EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Cannabis Use Documentation within the Electronic Health Record: A Use Case for Natural Language Processing Methods

Apoorva M Pradhan, Vishal A Shetty, Christina M Gregor, Jove H Graham, Lorraine Tusing, Annemarie G Hirsch, Eric Hall, Vanessa Troiani, Mellar P Davis, Donielle L Beiler, Katrina M Romagnoli, Chadd K Kraus und 2 weitere

Medical Cannabis and Cannabinoids · 27.06.2026 · 9 (1) · 235-249

DOI: 10.1159/000553307 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Cannabis and Cannabinoids, online erschienen am 27.06.2026. Verfasst von Apoorva M Pradhan und 13 weiteren Autor:innen. Beteiligte Einrichtung: Center for Pharmacy Innovation and Outcomes, Geisinger College of Health Sciences, Danville, PA, USA. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Recreational and medical cannabis use (CU) information is often available within the electronic health record (EHR) in a format that is impractical for health care provider use. Transformation of free-text EHR documentation in notes to discrete elements is possible using natural language processing (NLP) and has the potential to characterize CU efficiently. The objective of this study was to develop an NLP algorithm to identify CU documentation within unstructured EHR clinical notes.

Methods

We identified EHR notes with cannabis-related terminologies through a keyword search among all Geisinger patients with at least one encounter between January 1, 2013 and June 30, 2022. We trained four NLP models to classify CU documentation within notes into six categories based on time, context, and reliability, as identified through manual annotation. We compared the demographic characteristics of patients with a positive CU classification using the best-performing model to those of the studied sample.

Results

Of the over 1.7 million eligible patients, 150,726 (8.6%) were flagged as cannabis users. Bio-ClinicalBERT, a transformer-based NLP model, achieved close to human performance in classifying CU (weighted precision = 91.4, recall = 93.3, and F score = 92.4). An unadjusted analysis showed that cannabis users had higher body mass index and were at least nine-fold more likely to use tobacco, alcohol, or illicit substances.

Conclusion

Our study evaluated the prevalence of CU documentation across the entire corpus of EHR notes data based on available data without population segmentation over a 9.5-year period. The NLP methodologies used achieved performance close to that of human annotation and laid the foundation for identifying and classifying CU within unstructured data sources, with future applications in research and patient care.

Schlagwörter

Stichwörter der Autor:innen

Electronic health record notesMachine learningMarijuanaUnstructured data

Autor:innen und Institutionen

  • Center for Pharmacy Innovation and Outcomes, Geisinger College of Health Sciences, Danville, PA, USA.
  • Department of Pharmacy, Geisinger College of Health Sciences, Danville, PA, USA.
  • Department of Health Promotion and Policy, University of Massachusetts, Amherst, MA, USA.
  • Department of Population Health Sciences, Geisinger College of Health Sciences, Danville, PA, USA.
  • Biomedical Research Informatics Center, Nemours Children's Health, Wilmington, DE, USA.
  • Department of Developmental Medicine, Geisinger College of Health Sciences, Danville, PA, USA.

Zitieren

APA

Pradhan, A. M., Shetty, V. A., Gregor, C. M., Graham, J. H., Tusing, L., Hirsch, A. G., Hall, E., Troiani, V., Davis, M. P., Beiler, D. L., Romagnoli, K. M., Kraus, C. K., Piper, B. J., & Wright, E. A. (2026). Cannabis Use Documentation within the Electronic Health Record: A Use Case for Natural Language Processing Methods. Medical Cannabis and Cannabinoids, 9(1), 235-249. https://doi.org/10.1159/000553307

Vancouver

Pradhan AM, Shetty VA, Gregor CM, Graham JH, Tusing L, Hirsch AG, et al. Cannabis Use Documentation within the Electronic Health Record: A Use Case for Natural Language Processing Methods. Medical Cannabis and Cannabinoids. 2026;9(1):235-249. doi:10.1159/000553307

BibTeX
@article{Pradhan2026,
  author = {Pradhan, Apoorva M and Shetty, Vishal A and Gregor, Christina M and Graham, Jove H and Tusing, Lorraine and Hirsch, Annemarie G and Hall, Eric and Troiani, Vanessa and Davis, Mellar P and Beiler, Donielle L and Romagnoli, Katrina M and Kraus, Chadd K and Piper, Brian J and Wright, Eric A},
  title = {Cannabis Use Documentation within the Electronic Health Record: A Use Case for Natural Language Processing Methods},
  journal = {Medical Cannabis and Cannabinoids},
  year = {2026},
  volume = {9},
  number = {1},
  pages = {235--249},
  doi = {10.1159/000553307}
}
Kostenlos starten →