Study design indexing in transition: a focused comparison of manual NLM indexing versus transformer-based automated models

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.

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.

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.

TM may have value for identifying articles exhibiting study designs, which is important for clinical decision-making and evidence syntheses.

NLM's cohort studies indexing is unreliable as a gold standard for building automated systems, warranting efforts to create a new manually annotated corpus.