Prediction of Repeated Self-Harm in Six Months: Comparison of Traditional Psychometrics With Random Forest Algorithm

2021 ◽  
pp. 003022282110605
Author(s):  
Shu-Chin Chen ◽  
Hui-Chun Huang ◽  
Shen-Ing Liu ◽  
Sue-Huei Chen
Keyword(s):  
Random Forest ◽  
Suicide Risk ◽  
Predictive Ability ◽  
Random Forest Algorithm ◽  
The Past ◽  
Self Harm ◽  
Two Phases ◽  
Screening Scale ◽  
Potential Tool

Suicidal risk has been a significant mental health problem. However, the predictive ability for repeated self-harm (SH) has not improved over the past decades. This study thus aimed to explore a potential tool with theoretical accommodation and clinical application by employing traditional logistic regression (LR) and newly developed machine learning, random forest algorithm (RF). Starting with 89 items from six commonly used scales (i.e., proximal suicide risk factors) as preliminary predictors, both LR and RF resulted in a better solution with much fewer items in two phases of item selections and analyses, with prediction accuracy 88.6% and 79.8%, respectively. A combination with 12 selected items, named LR-12, well predicted repeated self-harm in 6-month follow-up with satisfactory performance (AUC = 0.84, 95% CI: 0.76–0.92; cut-off point by 1/2 with sensitivity 81.1% and specificity 74.0%). The psychometrically appealing LR-12 could be used as a screening scale for suicide risk assessment.

scholarly journals Repetition of deliberate self-harm and subsequent suicide risk: Long-term follow-up study of 11 583 patients

2004 ◽  
Vol 185 (1) ◽  
pp. 70-75 ◽  
Author(s):  
Daniel Louis Zahl ◽  
Keith Hawton
Keyword(s):  
Relative Risk ◽  
Suicide Risk ◽  
Single Episode ◽  
Deliberate Self Harm ◽  
Young Females ◽  
Follow Up Study ◽  
Increased Risk ◽  
Self Harm

BackgroundRepetition of deliberate self-harm (DSH) is a risk factor for suicide. Little information is available on the risk for specific groups of people who deliberately harm themselves repeatedly.AimsTo investigate the long-term risk of suicide associated with repetition of DSH by gender, age and frequency of repetition.MethodA mortality follow-up study to the year 2000 was conducted on 11583 people who presented to the general hospital in Oxford between 1978 and 1997. Repetition of DSH was determined from reported episodes prior to the index episode and episodes presenting to the same hospital during the follow-up period. Deaths were identified through national registers.ResultsThirty-nine percent of patients repeated the DSH. They were at greater relative risk of suicide than the single-episode DSH group (2.24; 95% CI 1.77–2.84). The relative risk of suicide in the repeated DSH group compared with the single-episode DSH group was greater in females (3.5; 95% C11.3–2.4) than males (1.8; 95% C1 2.3–5.3) and was inversely related to age (up to 54 years). Suicide risk increased further with multiple repeat episodes of DSH in females.ConclusionsRepetition of DSH is associated with an increased risk of suicide in males and females. Repetition may be a better indicator of risk in females, especially young females.

scholarly journals Severe and enduring mental health problems within an established substance misuse treatment partnership

2014 ◽  
Vol 38 (5) ◽  
pp. 216-219 ◽  
Author(s):  
Kathryn Walsh ◽  
Alex Copello
Keyword(s):  
Mental Health ◽  
Substance Use ◽  
Suicide Risk ◽  
Substance Misuse ◽  
Mental Health Problems ◽  
Health Problems ◽  
Clinical Implications ◽  
The Past ◽  
Self Harm ◽  
Effective Service

Aims and methodThe study reports findings of an investigation into the presence of severe and enduring mental health problems within the four statutory and non-statutory teams of an established substance misuse treatment partnership.ResultsOf a total of 772 clients in the four teams surveyed, 69 (8.9%) were identified as having severe and enduring mental health problems and problem substance use in the past 12 months. Alcohol was the most prevalent substance used by this predominantly male group. Different rates were found across the four teams, with higher numbers in the non-statutory teams. The clients displayed significant levels of self-harm and suicide risk and were responsible for 131 acute service contacts over the past 12 months.Clinical implicationsClients with severe and enduring mental health problems engaged with substance misuse services display high levels of complex need. It is important to identify the best and most effective service response to this group.

scholarly journals Towards developing diagnostic criteria for early knee osteoarthritis: data from the CHECK study

Rheumatology ◽  
2020 ◽  
Author(s):  
J Runhaar ◽  
M Kloppenburg ◽  
M Boers ◽  
J W J Bijlsma ◽  
S M A Bierma-Zeinstra
Keyword(s):  
Diagnostic Criteria ◽  
Medical Records ◽  
Area Under The Curve ◽  
Predictive Ability ◽  
Selection Methods ◽  
Knee Oa ◽  
The Past ◽  
Diagnostic Models ◽  
Baseline Factors

