Negation detection in Dutch clinical texts: an evaluation of rule-based and machine learning methods
This work addresses the need for accurate label extraction from clinical records to support information retrieval and decision systems, but it is incremental as it applies existing methods to a specific language and domain.
The study tackled the problem of detecting negation in Dutch clinical texts by comparing rule-based, biLSTM, and RoBERTa-based methods, finding that both machine learning models consistently outperformed the rule-based approach in F1 score, precision, and recall.
As structured data are often insufficient, labels need to be extracted from free text in electronic health records when developing models for clinical information retrieval and decision support systems. 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.