Time Expressions in Mental Health Records for Symptom Onset Extraction

For psychiatric disorders such as schizophrenia, longer durations of untreated psychosis are associated with worse intervention outcomes. Data included in electronic health records (EHRs) can be useful for retrospective clinical studies, but much of this is stored as unstructured text which cannot be directly used in computation. Natural Language Processing (NLP) methods can be used to extract this data, in order to identify symptoms and treatments from mental health records, and temporally anchor the first emergence of these. We are developing an EHR corpus annotated with time expressions, clinical entities and their relations, to be used for NLP development. In this study, we focus on the first step, identifying time expressions in EHRs for patients with schizophrenia. We developed a gold standard corpus, compared this corpus to other related corpora in terms of content and time expression prevalence, and adapted two NLP systems for extracting time expressions. To the best of our knowledge, this is the first resource annotated for temporal entities in the mental health domain.

[1]  Hongfang Liu,et al.  Journal of Biomedical Informatics , 2022 .

[2]  J. Waddington,et al.  Prospective relationship of duration of untreated psychosis to psychopathology and functional outcome over 12years , 2012, Schizophrenia Research.

[3]  G. Simon,et al.  Duration of untreated symptoms in common mental disorders: association with outcomes , 2006, British Journal of Psychiatry.

[4]  Peter B. Jones,et al.  Duration of untreated psychosis and neuropsychological function in first episode psychosis , 2007, Schizophrenia Research.

[5]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[6]  James Pustejovsky,et al.  SemEval-2015 Task 6: Clinical TempEval , 2015, *SEMEVAL.

[7]  Tommaso Caselli,et al.  SemEval-2010 Task 13: TempEval-2 , 2010, *SEMEVAL.

[8]  Dan Roth,et al.  Extraction of events and temporal expressions from clinical narratives , 2013, J. Biomed. Informatics.

[9]  N. Freemantle,et al.  Don’t turn your back on the symptoms of psychosis: a proof-of-principle, quasi-experimental public health trial to reduce the duration of untreated psychosis in Birmingham, UK , 2013, BMC Psychiatry.

[10]  Andrea C. Fernandes,et al.  Cohort profile of the South London and Maudsley NHS Foundation Trust Biomedical Research Centre (SLaM BRC) Case Register: current status and recent enhancement of an Electronic Mental Health Record-derived data resource , 2016, BMJ Open.

[11]  John F. Hurdle,et al.  Extracting Information from Textual Documents in the Electronic Health Record: A Review of Recent Research , 2008, Yearbook of Medical Informatics.

[12]  George Hripcsak,et al.  Technical Brief: Agreement, the F-Measure, and Reliability in Information Retrieval , 2005, J. Am. Medical Informatics Assoc..

[13]  Chen Lin,et al.  Temporal Annotation in the Clinical Domain , 2014, TACL.

[14]  James Pustejovsky,et al.  SemEval-2017 Task 12: Clinical TempEval , 2017, *SEMEVAL.

[15]  Shuying Shen,et al.  A Prototype Tool Set to Support Machine-Assisted Annotation , 2012, BioNLP@HLT-NAACL.

[16]  Michael Gertz,et al.  HeidelTime: High Quality Rule-Based Extraction and Normalization of Temporal Expressions , 2010, *SEMEVAL.

[17]  Angel X. Chang,et al.  SUTime: A library for recognizing and normalizing time expressions , 2012, LREC.

[18]  James Pustejovsky,et al.  ISO-TimeML: An International Standard for Semantic Annotation , 2010, LREC.

[19]  Anna Rumshisky,et al.  Evaluating temporal relations in clinical text: 2012 i2b2 Challenge , 2013, J. Am. Medical Informatics Assoc..

[20]  Anna Rumshisky,et al.  Annotating temporal information in clinical narratives , 2013, J. Biomed. Informatics.

[21]  Wei Wang,et al.  A new algorithmic approach for the extraction of temporal associations from clinical narratives with an application to medical product safety surveillance reports , 2016, J. Biomed. Informatics.