Abstract Objectives There is a general consensus that a shift in focus towards early diagnosis and treatment of knee OA is warranted. However, there are no validated and widely accepted diagnostic criteria for early knee OA available. The current study aimed to take the first steps towards developing diagnostic criteria for early knee OA. Methods Data of 761 individuals with 1185 symptomatic knees at baseline were selected from the CHECK study. For CHECK, individuals with pain/stiffness of the knee, aged 45–65 years, who had no prior consultation or a first consultation with the general practitioner for these symptoms in the past 6 months were recruited and followed for 10 years. A group of 36 experts (17 general practitioners and 19 secondary care physicians) evaluated the medical records in pairs to diagnose the presence of clinically relevant knee OA 5–10 years after enrolment. A backward selection methods was used to create predictive models based on pre-defined baseline factors from history taking, physical examination, radiography and blood testing, using the experts’ diagnoses as gold standard outcome. Results Prevalence of clinically relevant knee OA during follow-up was 37%. Created models contained 7–11 baseline factors and obtained an area under the curve between 0.746 (0.002) and 0.764 (0.002). Conclusion The obtained diagnostic models for early knee OA had ‘fair’ predictive ability in individuals presenting with knee pain in primary care. Further modelling and validation of the identified predictive factors is required to obtain clinically feasible and relevant diagnostic criteria for early knee OA.

The Effects of Suicide Ideation Assessments on Urges to Self-Harm and Suicide

Crisis ◽  
2014 ◽  
Vol 35 (2) ◽  
pp. 123-131 ◽  
Author(s):  
Rahel Eynan ◽  
Yvonne Bergmans ◽  
Jesmin Antony ◽  
John R. Cutcliffe ◽  
Henry G. Harder ◽  
...  
Keyword(s):  
Suicidal Ideation ◽  
Suicide Risk ◽  
Suicide Ideation ◽  
Psychiatric Service ◽  
Exclusion Criterion ◽  
Primary Concern ◽  
Assessment Protocol ◽  
Self Harm ◽  
Study Participants

Background: Participants’ safety is the primary concern when conducting research with suicidal or potentially suicidal participants. The presence of suicide risk is often an exclusion criterion for research participants. Subsequently, few studies have examined the effects of research assessments on study participants’ suicidality. Aims: The purpose of this research was to examine the patterns of postassessment changes in self-harm and suicide urges of study participants who were recently discharged from an inpatient psychiatric service. Method: Study participants (N = 120) were recruited from patients with a lifetime history of suicidal behavior admitted with current suicidal ideation or suicide attempt to an inpatient psychiatric service and/or a crisis stabilization unit. Participants were assessed for suicidal ideation with the Suicide Ideation Scale at 1, 3, and 6 months following their discharge from hospital. The risk assessment protocol was administered at the start and at the end of each of the study follow-up assessments. Results: Changes in self-harm and suicide urges following study assessments were small, infrequent, and were most likely to reflect a decrease in suicidality. Similarly, participants rarely reported worsening self-control over suicidal urges, and when they did, the effect was minimal. By the end of the 6-month follow-up period, increases in self-harm and suicidal urges postassessment were not seen. Conclusion: The inclusion of suicidal participants in research interviews rarely increased suicide risk. Research involving suicidal individuals is possible when study protocols are well planned and executed by trained assessors and clinicians who are able to identify participants at risk and provide intervention if necessary. The few participants that required intervention had high levels of suicide ideation and behavior at baseline and almost all reported symptoms of posttraumatic stress disorder. Further study is needed to better characterize this subgroup of participants.

Older people who self harm need long term follow-up to reduce suicide risk

BMJ ◽  
2012 ◽  
Vol 344 (may01 2) ◽  
pp. e3120-e3120
Author(s):  
Z. Kmietowicz
Keyword(s):  
Older People ◽  
Suicide Risk ◽  
Long Term Follow Up ◽  
Self Harm

scholarly journals Understanding and managing suicide risk

2020 ◽  
Vol 134 (1) ◽  
pp. 73-84
Author(s):  
Tiago C Zortea ◽  
Seonaid Cleare ◽  
Ambrose J Melson ◽  
Karen Wetherall ◽  
Rory C O’Connor
Keyword(s):  
Suicide Risk ◽  
Suicide Attempts ◽  
Psychosocial Interventions ◽  
Crisis Response ◽  
Individual Risk ◽  
Global Public Health ◽  
Self Harm ◽  
Meta Analyses ◽  
Better Than

Abstract Background Suicidal behaviours and non-suicidal self-harm (NSSH) are global public health concerns that affect millions of lives. Sources of data This review is a narrative synthesis of systematic reviews, meta-analyses of randomized control trials (RCTs) and landmark studies published in scientific journals. Areas of agreement Restricting access to lethal means reduces the likelihood of future suicide deaths. Areas of controversy Our ability to predict future suicidal behaviour is no better than chance. No individual risk prediction instrument offers sufficient sensitivity and specificity to inform clinically useful decision-making. Growing points Different types of psychosocial interventions may be effective in preventing future suicide attempts; such interventions include clinical assessment, tailored crisis response and safety plans and follow-up contact. Areas timely for developing research Whilst some psychosocial interventions can be effective in reducing suicide risk, little is known about the mechanisms of recovery from suicidal thoughts and behaviours.

