Identifying Suicide Ideation and Suicidal Attempts in a Psychiatric Clinical Research Database using Natural Language Processing

Abstract

Research into suicide prevention has been hampered by methodological limitations such as low sample size and recall bias. Recently, Natural Language Processing (NLP) strategies have been used with Electronic Health Records to increase information extraction from free text notes as well as structured fields concerning suicidality and this allows access to much larger cohorts than previously possible. This paper presents two novel NLP approaches – a rule-based approach to classify the presence of suicide ideation and a hybrid machine learning and rule-based approach to identify suicide attempts in a psychiatric clinical database. Good performance of the two classifiers in the evaluation study suggest they can be used to accurately detect mentions of suicide ideation and attempt within free-text documents in this psychiatric database. The novelty of the two approaches lies in the malleability of each classifier if a need to refine performance, or meet alternate classification requirements arises. The algorithms can also be adapted to fit infrastructures of other clinical datasets given sufficient clinical recording practice knowledge, without dependency on medical codes or additional data extraction of known risk factors to predict suicidal behaviour.

Identifying Veterans Using Electronic Health Records in the United Kingdom: A Feasibility Study

“…A more immediate solution to accelerating veteran identification is the creation of digitalised tools, such as natural language processing (NLP) methods, to automatically detect these individuals using keywords and rules. Of great importance is its utility in being applied automatically to EHR and free-text clinical notes [28,29]. NLP sub-themes, such as text mining, are represented as a set of programmatic rules or machine learning algorithms (i.e.…”

“…NLP sub-themes, such as text mining, are represented as a set of programmatic rules or machine learning algorithms (i.e. automated learning from gold standard labelled data) to extract meaning from "naturally-occurring" text (meaning human generated text) [9,28]. The result is often an output that can be interpreted by humans with relative ease [30,31].…”

“…The result is often an output that can be interpreted by humans with relative ease [30,31]. Previous work has developed successful NLP approaches for use within CRIS to identify subgroups of interest-for example, to allow the identification of patient suicide attempts [28,32], or linking education, social care and EHR records for adolescents mental health analyses with is the subject of ongoing work [33]. Considering this study, the creation of a similar NLP tool would ensure a consistent, reliable and effective approach to identifying veterans from free-text clinical notes.…”

Machine learning in suicide science: Applications and ethics

“…Since then, very few machine learning suicide prediction studies have been published, with the majority of suicide prediction studies using machine learning being published in the past decade. Relative to prediction studies, applications of machine learning to cross‐sectional data are more common (e.g., Fernandes et al, ; Hettige et al, ). Although this pattern echoes the broader suicide literature (Franklin et al, ), longitudinal study designs are critical to inform risk (Kraemer et al, ).…”

Clinician-recalled quoted speech in electronic health records and risk of suicide attempt: a case–crossover study

“…For example, text-mined EHR data were found to produce more accurate models of suicidal behaviour in a sample of Gulf War veterans, 10 and important information such as recorded suicidal ideation and past attempts has been successfully identified in mental healthcare text using natural language processing (NLP). 11 Previous studies using EHRs to investigate suicide risk have focused on identifying individuals at risk of suicide from those not at Open access risk (ie, between-person variation). These have included Bayesian modelling to identify patients at risk of suicide attempt where patients had made three or more healthcare visits in a retrospective cohort, 12 Cox regression to develop a 10-year probability prediction model for death by suicide in a sample from the Korean National Health Insurance Service 13 and neural networks applied to the EHRs of UK patients to identify those most at risk of suicide.…”