Reviewing a Decade of Research Into Suicide and Related Behaviour Using the South London and Maudsley NHS Foundation Trust Clinical Record Interactive Search (CRIS) System

Abstract

Suicide is a serious public health issue worldwide, yet current clinical methods for assessing a person's risk of taking their own life remain unreliable and new methods for assessing suicide risk are being explored. The widespread adoption of electronic health records (EHRs) has opened up new possibilities for epidemiological studies of suicide and related behaviour amongst those receiving healthcare. These types of records capture valuable information entered by healthcare practitioners at the point of care. However, much recent work has relied heavily on the structured data of EHRs, whilst much of the important information about a patient's care pathway is recorded in the unstructured text of clinical notes. Accessing and structuring text data for use in clinical research, and particularly for suicide and self-harm research, is a significant challenge that is increasingly being addressed using methods from the fields of natural language processing (NLP) and machine learning (ML). In this review, we provide an overview of the range of suicide-related studies that have been carried out using the Clinical Records Interactive Search (CRIS): a database for epidemiological and clinical research that contains de-identified EHRs from the South London and Maudsley NHS Foundation Trust. We highlight the variety of clinical research questions, cohorts and techniques that have been explored for suicide and related behaviour research using CRIS, including the development of NLP and ML approaches. We demonstrate how EHR data provides comprehensive material to study prevalence of suicide and self-harm in clinical populations. Structured data alone is insufficient and NLP methods are needed to more accurately identify relevant information from EHR data. We also show how the text in clinical notes provide signals for ML approaches to suicide risk assessment. We envision increased progress in the decades to come, particularly in externally validating findings across multiple sites and countries, both in terms of clinical evidence and in terms of NLP and machine learning method transferability.

Incremental Validity of Language-Based Assessments of Personality in World Trade Center Responders

“…With the power of increased computational modeling, in addition to single words, (a) multi-word "phrases" and (b) multiword/phrase "topics" can be extracted and used to improve language models that capture personality (Eichstaedt et al, 2020). Mining of electronic health records has also been used to provide large samples of textual language to assess mental health (Bittar et al, 2020;Boag et al, 2021). However, to date few studies have applied these techniques to spoken language, especially with patients, which provides unique challenges to obtain, but exciting opportunities for improving language models used to capture psychiatric constructs.…”

Natural language processing of multi-hospital electronic health records for public health surveillance of suicidality

“…First, although some projects have already demonstrated that NLP algorithms applied on clinical reports could extract variables of interest regarding mental health 23 – 27 , many of these algorithms were developed using disease-, age- or hospital-specific cohorts and concerns have been raised regarding their generalisability 28 . It is therefore necessary to train and validate NLP algorithms on datasets that are representative of various contexts of care to detect indications on mental health that are often scattered among millions of reports edited throughout care organisations.…”