EUVIMEDEUVIMED entdecken
Open Access

Automated deidentification of radiology reports combining transformer and “hide in plain sight” rule-based methods

Pierre J Chambon iD, Christopher Wu, Jackson M Steinkamp, Jason Adleberg, Tessa S Cook, Curtis P Langlotz

Journal of the American Medical Informatics Association · 18.01.2023 · 30 (2) · 318-328

DOI: 10.1093/jamia/ocac219 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 23.11.2022. Verfasst von Pierre J Chambon und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Stanford University, Stanford, California, USA. Hauptthemen laut MEDLINE: Data Anonymization, Radiology. Die Arbeit wurde bisher 51-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHLBI NIH HHS, NIH HHS, The Medical Imaging Data Resource Center.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To develop an automated deidentification pipeline for radiology reports that detect protected health information (PHI) entities and replaces them with realistic surrogates “hiding in plain sight.” Materials and Methods In this retrospective study, 999 chest X-ray and CT reports collected between November 2019 and November 2020 were annotated for PHI at the token level and combined with 3001 X-rays and 2193 medical notes previously labeled, forming a large multi-institutional and cross-domain dataset of 6193 documents. Two radiology test sets, from a known and a new institution, as well as i2b2 2006 and 2014 test sets, served as an evaluation set to estimate model performance and to compare it with previously released deidentification tools. Several PHI detection models were developed based on different training datasets, fine-tuning approaches and data augmentation techniques, and a synthetic PHI generation algorithm. These models were compared using metrics such as precision, recall and F1 score, as well as paired samples Wilcoxon tests.

Results

Our best PHI detection model achieves 97.9 F1 score on radiology reports from a known institution, 99.6 from a new institution, 99.5 on i2b2 2006, and 98.9 on i2b2 2014. On reports from a known institution, it achieves 99.1 recall of detecting the core of each PHI span.

Discussion

Our model outperforms all deidentifiers it was compared to on all test sets as well as human labelers on i2b2 2014 data. It enables accurate and automatic deidentification of radiology reports.

Conclusions

A transformer-based deidentification pipeline can achieve state-of-the-art performance for deidentifying radiology reports and other medical documents.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Data AnonymizationRadiologyHumansRetrospective StudiesAlgorithmsHealth FacilitiesNatural Language Processing

Stichwörter der Autor:innen

NLPdeidentificationmachine learningradiologytransformer

Autor:innen und Institutionen

  • Department of Radiology, Stanford University, Stanford, California, USA.
  • Department of Applied Mathematics and Engineering, Paris-Saclay University, Ecole Centrale Paris, Paris, France.
  • Department of Radiology, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
  • Department of Radiology, Mount Sinai Health System, New York, New York, USA.

ORCID-Profile: Pierre J Chambon

Förderung

  • NHLBI NIH HHS
  • NIH HHS
  • The Medical Imaging Data Resource Center
  • National Institute of Biomedical Imaging and Bioengineering
  • NIBIB
  • National Institutes of Health
  • Independence Blue Cross

Zitieren

APA

Chambon, P. J., Wu, C., Steinkamp, J. M., Adleberg, J., Cook, T. S., & Langlotz, C. P. (2023). Automated deidentification of radiology reports combining transformer and “hide in plain sight” rule-based methods. Journal of the American Medical Informatics Association, 30(2), 318-328. https://doi.org/10.1093/jamia/ocac219

Vancouver

Chambon PJ, Wu C, Steinkamp JM, Adleberg J, Cook TS, Langlotz CP. Automated deidentification of radiology reports combining transformer and “hide in plain sight” rule-based methods. Journal of the American Medical Informatics Association. 2023;30(2):318-328. doi:10.1093/jamia/ocac219

BibTeX
@article{Chambon2023,
  author = {Chambon, Pierre J and Wu, Christopher and Steinkamp, Jackson M and Adleberg, Jason and Cook, Tessa S and Langlotz, Curtis P},
  title = {Automated deidentification of radiology reports combining transformer and “hide in plain sight” rule-based methods},
  journal = {Journal of the American Medical Informatics Association},
  year = {2023},
  volume = {30},
  number = {2},
  pages = {318--328},
  doi = {10.1093/jamia/ocac219}
}
Kostenlos starten →