%0 Journal Article
%A Kebede, Mihiretu
%A Le Cornet, Charlotte
%A Turzanski-Fortner, Renée
%T In-depth evaluation of machine learning methods for semi-automating article screening in a systematic review of mechanistic literature.
%J Cordis
%V 14
%N 2
%@ 1759-2879
%C Sao Paulo
%I Programa de Estudos Pós-Graduados em História
%M DKFZ-2022-01433
%P 156-172
%D 2023
%Z #EA:C020#LA:C020# / 2023 Mar;14(2):156-172
%X We aimed to evaluate the performance of supervised machine learning algorithms in predicting articles relevant for full-text review in a systematic review. Overall, 16,430 manually screened titles/abstracts, including 861 references identified relevant for full-text review were used for the analysis. Of these, 40
%K Automated screening (Other)
%K Citation Screening (Other)
%K Machine Learning (Other)
%K NLP (Other)
%K Natural Language Processing (Other)
%K Systematic review (Other)
%K Text mining (Other)
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:35798691
%R 10.1002/jrsm.1589
%U https://inrepo02.dkfz.de/record/180603