Comparative analysis of machine learning algorithms for computer-assisted reporting based on fully automated cross-lingual RadLex mappings
Abstract 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 algo...
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/12348a5318d740d1a6395bfc7358ede7 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | Abstract 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. |
|---|