EUVIMEDEUVIMED entdecken
Open Access

Identifying Incident Medication‐Related Osteonecrosis of the Jaw and Antiresorptive Drug Holidays Using Natural Language Processing on Clinical Notes in Men and Women Prescribed Bisphosphonates or Denosumab for Fracture Prevention

Emily Budde, Rachel E Elam iD, Laura D Carbone, Brian Le, Thomas B Dodson, Peter J Gerngross, Howard A Fink, Robert A Adler, Joan C Lo, John T Schousboe, Frances Weaver, Dezon Finch

Arthritis Care & Research · 14.10.2026

DOI: 10.1002/acr.80173 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Arthritis Care & Research, online erschienen am 14.10.2026. Verfasst von Emily Budde und 11 weiteren Autor:innen. Beteiligte Einrichtung: Edward Hines Jr. Veterans Affairs Hospital, Hines, Illinois. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIA NIH HHS, National Institute on Aging.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Medication‐related osteonecrosis of the jaw (MRONJ) is a rare complication of antiresorptive therapy for osteoporosis, with risk potentially influenced by “drug holidays” around dentoalveolar procedures. MRONJ risk is higher in rheumatic diseases. Epidemiologic studies are limited by poor administrative code performance for MRONJ identification and lack of structured pharmacy data capturing drug holidays. We developed and validated a natural language processing (NLP) algorithm to classify MRONJ and detect drug holidays from free‐text clinical notes in electronic health records (EHRs).

Methods

Using US Veterans Health Administration EHRs, we identified adults aged ≥50 years old with at least one filled prescription for a bisphosphonate or denosumab for fracture prevention (October 1, 1999, to December 31, 2022). An NLP codebook defined 11 targets with 16 attributes. Two annotators independently labeled notes to create a reference set (n = 870; 200 held out for validation) and an independent validation set (n = 100) for performance assessment (precision, recall, and F‐measure). A decision tree–based machine‐learning model used NLP‐extracted features to classify MRONJ. Drug holiday was an NLP target directly.

Results

The reference set included 6,421 annotations, informing a curated vocabulary of >1,350 terms. For MRONJ classification excluding unclassifiable outputs across all validation notes, precision was 1.00 (95% confidence interval [CI] 0.86–1.00), recall 0.96 (95% CI 0.80–1.00), and F‐measure 0.95 (95% CI 0.88–1.00). For drug holiday detection in the held‐out validation set, precision was 0.90 (95% CI 0.83–0.95), recall 0.98 (95% CI 0.93–1.00), and F‐measure 0.94.

Conclusion

We developed an NLP algorithm that is sufficiently accurate in classifying MRONJ and detecting drug holidays to be a promising tool for future studies, including in people with rheumatic diseases. image

Autor:innen und Institutionen

  • Edward Hines Jr. Veterans Affairs Hospital, Hines, Illinois.
  • Medical College of Georgia at Augusta University, Augusta, Georgia.
  • Veterans Affairs Augusta Health Care System, Augusta, Georgia.
  • University of Washington, Seattle, Washington.
  • Veterans Health Administration Office of Dentistry, Washington, DC.
  • Minneapolis Veterans Affairs Health Care System, Minneapolis, Minnesota.

ORCID-Profile: Rachel E Elam

Förderung

  • NIA NIH HHS
  • National Institute on Aging

Zitieren

APA

Budde, E., Elam, R. E., Carbone, L. D., Le, B., Dodson, T. B., Gerngross, P. J., Fink, H. A., Adler, R. A., Lo, J. C., Schousboe, J. T., Weaver, F., & Finch, D. (2026). Identifying Incident Medication‐Related Osteonecrosis of the Jaw and Antiresorptive Drug Holidays Using Natural Language Processing on Clinical Notes in Men and Women Prescribed Bisphosphonates or Denosumab for Fracture Prevention. Arthritis Care & Research. https://doi.org/10.1002/acr.80173

Vancouver

Budde E, Elam RE, Carbone LD, Le B, Dodson TB, Gerngross PJ, et al. Identifying Incident Medication‐Related Osteonecrosis of the Jaw and Antiresorptive Drug Holidays Using Natural Language Processing on Clinical Notes in Men and Women Prescribed Bisphosphonates or Denosumab for Fracture Prevention. Arthritis Care & Research. 2026. doi:10.1002/acr.80173

BibTeX
@article{Budde2026,
  author = {Budde, Emily and Elam, Rachel E and Carbone, Laura D and Le, Brian and Dodson, Thomas B and Gerngross, Peter J and Fink, Howard A and Adler, Robert A and Lo, Joan C and Schousboe, John T and Weaver, Frances and Finch, Dezon},
  title = {Identifying Incident Medication‐Related Osteonecrosis of the Jaw and Antiresorptive Drug Holidays Using Natural Language Processing on Clinical Notes in Men and Women Prescribed Bisphosphonates or Denosumab for Fracture Prevention},
  journal = {Arthritis Care & Research},
  year = {2026},
  doi = {10.1002/acr.80173}
}
Kostenlos starten →