EUVIMEDEUVIMED entdecken
Open Access

Near Real-time Natural Language Processing for the Extraction of Abdominal Aortic Aneurysm Diagnoses From Radiology Reports: Algorithm Development and Validation Study

Simon Gaviria-Valencia iD, Sean P Murphy iD, Vinod C Kaggal iD, Robert D McBane Ii iD, Thom W Rooke iD, Rajeev Chaudhry iD, Mateo Alzate-Aguirre iD, Adelaide M Arruda-Olson iD

JMIR Medical Informatics · 24.02.2023 · 11 · e40964

DOI: 10.2196/40964 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Medical Informatics, online erschienen am 24.02.2023. Verfasst von Simon Gaviria-Valencia und 7 weiteren Autor:innen. Beteiligte Einrichtung: Divisions of Preventive Cardiology and Cardiovascular Ultrasound, Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, United States. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Management of abdominal aortic aneurysms (AAAs) requires serial imaging surveillance to evaluate the aneurysm dimension. Natural language processing (NLP) has been previously developed to retrospectively identify patients with AAA from electronic health records (EHRs). However, there are no reported studies that use NLP to identify patients with AAA in near real-time from radiology reports.

Objective

This study aims to develop and validate a rule-based NLP algorithm for near real-time automatic extraction of AAA diagnosis from radiology reports for case identification.

Methods

The AAA-NLP algorithm was developed and deployed to an EHR big data infrastructure for near real-time processing of radiology reports from May 1, 2019, to September 2020. NLP extracted named entities for AAA case identification and classified subjects as cases and controls. The reference standard to assess algorithm performance was a manual review of processed radiology reports by trained physicians following standardized criteria. Reviewers were blinded to the diagnosis of each subject. The AAA-NLP algorithm was refined in 3 successive iterations. For each iteration, the AAA-NLP algorithm was modified based on performance compared to the reference standard.

Results

A total of 360 reports were reviewed, of which 120 radiology reports were randomly selected for each iteration. At each iteration, the AAA-NLP algorithm performance improved. The algorithm identified AAA cases in near real-time with high positive predictive value (0.98), sensitivity (0.95), specificity (0.98), F1 score (0.97), and accuracy (0.97).

Conclusions

Implementation of NLP for accurate identification of AAA cases from radiology reports with high performance in near real time is feasible. This NLP technique will support automated input for patient care and clinical decision support tools for the management of patients with AAA.

Schlagwörter

Stichwörter der Autor:innen

abdominal aortic aneurysmalgorithmbig dataelectronic health recordmedical recordsnatural language processingradiologyradiology reports

Autor:innen und Institutionen

  • Divisions of Preventive Cardiology and Cardiovascular Ultrasound, Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, United States.
  • Advanced Analytics Services Unit (Natural Language Processing), Department of Information Technology, Mayo Clinic, Rochester, MN, United States.
  • Enterprise Technology Services (Natural Language Processing), Department of Information Technology, Mayo Clinic, Rochester, MN, United States.
  • Gonda Vascular Center, Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, United States.
  • Department of Internal Medicine, Mayo Clinic, Rochester, MN, United States.

ORCID-Profile: Simon Gaviria-Valencia, Sean P Murphy, Vinod C Kaggal, Robert D McBane Ii, Thom W Rooke, Rajeev Chaudhry, Mateo Alzate-Aguirre, Adelaide M Arruda-Olson

Zitieren

APA

Gaviria-Valencia, S., Murphy, S. P., Kaggal, V. C., McBane Ii, R. D., Rooke, T. W., Chaudhry, R., Alzate-Aguirre, M., & Arruda-Olson, A. M. (2023). Near Real-time Natural Language Processing for the Extraction of Abdominal Aortic Aneurysm Diagnoses From Radiology Reports: Algorithm Development and Validation Study. JMIR Medical Informatics, 11, e40964. https://doi.org/10.2196/40964

Vancouver

Gaviria-Valencia S, Murphy SP, Kaggal VC, McBane Ii RD, Rooke TW, Chaudhry R, et al. Near Real-time Natural Language Processing for the Extraction of Abdominal Aortic Aneurysm Diagnoses From Radiology Reports: Algorithm Development and Validation Study. JMIR Medical Informatics. 2023;11:e40964. doi:10.2196/40964

BibTeX
@article{GaviriaValencia2023,
  author = {Gaviria-Valencia, Simon and Murphy, Sean P and Kaggal, Vinod C and McBane Ii, Robert D and Rooke, Thom W and Chaudhry, Rajeev and Alzate-Aguirre, Mateo and Arruda-Olson, Adelaide M},
  title = {Near Real-time Natural Language Processing for the Extraction of Abdominal Aortic Aneurysm Diagnoses From Radiology Reports: Algorithm Development and Validation Study},
  journal = {JMIR Medical Informatics},
  year = {2023},
  volume = {11},
  pages = {e40964},
  doi = {10.2196/40964}
}
Kostenlos starten →