Search

Background: For the provision of optimal care in a suicide prevention helpline, it is important to know what contributes to positive or negative effects on help seekers. Helplines can often be contacted through text-based chat services, which produce large amounts of text data for use in large-scale analysis. Objective: We trained a machine learning classification model to predict chat outcomes based on the content of the chat conversations in suicide helplines and identified the counsellor utterances that had the most impact on its outputs. Methods: From August 2021 until January 2023, help seekers (N=6903) scored themselves on factors known to be associated with suicidality (eg, hopelessness, feeling entrapped, will to live) before and after a chat conversation with the suicide prevention helpline in the Netherlands (113 Suicide Prevention). Machine learning text analysis was used to predict help seeker scores on these factors. Using 2 approaches for interpreting machine learning models, we identified text messages from helpers in a chat that contributed the most to the prediction of the model. Results: According to the machine learning model, helpers’ positive affirmations and expressing involvement contributed to improved scores of the help seekers. Use of macros and ending the chat prematurely due to the help seeker being in an unsafe situation had negative effects on help seekers. Conclusions: This study reveals insights for improving helpline chats, emphasizing the value of an evocative style with questions, positive affirmations, and practical advice. It also underscores the potential of machine learning in helpline chat analysis.

Contains fulltext : 307349.pdf (Publisher’s version ) (Open Access), Background: Railway suicide has profound implications for the victims and their family, and affects train drivers, railway personnel, emergency services and witnesses. To inform a multilevel prevention strategy, more knowledge is required about psychosocial and precipitating risk factors of railway suicide. Methods: Data from Statistics Netherlands of all suicides between 2017 and 2021 (n = 9.241) of whom 986 died by railway suicide and interview data from a psychosocial autopsy of railway suicide decedents (n = 39) were integrated. We performed logistic regression analyses to identify sociodemographic predictors of railway suicide compared to other methods of suicide. The Constant Comparative Method was subsequently employed on interview data from the psychosocial autopsy to identify patterns in psychosocial risk factors for railway suicide. Results: The strongest predictors of railway suicide compared to other suicide methods were young age (< 30 years old), native Dutch, a high educational level, living in a multi-person household (especially living with parents or in an institution), living in a rural area and a high annual household income of > 150.000 euros. Several subgroups emerged in the psychosocial autopsy interviews, which specifically reflect populations at risk of railway suicide. These subgroups were [1] young adult males with autism spectrum disorder who strived for more autonomy and an independent life, [2] young adult females with persistent suicidal thoughts and behaviours, [3] middle-aged males with a persistent mood disorder who lived with family and who faced stressors proximal to the suicide in personal and professional settings, [4] male out-of-the-blue suicides and [5] persons with psychotic symptoms and a rapid deterioration. Conclusions: based on our findings we propose and discuss several recommendations to prevent railway suicide. We must continue to invest in a safe railway environment by training personnel and installing barriers. Addi, 12 p.

Background: Predicted increases in suicide were not generally observed in the early months of the COVID-19 pandemic. However, the picture may be changing and patterns might vary across demographic groups. We aimed to provide a timely, granular picture of the pandemic's impact on suicides globally. Methods: We identified suicide data from official public-sector sources for countries/areas-within-countries, searching websites and academic literature and contacting data custodians and authors as necessary. We sent our first data request on 22nd June 2021 and stopped collecting data on 31st October 2021. We used interrupted time series (ITS) analyses to model the association between the pandemic's emergence and total suicides and suicides by sex-, age- and sex-by-age in each country/area-within-country. We compared the observed and expected numbers of suicides in the pandemic's first nine and first 10-15 months and used meta-regression to explore sources of variation. Findings: We sourced data from 33 countries (24 high-income, six upper-middle-income, three lower-middle-income; 25 with whole-country data, 12 with data for area(s)-within-the-country, four with both). There was no evidence of greater-than-expected numbers of suicides in the majority of countries/areas-within-countries in any analysis; more commonly, there was evidence of lower-than-expected numbers. Certain sex, age and sex-by-age groups stood out as potentially concerning, but these were not consistent across countries/areas-within-countries. In the meta-regression, different patterns were not explained by countries’ COVID-19 mortality rate, stringency of public health response, economic support level, or presence of a national suicide prevention strategy. Nor were they explained by countries’ income level, although the meta-regression only included data from high-income and upper-middle-income countries, and there were suggestions from the ITS analyses that lower-middle-income countries fared less well

