Negation detection in Dutch clinical texts: an evaluation of rule-based and machine learning methods

Abstract When developing models for clinical information retrieval and decision support systems, the discrete outcomes required for training are often missing. These labels need to be extracted from free text in electronic health records. For this extraction process one of the most important contextual properties in clinical text is negation, which indicates the absence of findings. We aimed to improve large scale extraction of labels by comparing three methods for negation detection in Dutch clinical notes. We used the Erasmus Medical Center Dutch Clinical Corpus to compare a rule-based metho... Mehr ...

Verfasser: Bram van Es
Leon C. Reteig
Sander C. Tan
Marijn Schraagen
Myrthe M. Hemker
Sebastiaan R. S. Arends
Miguel A. R. Rios
Saskia Haitjema
Dokumenttyp: Artikel
Erscheinungsdatum: 2023
Reihe/Periodikum: BMC Bioinformatics, Vol 24, Iss 1, Pp 1-20 (2023)
Verlag/Hrsg.: BMC
Schlagwörter: Natural language processing / Text mining / Negation detection / Computer applications to medicine. Medical informatics / R858-859.7 / Biology (General) / QH301-705.5
Sprache: Englisch
Permalink: https://search.fid-benelux.de/Record/base-28989564
Datenquelle: BASE; Originalkatalog
Powered By: BASE
Link(s) : https://doi.org/10.1186/s12859-022-05130-x

Abstract When developing models for clinical information retrieval and decision support systems, the discrete outcomes required for training are often missing. These labels need to be extracted from free text in electronic health records. For this extraction process one of the most important contextual properties in clinical text is negation, which indicates the absence of findings. We aimed to improve large scale extraction of labels by comparing three methods for negation detection in Dutch clinical notes. We used the Erasmus Medical Center Dutch Clinical Corpus to compare a rule-based method based on ContextD, a biLSTM model using MedCAT and (finetuned) RoBERTa-based models. We found that both the biLSTM and RoBERTa models consistently outperform the rule-based model in terms of F1 score, precision and recall. In addition, we systematically categorized the classification errors for each model, which can be used to further improve model performance in particular applications. Combining the three models naively was not beneficial in terms of performance. We conclude that the biLSTM and RoBERTa-based models in particular are highly accurate accurate in detecting clinical negations, but that ultimately all three approaches can be viable depending on the use case at hand.