Risk Assessment Tools and Data-Driven Approaches for Predicting and Preventing Suicidal Behavior

Velupillai, Sumithra; Hadlaczky, Gergö; Baca‐García, Enrique; Gorrell, Genevieve; Werbeloff, Nomi; Nguyen, Dong; Patel, Rashmi; Leightley, Daniel; Downs, Johnny; Hotopf, Matthew; Dutta, Rina

doi:10.3389/fpsyt.2019.00036

Cited by 58 publications

(32 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other studies have used different NLP approaches which do not involve interpretation of the linguistic context within which words appear. One example is assessing the overall positive or negative valence in discharge summaries in relation to risk of suicide and suicide attempts (15,39), or using a "bag-of-words" approach which analyses text in terms of the frequency of specific words to predict suicide (40), or seclusion for psychiatric inpatients (41). While the 'bag-of-words' approach is intuitively clear and serves as a good baseline model, it lacks the ability to capture the contextual information.…”

Section: Study 2: Application Of Natural Language Processing Tools Tomentioning

confidence: 99%

“…One important consideration is that much of the information within them is contained within free-text clinical notes rather than structured fields. This makes extraction of data difficult, relying either on resource-intensive manual review of clinical records, or, increasingly, automated natural language processing (NLP) algorithms (15,16). NLP processes have been applied to extract a variety of information from free-text clinical records including medication use (17,18), self-harm (19,20), and socio-demographic history (21,22); such approaches have addressed model development using limited numbers of annotated text examples (23).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identifying Predictors of Suicide in Severe Mental Illness: A Feasibility Study of a Clinical Prediction Rule (Oxford Mental Illness and Suicide Tool or OxMIS)

Senior

Burghart

et al. 2020

Front. Psychiatry

View full text Add to dashboard Cite

Background: Oxford Mental Illness and Suicide tool (OxMIS) is a brief, scalable, freely available, structured risk assessment tool to assess suicide risk in patients with severe mental illness (schizophrenia-spectrum disorders or bipolar disorder). OxMIS requires further external validation, but a lack of large-scale cohorts with relevant variables makes this challenging. Electronic health records provide possible data sources for external validation of risk prediction tools. However, they contain large amounts of information within free-text that is not readily extractable. In this study, we examined the feasibility of identifying suicide predictors needed to validate OxMIS in routinely collected electronic health records. Methods: In study 1, we manually reviewed electronic health records of 57 patients with severe mental illness to calculate OxMIS risk scores. In study 2, we examined the feasibility of using natural language processing to scale up this process. We used anonymized freetext documents from the Clinical Record Interactive Search database to train a named entity recognition model, a machine learning technique which recognizes concepts in freetext. The model identified eight concepts relevant for suicide risk assessment: medication (antidepressant/antipsychotic treatment), violence, education, self-harm, benefits receipt, drug/alcohol use disorder, suicide, and psychiatric admission. We assessed model performance in terms of precision (similar to positive predictive value), recall (similar to sensitivity) and F1 statistic (an overall performance measure). Results: In study 1, we estimated suicide risk for all patients using the OxMIS calculator, giving a range of 12 month risk estimates from 0.1-3.4%. For 13 out of 17 predictors, there was no missing information in electronic health records. For the remaining 4 predictors missingness ranged from 7-26%; to account for these missing variables, it was possible for OxMIS to estimate suicide risk using a range of scores. In study 2, the named entity recognition model had an overall precision of 0.77, recall of 0.90 and F1 score of 0.83. The concept with the best precision and recall was medication (precision

show abstract

Section: Study 2: Application Of Natural Language Processing Tools Tomentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Identifying Predictors of Suicide in Severe Mental Illness: A Feasibility Study of a Clinical Prediction Rule (Oxford Mental Illness and Suicide Tool or OxMIS)

Senior

Burghart

et al. 2020

Front. Psychiatry

View full text Add to dashboard Cite

show abstract

“…However, given the number of available adjunct measures of suicide risk with low predictive validity and a limited number of measures suitable for use in the fast-paced ED setting, 24,[49][50][51][52] further research is needed, particularly in the use of machine learning to improve suicide risk prediction. 42,53 Future work in the ED setting should focus on incorporating valid and reliable predictive algorithms as an aid to existing clinical decisionmaking practices, while also aligning suicide risk decisions with appropriate and evidence-based clinical interventions to reduce patient suicide risk. [25][26][27]52,54 Overall, results from this study provide important implications for improving ED care and treatment planning for patients reporting active suicidal ideation.…”

Section: Limitationsmentioning

confidence: 99%

An investigation of clinical decisionmaking: identifying important factors in treatment planning for suicidal patients in the emergency department

et al. 2020

View full text Add to dashboard Cite

Objective We sought to evaluate the influence of several well‐documented, readily available risk factors that may influence a psychiatric consultant's decision to admit an emergency department (ED) patient reporting suicidal ideation for psychiatric hospitalization. Methods We conducted a retrospective study of adult patients presenting to six affiliated EDs within Pennsylvania from January 2015 to June 2017. We identified 533 patients reporting current active suicidal ideation and receiving a complete psychiatric consultation. Socio‐demographic characteristics, psychiatric presentation and history, and disposition were collected. Decision tree analysis was conducted with disposition as the outcome. Results Four of 27 variables emerged as most influential to decisionmaking, including psychiatric consultant determination of current suicide risk, patient age, current depressive disorder diagnosis, and patient history of physical violence. Likelihood of admission versus discharge ranged from 97% to 58%, depending on the variables considered. Post hoc analysis indicated that current suicide plan, access to means, lack of social support, and suicide attempt history were significantly associated with psychiatric consultant determination of moderate‐to‐high suicide risk, with small‐to‐medium effect sizes emerging. Conclusions Only a handful of variables drive disposition decisions for ED patients reporting current active suicidal ideation, with both high and low fidelity decisions made. Patient suicide risk, determined by considering empirically supported risk factors for suicide attempt and death, contributes the greatest influence on a psychiatric consultant's decision to admit. In line with American College of Emergency Physicians (ACEP) recommendations, this study accentuates the importance of using clinical judgment and adjunct measures to determine patient disposition within this population.

show abstract

“…Velupillai et al ( 19 ) developed and validated a method for identifying suicidality across a more heterogenous clinical adolescent population in EHRs using NLP, expanding the population beyond ASD. They examined 1,601,422 documents from 23,455 young people and developed a method to accurately identify suicidal behaviour information in a very broad clinical population.…”

Section: Identification and Prevalence Estimates Of Suicidality In Crmentioning

confidence: 99%

“…The availability of this type of large-scale data heralds the prospect of using statistical and data science approaches to analyse larger cohorts and better understand how these behaviours manifest in healthcare settings ( 19 ). However, using these data also presents major challenges, as much of the key clinical information, including suicidal behaviour, is recorded as unstructured clinical case notes and correspondence ( 20 – 22 ).…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2020

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Risk Assessment Tools and Data-Driven Approaches for Predicting and Preventing Suicidal Behavior

Cited by 58 publications

References 64 publications

Identifying Predictors of Suicide in Severe Mental Illness: A Feasibility Study of a Clinical Prediction Rule (Oxford Mental Illness and Suicide Tool or OxMIS)

Identifying Predictors of Suicide in Severe Mental Illness: A Feasibility Study of a Clinical Prediction Rule (Oxford Mental Illness and Suicide Tool or OxMIS)

An investigation of clinical decisionmaking: identifying important factors in treatment planning for suicidal patients in the emergency department

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

Contact Info

Product

Resources

About