Comparative analysis of machine learning algorithms for computer-assisted reporting based on fully automated cross-lingual RadLex mappings
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 ar...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
09 March 2021
|
| In: |
Scientific reports
Year: 2021, Jahrgang: 11, Pages: 1-18 |
| ISSN: | 2045-2322 |
| DOI: | 10.1038/s41598-021-85016-9 |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.1038/s41598-021-85016-9 Verlag, kostenfrei, Volltext: https://www.nature.com/articles/s41598-021-85016-9 
|
| Verfasserangaben: | Máté E. Maros, Chang Gyu Cho, Andreas G. Junge, Benedikt Kämpgen, Victor Saase, Fabian Siegel, Frederik Trinkmann, Thomas Ganslandt, Christoph Groden and Holger Wenz |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1766546102 | ||
| 003 | DE-627 | ||
| 005 | 20230427164256.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 210812s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1038/s41598-021-85016-9 |2 doi | |
| 035 | |a (DE-627)1766546102 | ||
| 035 | |a (DE-599)KXP1766546102 | ||
| 035 | |a (OCoLC)1341420477 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Maros, Máté E. |d 1986- |e VerfasserIn |0 (DE-588)1144379407 |0 (DE-627)1004715153 |0 (DE-576)495364827 |4 aut | |
| 245 | 1 | 0 | |a Comparative analysis of machine learning algorithms for computer-assisted reporting based on fully automated cross-lingual RadLex mappings |c Máté E. Maros, Chang Gyu Cho, Andreas G. Junge, Benedikt Kämpgen, Victor Saase, Fabian Siegel, Frederik Trinkmann, Thomas Ganslandt, Christoph Groden and Holger Wenz |
| 264 | 1 | |c 09 March 2021 | |
| 300 | |a 18 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 12.08.2021 | ||
| 520 | |a 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. | ||
| 700 | 1 | |a Cho, Chang Gyu |d 1989- |e VerfasserIn |0 (DE-588)1238814832 |0 (DE-627)1766536050 |4 aut | |
| 700 | 1 | |a Junge, Andreas Georg |e VerfasserIn |0 (DE-588)1238815928 |0 (DE-627)1766537189 |4 aut | |
| 700 | 1 | |a Kämpgen, Benedikt |e VerfasserIn |4 aut | |
| 700 | 1 | |a Saase, Victor |d 1985- |e VerfasserIn |0 (DE-588)1214458068 |0 (DE-627)172550457X |4 aut | |
| 700 | 1 | |a Siegel, Fabian |d 1979- |e VerfasserIn |0 (DE-588)1034567551 |0 (DE-627)745868037 |0 (DE-576)382210514 |4 aut | |
| 700 | 1 | |a Trinkmann, Frederik |d 1983- |e VerfasserIn |0 (DE-588)142731773 |0 (DE-627)704298066 |0 (DE-576)332907406 |4 aut | |
| 700 | 1 | |a Ganslandt, Thomas |d 1969- |e VerfasserIn |0 (DE-588)124367720 |0 (DE-627)08581623X |0 (DE-576)294139915 |4 aut | |
| 700 | 1 | |a Groden, Christoph |e VerfasserIn |4 aut | |
| 700 | 1 | |a Wenz, Holger |e VerfasserIn |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Scientific reports |d [London] : Springer Nature, 2011 |g 11(2021), Artikel-ID 5529, Seite 1-18 |h Online-Ressource |w (DE-627)663366712 |w (DE-600)2615211-3 |w (DE-576)346641179 |x 2045-2322 |7 nnas |a Comparative analysis of machine learning algorithms for computer-assisted reporting based on fully automated cross-lingual RadLex mappings |
| 773 | 1 | 8 | |g volume:11 |g year:2021 |g elocationid:5529 |g pages:1-18 |g extent:18 |a Comparative analysis of machine learning algorithms for computer-assisted reporting based on fully automated cross-lingual RadLex mappings |
| 856 | 4 | 0 | |u https://doi.org/10.1038/s41598-021-85016-9 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
| 856 | 4 | 0 | |u https://www.nature.com/articles/s41598-021-85016-9 |x Verlag |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20210812 | ||
| 993 | |a Article | ||
| 994 | |a 2021 | ||
| 998 | |g 124367720 |a Ganslandt, Thomas |m 124367720:Ganslandt, Thomas |d 60000 |e 60000PG124367720 |k 0/60000/ |p 8 | ||
