Transfer Learning for the Prediction of Entity Modifiers in Clinical Text: Application to Opioid Use Disorder Case Detection
This work addresses the challenge of accurately interpreting clinical text for applications like opioid use disorder detection, though it is incremental as it builds on existing transformer methods.
The paper tackled the problem of predicting entity modifiers in clinical text, such as negation and uncertainty, by developing a multi-task transformer architecture, achieving state-of-the-art results with increases of up to 10% in micro F1 scores on a benchmark dataset.
Background: The semantics of entities extracted from a clinical text can be dramatically altered by modifiers, including entity negation, uncertainty, conditionality, severity, and subject. Existing models for determining modifiers of clinical entities involve regular expression or features weights that are trained independently for each modifier. Methods: We develop and evaluate a multi-task transformer architecture design where modifiers are learned and predicted jointly using the publicly available SemEval 2015 Task 14 corpus and a new Opioid Use Disorder (OUD) data set that contains modifiers shared with SemEval as well as novel modifiers specific for OUD. We evaluate the effectiveness of our multi-task learning approach versus previously published systems and assess the feasibility of transfer learning for clinical entity modifiers when only a portion of clinical modifiers are shared. Results: Our approach achieved state-of-the-art results on the ShARe corpus from SemEval 2015 Task 14, showing an increase of 1.1% on weighted accuracy, 1.7% on unweighted accuracy, and 10% on micro F1 scores. Conclusions: We show that learned weights from our shared model can be effectively transferred to a new partially matched data set, validating the use of transfer learning for clinical text modifiers