> Details

Maros, Máté E. [Author]; Cho, Chang Gyu [Author]; Junge, Andreas Georg [Author]; Kämpgen, Benedikt [Author]; Saase, Victor [Author]; Siegel, Fabian [Author]; Trinkmann, Frederik [Author]; Ganslandt, Thomas [Author]; Groden, Christoph [Author]; Wenz, Holger [Author]

Comparative analysis of machine learning algorithms for computer-assisted reporting based on fully automated cross-lingual RadLex mappings

Reference
management

Bookmarks

Remove from
bookmarks

Share this on Whatsapp

Close

Bookmarks



You can manage bookmarks using lists, please log in to your user account for this.
  • Media type: E-Article
  • Title: Comparative analysis of machine learning algorithms for computer-assisted reporting based on fully automated cross-lingual RadLex mappings
  • Contributor: Maros, Máté E. [VerfasserIn]; Cho, Chang Gyu [VerfasserIn]; Junge, Andreas Georg [VerfasserIn]; Kämpgen, Benedikt [VerfasserIn]; Saase, Victor [VerfasserIn]; Siegel, Fabian [VerfasserIn]; Trinkmann, Frederik [VerfasserIn]; Ganslandt, Thomas [VerfasserIn]; Groden, Christoph [VerfasserIn]; Wenz, Holger [VerfasserIn]
  • imprint: 09 March 2021
  • Published in: Scientific reports ; 11(2021), Artikel-ID 5529, Seite 1-18
  • Language: English
  • DOI: 10.1038/s41598-021-85016-9
  • ISSN: 2045-2322
  • Identifier:
  • Origination:
  • Footnote:
  • Description: Computer-assisted reporting (CAR) tools were suggested to improve radiology report quality by context-sensitively recommending key imaging biomarkers. However, studies evaluating machine learning (ML) algorithms on cross-lingual ontological (RadLex) mappings for developing embedded CAR algorithms are lacking. Therefore, we compared ML algorithms developed on human expert-annotated features against those developed on fully automated cross-lingual (German to English) RadLex mappings using 206 CT reports of suspected stroke. Target label was whether the Alberta Stroke Programme Early CT Score (ASPECTS) should have been provided (yes/no:154/52). We focused on probabilistic outputs of ML-algorithms including tree-based methods, elastic net, support vector machines (SVMs) and fastText (linear classifier), which were evaluated in the same 5 × fivefold nested cross-validation framework. This allowed for model stacking and classifier rankings. Performance was evaluated using calibration metrics (AUC, brier score, log loss) and -plots. Contextual ML-based assistance recommending ASPECTS was feasible. SVMs showed the highest accuracies both on human-extracted- (87%) and RadLex features (findings:82.5%; impressions:85.4%). FastText achieved the highest accuracy (89.3%) and AUC (92%) on impressions. Boosted trees fitted on findings had the best calibration profile. Our approach provides guidance for choosing ML classifiers for CAR tools in fully automated and language-agnostic fashion using bag-of-RadLex terms on limited expert-labelled training data.
  • Access State: Open Access