Multi-task transfer learning for the prediction of entity modifiers in clinical text: application to opioid use disorder case detection.

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.

Annotation of Opioid Use Disorder Entity Modifiers in Clinical Text.

Natural Language Processing can be used to identify opioid use disorder in patients from clinical text1. We annotate a corpus of clinical text for mentions of concepts associated with unhealthy use of opiates including concept modifiers such as negation, subject, uncertainty, relation to document time and illicit use.

Accumulation Dynamics of Transcripts and Proteins of Cold-Responsive Genes in Fragaria vesca Genotypes of Differing Cold Tolerance.

Identifying and characterizing cold responsive genes in Fragaria vesca associated with or responsible for low temperature tolerance is a vital part of strawberry cultivar development. In this study we have investigated the transcript levels of eight genes, two dehydrin genes, three putative ABA-regulated genes, two cold-inducible CBF genes and the alcohol dehydrogenase gene, extracted from leaf and crown tissues of three F. vesca genotypes that vary in cold tolerance. Transcript levels of the CBF/DREB1 transcription factor FvCBF1E exhibited stronger cold up-regulation in comparison to FvCBF1B.1 in all genotypes. Transcripts of FvADH were highly up-regulated in both crown and leaf tissues from all three genotypes. In the 'ALTA' genotype, FvADH transcripts were significantly higher in leaf than crown tissues and more than 10 to 20-fold greater than in the less cold-tolerant 'NCGR1363' and 'FDP817' genotypes. FvGEM, containing the conserved ABRE promoter element, transcript was found to be cold-regulated in crowns. Direct comparison of the kinetics of transcript and protein accumulation of dehydrins was scrutinized. In all genotypes and organs, the changes of XERO2 transcript levels generally preceded protein changes, while levels of COR47 protein accumulation preceded the increases in COR47 RNA in 'ALTA' crowns.