Study design indexing in transition: a focused comparison of manual NLM indexing versus transformer-based automated models
JAMIA Open · 09.09.2026 · 9 (5)
DOI: 10.1093/jamiaopen/ooag197 ↗Kurz gefasst
Fachartikel in der Zeitschrift JAMIA Open, online erschienen am 29.10.2026. Verfasst von Puranjani Das und 11 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL 61820, United States. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NLM NIH HHS, National Institutes of Health, National Library of Medicine.
Abstract (Originalsprache)
Objectives
We sought to evaluate the accuracy and suitability of a transformer-based model (TM) for indexing clinical study designs, in comparison to National Library of Medicine (NLM) indexing. Materials and methods For 2016 (manual NLM) and 2025 (automated NLM) published articles, we conducted a limited evaluation of the TM model, with articles that received the most confident predictions, with which NLM assignments disagreed. Ground truth was established through independent dual annotation for 4 prominent study designs: cohort, case-control, cross-sectional, and case report.
Results
For 3 designs (case-control, case report, and cross-sectional), the articles having the top 100 predictive TM scores (when NLM failed to assign that design) were judged to exhibit that design in the great majority (86%-100%) of cases. Conversely, the articles having the lowest 100 predictive TM scores (when NLM did assign the study design) exhibited the design only in relatively few (0%-21%) of cases. The most confident predictions of the TM model were highly accurate and not redundant with automated NLM indexing; the exception was cohort studies articles, in which both TM and NLM labels showed high error rates of both omission and commission.
Discussion
TM may have value for identifying articles exhibiting study designs, which is important for clinical decision-making and evidence syntheses.
Conclusion
NLM’s cohort studies indexing is unreliable as a gold standard for building automated systems, warranting efforts to create a new manually annotated corpus.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL 61820, United States.
- Information School, University of Wisconsin-Madison, Madison, WI 53706, United States.
- Department of Epidemiology, University of North Carolina, Chapel Hill, NC 27514, United States.
- Department of Psychiatry, University of Illinois at Chicago, Chicago, IL 60612, United States.
ORCID-Profile: Puranjani Das, Jodi Schneider, Halil Kilicoglu, Neil R Smalheiser
Förderung
- NLM NIH HHS
- National Institutes of Health
- National Library of Medicine
Zitieren
APA
Das, P., Schneider, J., Mayo-Wilson, E., Kilicoglu, H., Menke, J. D., Nam, D., Ninan, K., Oberste, J. P., Troy, A. M., Ying, X., Holt, A. W., & Smalheiser, N. R. (2026). Study design indexing in transition: a focused comparison of manual NLM indexing versus transformer-based automated models. JAMIA Open, 9(5). https://doi.org/10.1093/jamiaopen/ooag197
Vancouver
Das P, Schneider J, Mayo-Wilson E, Kilicoglu H, Menke JD, Nam D, et al. Study design indexing in transition: a focused comparison of manual NLM indexing versus transformer-based automated models. JAMIA Open. 2026;9(5). doi:10.1093/jamiaopen/ooag197
BibTeX
@article{Das2026,
author = {Das, Puranjani and Schneider, Jodi and Mayo-Wilson, Evan and Kilicoglu, Halil and Menke, Joe D and Nam, Dongin and Ninan, Kiran and Oberste, Jean-Pierre and Troy, Ang Michael and Ying, Xiangji and Holt, Arthur W and Smalheiser, Neil R},
title = {Study design indexing in transition: a focused comparison of manual NLM indexing versus transformer-based automated models},
journal = {JAMIA Open},
year = {2026},
volume = {9},
number = {5},
doi = {10.1093/jamiaopen/ooag197}
}
EUVIMED