How to improve testing when trying to predict inmate suicidal behavior

Naud, Hélène; Daigle, Marc

doi:10.1016/j.ijlp.2013.06.010

Cited by 7 publications

(4 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the prison psychiatric sample data are not representative of the general population. Incarceration is associated with increased suicide risk (Naud & Daigle, 2013), raising questions about the generalizability of our findings to nonprison populations. Nevertheless, our results are comparable to findings from studies using nonprison populations (e.g., Walsh et al, 2017), although training our models on nonprison populations is an obvious direction for future research.…”

Section: Discussionmentioning

confidence: 92%

“…Previous findings indicate that retrospective and predictive modeling of suicidal behavior achieve similar accuracy (Walsh et al, 2017), which suggests that the same datasets and models can be used for both predictive and retrospective modeling of suicidal behavior, addressing a potential limitation of our retrospective modeling. Prisons tend to have a higher suicide rate than the rest of the population (Naud & Daigle, 2013), and prisoners have exceptionally high rates of personality disorders, including antisocial personality disorder (APD) and BPD (Fazel & Danesh, 2002). Some researchers argue that these disorders are merely different representations of the same underlying psychopathology (Paris, 1997), and further studies show that APD and BPD share at least some behavioral and neurobiological background (Black et al, 2010; Buchheim et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Suicidal Behavior Without Asking About Suicidal Ideation: Machine Learning and the Role of Borderline Personality Disorder Criteria

Horvath

Dras

Lai

et al. 2020

Suicide & Life Threat Behav

View full text Add to dashboard Cite

Objective Identifying predictors contributing to suicide risk could help prevent suicides via targeted interventions. However, using only known risk factors may not yield accurate enough results. Furthermore, risk models typically rely on suicidal ideation, even though people often withhold this information. Method This study examined the contribution of various predictors to the accuracy of six machine learning models for identifying suicidal behavior in a prison population (n = 353), including borderline personality disorder (BPD) and antisocial personality disorder (APD) criteria, and compared how excluding data about suicidal ideation affects accuracy. Results Results revealed that gradient tree boosting accurately identified individuals with suicidal behavior, even without relying on questions about suicidal ideation (AUC = 0.875, F1 = 0.846). Furthermore, the model maintained this accuracy with only 29 predictors. Meeting five or more diagnostic criteria of BPD was an important risk factor for suicidal behavior. APD criteria, in the presence of other predictors, did not substantially improve accuracy. Additionally, it may be possible to implement a decision tree model to assess individuals at risk of suicide, without focusing upon suicidal ideation. Conclusions These findings highlight that modern classification algorithms do not necessarily require information about suicidal ideation for modeling suicide and self‐harm behavior.

show abstract

Section: Discussionmentioning

confidence: 92%

Section: Introductionmentioning

confidence: 99%

Predicting Suicidal Behavior Without Asking About Suicidal Ideation: Machine Learning and the Role of Borderline Personality Disorder Criteria

Horvath

Dras

Lai

et al. 2020

Suicide & Life Threat Behav

View full text Add to dashboard Cite

show abstract

“…There are conflicting data about the possibility of a predictive score for self-harm / suicide. Thus, while authors from the UK use a psychometric instrument (SCOPE) designed to distinguish between those at risk and those with no risk of self-harm [7], other authors refute this possibility [6,8].…”

Section: Discussionmentioning

confidence: 99%

Self-harm in the prison system

Brezean¹,

Moldovan²,

Ferechide³

et al. 2016

RJLM

View full text Add to dashboard Cite

Self-harm is a much more common pathology within the prison environment than outside of this, so much so that it can be considered specific to it. For 7 years, in the biggest prison hospital in Romania, self-harm was present in 5% of the hospitalized patients, with a total of 762 cases. The mechanisms of self-harm were the ingestion of foreign bodies (63%) and the insertion of foreign bodies in: the soft parts (19%), intracranially (6%), intraabdominally (2%) and intrathoracically (2%). Metal bodies are the most commonly used in self-harm (over 90%). The self-harm technique is learnt from the inmates with a history of such incidents. The mortality is low (0.4%), refusal of treatment is found in 13% of cases, and recurrence of self-harm is common where the ingestion and intracranial insertion of foreign bodies occurs (42%-50%). Mental disorders, dominated by personality disorders, are found in 46% of patients.

show abstract

“…Research exploring how best to tackle prisoner suicide and self-harm has been compromised by insufficiently reliable and robust monitoring systems, an inability to generalise findings because of unique features of prisons participating in specific studies, and a reliance on prisoner perceptions/feedback (Barker et al, 2014; Humber et al, 2011; Naud & Daigle 2013). Additional problems include difficulties securing effective implementation in the prison environment, small sample sizes, attrition rates and missing data (Barker et al, 2014; Eccleston & Sorbello, 2002; Hayes et al, 2008; Humber et al, 2011; Naud & Daigle, 2013).…”

Section: Introductionmentioning

confidence: 99%

Reflections on a project to prevent suicide and self-harm among prisoners identified as high risk in two prisons in Northern England

et al. 2018

View full text Add to dashboard Cite

BackgroundThis article critically explores the implementation and evaluation of a project designed, delivered and evaluated by frontline staff to improve prison responses to prisoner suicide and self-harm. We begin by evidencing the need for the project and detail its content, delivery and attempts at evaluation. We draw on the reflections of the three practitioners most closely involved in its development, delivery and review in order to explore lessons learned for future staff-led projects including those aimed at tackling prison suicide and self-harm.ResultsFindings from staff reflections suggest that the development, implementation and evaluation of the project were influenced by a combination of issues around: project focus, communication and professional relationships, the institutional environment, funding and time, roll-out and evaluation, and the need for a ‘champion’ role.ConclusionsThere is limited evidence that the project left a modest positive legacy in terms of impact. A more substantial legacy of the project is provided in terms of actionable learning points for future projects of this nature.

show abstract

How to improve testing when trying to predict inmate suicidal behavior

Cited by 7 publications

References 64 publications

Predicting Suicidal Behavior Without Asking About Suicidal Ideation: Machine Learning and the Role of Borderline Personality Disorder Criteria

Predicting Suicidal Behavior Without Asking About Suicidal Ideation: Machine Learning and the Role of Borderline Personality Disorder Criteria

Self-harm in the prison system

Reflections on a project to prevent suicide and self-harm among prisoners identified as high risk in two prisons in Northern England

Contact Info

Product

Resources

About