EUVIMEDEUVIMED entdecken
Open Access

Positive act of reporting negative results in large language model research: a call for transparency

Satvik Tripathi, Dana Alkhulaifat, Tessa S Cook

Journal of the American Medical Informatics Association · 2026

DOI: 10.1093/jamia/ocaf221 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, 2026. Verfasst von Satvik Tripathi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, United States. Hauptthemen laut MEDLINE: Large Language Models, Biomedical Research. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 15 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To highlight the importance of reporting negative results in large language model (LLM) research, particularly as these systems are increasingly integrated into healthcare. Potential LLMs offer transformative capabilities in text generation, summarization, and clinical decision support. Transparent documentation of both successes and failures can accelerate innovation, improve reproducibility, and guide safe deployment. Caution Publication bias toward positive findings conceals model limitations, biases, and reproducibility challenges. In healthcare, underreporting failures risks patient safety, ethical lapses, and wasted resources. Structural barriers, including a lack of standards and limited funding for failure analysis, perpetuate this cycle.

Conclusions

Negative results should be recognized as valuable contributions that delineate the boundaries of LLM applicability. Structured reporting, educational initiatives, and stronger incentives for transparency are essential to ensure responsible, equitable, and trustworthy use of LLMs in healthcare.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsBiomedical ResearchHumansReproducibility of Results

Stichwörter der Autor:innen

large language modelmedical researchreproducibilitytransparency

Autor:innen und Institutionen

  • Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, United States.
  • Department of Radiology, Clinical Research Core, Children's Hospital of Philadelphia, Philadelphia, PA 19104, United States.
  • Department of Radiology, Emory University School of Medicine, Atlanta, GA 30307, United States.
  • Center for Practice Transformation in Radiology, Department of Radiology, Perelman School of Medicine at University of Pennsylvania, Philadelphia, PA 19104, United States.
  • Commission on Patient- and Family-Centered Care, American College of Radiology, Reston, VA 20191, United States.

Zitieren

APA

Tripathi, S., Alkhulaifat, D., & Cook, T. S. (2026). Positive act of reporting negative results in large language model research: a call for transparency. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocaf221

Vancouver

Tripathi S, Alkhulaifat D, Cook TS. Positive act of reporting negative results in large language model research: a call for transparency. Journal of the American Medical Informatics Association. 2026. doi:10.1093/jamia/ocaf221

BibTeX
@article{Tripathi2026,
  author = {Tripathi, Satvik and Alkhulaifat, Dana and Cook, Tessa S},
  title = {Positive act of reporting negative results in large language model research: a call for transparency},
  journal = {Journal of the American Medical Informatics Association},
  year = {2026},
  doi = {10.1093/jamia/ocaf221}
}
Kostenlos starten →