| 998 | |g 142731773 |a Trinkmann, Frederik |m 142731773:Trinkmann, Frederik |d 910000 |d 950000 |d 950900 |d 60000 |d 61000 |e 910000PT142731773 |e 950000PT142731773 |e 950900PT142731773 |e 60000PT142731773 |e 61000PT142731773 |k 0/910000/ |k 1/910000/950000/ |k 2/910000/950000/950900/ |k 0/60000/ |k 1/60000/61000/ |p 7 | ||
| 998 | |g 1034567551 |a Siegel, Fabian |m 1034567551:Siegel, Fabian |d 60000 |d 63100 |e 60000PS1034567551 |e 63100PS1034567551 |k 0/60000/ |k 1/60000/63100/ |p 6 | ||
| 998 | |g 1214458068 |a Saase, Victor |m 1214458068:Saase, Victor |d 60000 |d 63000 |e 60000PS1214458068 |e 63000PS1214458068 |k 0/60000/ |k 1/60000/63000/ |p 5 | ||
| 998 | |g 1238815928 |a Junge, Andreas Georg |m 1238815928:Junge, Andreas Georg |d 60000 |d 63000 |e 60000PJ1238815928 |e 63000PJ1238815928 |k 0/60000/ |k 1/60000/63000/ |p 3 | ||
| 998 | |g 1238814832 |a Cho, Chang Gyu |m 1238814832:Cho, Chang Gyu |d 60000 |d 63000 |e 60000PC1238814832 |e 63000PC1238814832 |k 0/60000/ |k 1/60000/63000/ |p 2 | ||
| 998 | |g 1144379407 |a Maros, Máté E. |m 1144379407:Maros, Máté E. |d 60000 |d 63000 |e 60000PM1144379407 |e 63000PM1144379407 |k 0/60000/ |k 1/60000/63000/ |p 1 |x j | ||
| 999 | |a KXP-PPN1766546102 |e 3966298619 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"relHost":[{"part":{"extent":"18","pages":"1-18","text":"11(2021), Artikel-ID 5529, Seite 1-18","year":"2021","volume":"11"},"title":[{"title":"Scientific reports","title_sort":"Scientific reports"}],"physDesc":[{"extent":"Online-Ressource"}],"type":{"bibl":"periodical","media":"Online-Ressource"},"recId":"663366712","id":{"issn":["2045-2322"],"zdb":["2615211-3"],"eki":["663366712"]},"origin":[{"publisher":"Springer Nature ; Nature Publishing Group","dateIssuedKey":"2011","publisherPlace":"[London] ; London","dateIssuedDisp":"2011-"}],"disp":"Comparative analysis of machine learning algorithms for computer-assisted reporting based on fully automated cross-lingual RadLex mappingsScientific reports","language":["eng"],"note":["Gesehen am 12.07.24"],"pubHistory":["1, article number 1 (2011)-"]}],"title":[{"title_sort":"Comparative analysis of machine learning algorithms for computer-assisted reporting based on fully automated cross-lingual RadLex mappings","title":"Comparative analysis of machine learning algorithms for computer-assisted reporting based on fully automated cross-lingual RadLex mappings"}],"physDesc":[{"extent":"18 S."}],"language":["eng"],"note":["Gesehen am 12.08.2021"],"person":[{"given":"Máté E.","family":"Maros","role":"aut","display":"Maros, Máté E."},{"given":"Chang Gyu","family":"Cho","role":"aut","display":"Cho, Chang Gyu"},{"display":"Junge, Andreas Georg","family":"Junge","role":"aut","given":"Andreas Georg"},{"given":"Benedikt","display":"Kämpgen, Benedikt","role":"aut","family":"Kämpgen"},{"family":"Saase","role":"aut","display":"Saase, Victor","given":"Victor"},{"family":"Siegel","role":"aut","display":"Siegel, Fabian","given":"Fabian"},{"display":"Trinkmann, Frederik","role":"aut","family":"Trinkmann","given":"Frederik"},{"given":"Thomas","family":"Ganslandt","role":"aut","display":"Ganslandt, Thomas"},{"given":"Christoph","display":"Groden, Christoph","family":"Groden","role":"aut"},{"family":"Wenz","role":"aut","display":"Wenz, Holger","given":"Holger"}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"id":{"eki":["1766546102"],"doi":["10.1038/s41598-021-85016-9"]},"recId":"1766546102","name":{"displayForm":["Máté E. Maros, Chang Gyu Cho, Andreas G. Junge, Benedikt Kämpgen, Victor Saase, Fabian Siegel, Frederik Trinkmann, Thomas Ganslandt, Christoph Groden and Holger Wenz"]},"origin":[{"dateIssuedKey":"2021","dateIssuedDisp":"09 March 2021"}]} | ||
| SRT | |a MAROSMATEECOMPARATIV0920 | ||