scholarly journals Fatal and non-fatal repetition of self-harm

2002 ◽  
Vol 181 (3) ◽  
pp. 193-199 ◽  
Author(s):  
David Owens ◽  
Judith Horrocks ◽  
Allan House
Keyword(s):  
Systematic Review ◽  
General Population ◽  
Suicide Risk ◽  
Experimental Studies ◽  
Inclusion Criteria ◽  
Strong Connection ◽  
Effective Interventions ◽  
Self Harm ◽  
The Uk

BackgroundNon-fatal self-harm frequently leads to non-fatal repetition and sometimes to suicide. We need to quantify these two outcomes of self-harm to help us to develop and test effective interventions.AimsTo estimate rates of fatal and non-fatal repetition of self-harm.MethodA systematic review of published follow-up data, from observational and experimental studies. Four electronic databases were searched and 90 studies met the inclusion criteria.ResultsEighty per cent of studies found were undertaken in Europe, over one-third in the UK. Median proportions for repetition 1 year later were: 16% non-fatal and 2% fatal; after more than 9 years, around 7% of patients had died by suicide. The UK studies found particularly low rates of subsequent suicide.ConclusionsAfter 1 year, non-fatal repetition rates are around 15%. The strong connection between self-harm and later suicide lies somewhere between 0.5% and 2% after 1 year and above 5% after 9 years. Suicide risk among self-harm patients is hundreds of times higher than in the general population.

Assessment and Referral Patterns of Patients Admitted after Deliberate Self-Poisoning

1995 ◽  
Vol 40 (5) ◽  
pp. 144-146
Author(s):  
D.H. Brown ◽  
N. Reynolds ◽  
T. Pullar
Keyword(s):  
Medical Staff ◽  
Suicide Risk ◽  
Demographic Data ◽  
Psychiatric Service ◽  
Referral Rate ◽  
Poor Agreement ◽  
Referral Patterns ◽  
Psychiatric Referral ◽  
Self Harm

The assessment and referral patterns of adult patients after deliberate self-poisoning in Dundee were examined. Questionnaires were completed by the admitting physicians and assessing psychiatrists over a 3 month period. Demographic data concerning the patients and the nature of self-harm were similar to previous studies. Initial referral rate was 95% but dropped to between 70% and 81% after the post receiving round. Up to 2 hours/ day could be required for assessment and 75% of the cases required some form of psychiatric follow-up. Although both groups of doctors considered that the majority of patients required or would benefit from psychiatric referral, there was poor agreement when patients were independently categorised into high or low suicide risk (kappa = 0.04). Agreement was also low regarding whether referral was essential or not (kappa = 0.06). Although junior medical staff can play an important role in screening of patients, the psychiatric service, including trained nurses, may be best placed to provide a full assessment, where required.

Risk of suicide in patients who present to hospital after self-cutting according to site of injury: findings from the Multicentre Study of Self-harm in England

2021 ◽  
pp. 1-9
Author(s):  
Galit Geulayov ◽  
Deborah Casey ◽  
Elizabeth Bale ◽  
Fiona Brand ◽  
Caroline Clements ◽  
...  
Keyword(s):  
Multicentre Study ◽  
Odds Ratio ◽  
Suicide Risk ◽  
Adjusted Odds Ratio ◽  
The Body ◽  
Mixed Effect ◽  
Risk Of Death ◽  
Mixed Effect Models ◽  
Self Harm

Abstract Background We compared the risk of death by suicide following hospital presentation for self-harm according to site of self-cut/stab. Method We included 54 999 self-harm presentations (involving 31 419 individuals) to hospitals in the Multicentre Study of Self-harm in England (1/1/2004–31/12/2014), with mortality follow-up to 31/12/2019. Information on method of self-harm was obtained through monitoring in hospitals. Information about mortality was obtained through linkage with NHS Digital. We assessed the association of site of self-cut with death by suicide using mixed effect models. Results In total, 10 790 (19.6%) hospital presentations involved self-cutting/stabbing, 7489 of which (69.4%) were due to laceration to the arm/wrist alone, 1846 episodes (17.1%) involved cutting elsewhere on the body, and 1455 (13.5%) were due to laceration to unknown site. Controlling for confounders, presentation to a hospital following self-cut/stab to bodily parts other than wrist/arm was associated with greater chance of subsequent suicide relative to presentation after self-poisoning alone [adjusted odds ratio (aOR) 1.75, 95% confidence interval (CI) 1.03–2.96, p = 0.038]. The likelihood of suicide after presentation for cutting/stabbing the wrist/arm alone was comparable to that of patients who had self-poisoned alone. Presentations after laceration involving the neck were associated with a four-fold greater chance of subsequent suicide relative to self-poisoning (aOR 4.09, 95% CI 1.80–9.30, p = 0.001). Conclusions Patients who attend hospital after self-cutting/stabbing are a heterogeneous group in terms of characteristics, methods of cutting/stabbing and risk of subsequent suicide. Risk of suicide is greater in individuals who self-cut/stab to parts of the body other than the wrist or arm, especially the neck.

Sign in / Sign up

Export Citation Format

Share Document