EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Automated Classification of Free-Text Radiology Reports: Using Different Feature Extraction Methods to Identify Fractures of the Distal Fibula

Cornelia L A Dewald iD, Alina Balandis, Lena S Becker, Jan B Hinrichs, Christian von Falck, Frank K Wacker, Hans Laser, Svetlana Gerbel, Hinrich B Winther, Johanna Apfel-Starke

RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren · 01.08.2023 · 195 (08) · 713-719

DOI: 10.1055/a-2061-6562 ↗

Kurz gefasst

Fachartikel in der Zeitschrift RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren, erschienen am 01.08.2023. Verfasst von Cornelia L A Dewald und 9 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Diagnostic and Interventional Radiology, Hannover Medical School, Hannover, Germany. Hauptthemen laut MEDLINE: Fibula, Radiology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Radiology reports mostly contain free-text, which makes it challenging to obtain structured data. Natural language processing (NLP) techniques transform free-text reports into machine-readable document vectors that are important for creating reliable, scalable methods for data analysis. The aim of this study is to classify unstructured radiograph reports according to fractures of the distal fibula and to find the best text mining method. Materials & Methods We established a novel German language report dataset: a designated search engine was used to identify radiographs of the ankle and the reports were manually labeled according to fractures of the distal fibula. This data was used to establish a machine learning pipeline, which implemented the text representation methods bag-of-words (BOW), term frequency-inverse document frequency (TF-IDF), principal component analysis (PCA), non-negative matrix factorization (NMF), latent Dirichlet allocation (LDA), and document embedding (doc2vec). The extracted document vectors were used to train neural networks (NN), support vector machines (SVM), and logistic regression (LR) to recognize distal fibula fractures. The results were compared via cross-tabulations of the accuracy (acc) and area under the curve (AUC).

Results

In total, 3268 radiograph reports were included, of which 1076 described a fracture of the distal fibula. Comparison of the text representation methods showed that BOW achieved the best results (AUC = 0.98; acc = 0.97), followed by TF-IDF (AUC = 0.97; acc = 0.96), NMF (AUC = 0.93; acc = 0.92), PCA (AUC = 0.92; acc = 0.9), LDA (AUC = 0.91; acc = 0.89) and doc2vec (AUC = 0.9; acc = 0.88). When comparing the different classifiers, NN (AUC = 0,91) proved to be superior to SVM (AUC = 0,87) and LR (AUC = 0,85).

Conclusion

An automated classification of unstructured reports of radiographs of the ankle can reliably detect findings of fractures of the distal fibula. A particularly suitable feature extraction method is the BOW model. Key Points: Citation Format

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

FibulaRadiologyRadiographyAlgorithmsMachine LearningNatural Language Processing

Autor:innen und Institutionen

  • Institute for Diagnostic and Interventional Radiology, Hannover Medical School, Hannover, Germany.
  • Centre for Information Management (ZIMt), Hannover Medical School, Hannover, Germany.

ORCID-Profile: Cornelia L A Dewald

Zitieren

APA

Dewald, C. L. A., Balandis, A., Becker, L. S., Hinrichs, J. B., von Falck, C., Wacker, F. K., Laser, H., Gerbel, S., Winther, H. B., & Apfel-Starke, J. (2023). Automated Classification of Free-Text Radiology Reports: Using Different Feature Extraction Methods to Identify Fractures of the Distal Fibula. RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren, 195(08), 713-719. https://doi.org/10.1055/a-2061-6562

Vancouver

Dewald CLA, Balandis A, Becker LS, Hinrichs JB, von Falck C, Wacker FK, et al. Automated Classification of Free-Text Radiology Reports: Using Different Feature Extraction Methods to Identify Fractures of the Distal Fibula. RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren. 2023;195(08):713-719. doi:10.1055/a-2061-6562

BibTeX
@article{Dewald2023,
  author = {Dewald, Cornelia L A and Balandis, Alina and Becker, Lena S and Hinrichs, Jan B and von Falck, Christian and Wacker, Frank K and Laser, Hans and Gerbel, Svetlana and Winther, Hinrich B and Apfel-Starke, Johanna},
  title = {Automated Classification of Free-Text Radiology Reports: Using Different Feature Extraction Methods to Identify Fractures of the Distal Fibula},
  journal = {RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren},
  year = {2023},
  volume = {195},
  number = {08},
  pages = {713--719},
  doi = {10.1055/a-2061-6562}
}
Kostenlos starten →