Industrial & Systems Engineering, Madison, Wisconsin, United States of America.

ORCID-Profile: Sarah A Alkhatib, Nadiya Jiwa

Zitieren

APA

Alkhatib, S. A., Jiwa, N., Judd, D., Luningham, J. M., Sawyer-Morris, G., Ulukaya, M., Molfenter, T., Taxman, F. S., & Walters, S. T. (2026). AI versus human coding of NIH grant abstracts. PLOS One. https://doi.org/10.1371/journal.pone.0343857

Vancouver

Alkhatib SA, Jiwa N, Judd D, Luningham JM, Sawyer-Morris G, Ulukaya M, et al. AI versus human coding of NIH grant abstracts. PLOS One. 2026. doi:10.1371/journal.pone.0343857

BibTeX
@article{Alkhatib2026,
  author = {Alkhatib, Sarah A and Jiwa, Nadiya and Judd, Dallin and Luningham, Justin M and Sawyer-Morris, Ginnie and Ulukaya, Merve and Molfenter, Todd and Taxman, Faye S and Walters, Scott T},
  title = {AI versus human coding of NIH grant abstracts},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0343857}
}
Kostenlos starten →