Inleiding: Voor suïcidepreventie is het van belang om groepen met een verhoogd risico op suïcide zo goed mogelijk te identificeren. Tot nog toe is er weinig bekend over interacties van meerdere risicofactoren. Machine learning-methoden bieden nieuwe mogelijk- heden voor flexibel, datagedreven, hypothesevrij en robuust onderzoek naar de interacties van risicofac- toren voor suïcide. Methode: In dit onderzoek is gebruikgemaakt van mi- crodata van het Centraal Bureau voor de Statistiek met sociaal-demografische gegevens van alle Nederlandse inwoners. Er is een machine learning-model ontwik- keld en uitgevoerd om interacties van risicofactoren voor suïcide te vinden. Resultaten: De resultaten laten disproportioneel hoge suïcide-incidenties zien onder 1) mensen met een arbeidsongeschiktheidsuitkering die nooit getrouwd zijn geweest, 2) arbeidsongeschikte mannen, 3) men- sen tussen de 55 en 69 jaar oud, die alleen wonen, nooit getrouwd zijn en wiens huishoudinkomen laag is. Daarnaast hebben we hoge suïcidecijfers gevonden onder mensen tussen de 25 en 39 jaar met een laag opleidingsniveau en onder verweduwde mannen. Conclusie: De bevindingen helpen om gericht inter- venties in te kunnen zetten om het aantal suïcides te verminderen.

Background: Each year, many help seekers in need contact health helplines for mental support. It is crucial that they receive support immediately, and that waiting times are minimal. In order to minimize delay, helplines must have adequate staffing levels, especially during peak hours. This has raised the need for means to predict the call and chat volumes ahead of time accurately. Motivated by this, in this paper, we analyze real-life data to develop models for accurately forecasting call volumes, for both phone and chat conversations for online mental health support. Methods: This research was conducted on real call and chat data (adequately anonymized) provided by 113 Suicide Prevention (Over ons | 113 Zelfmoordpreventie) (throughout referred to as ‘113’), the online helpline for suicide prevention in the Netherlands. Chat and phone call data were analyzed to better understand the important factors that influence the call arrival process. These factors were then used as input to several Machine Learning (ML) models to forecast the number of call and chat arrivals. Next to that, senior counselors of the helpline completed a web-based questionnaire after each shift to assess their perception of the workload. Results: This study has led to several remarkable and key insights. First, the most important factors that determine the call volumes for the helpline are the trend, and weekly and daily cyclic patterns (cycles), while monthly and yearly cycles were found to be non-significant predictors for the number of phone and chat conversations. Second, media events that were included in this study only have limited—and only short-term—impact on the call volumes. Third, so-called (S)ARIMA models are shown to lead to the most accurate prediction in the case of short-term forecasting, while simple linear models work best for long-term forecasting. Fourth, questionnaires filled in by senior counselors show that the experienced workload is mainly correlated to the number of c

Background: Targeted interventions for suicide prevention rely on adequate identification of groups at elevated risk. Several risk factors for suicide are known, but little is known about the interactions between risk factors. Interactions between risk factors may aid in detecting more specific sub-populations at higher risk. Methods: Here, we use a novel machine learning heuristic to detect sub-populations at ultra high-risk for suicide based on interacting risk factors. The data-driven and hypothesis-free model is applied to investigate data covering the entire population of the Netherlands. Findings: We found three sub-populations with extremely high suicide rates (i.e. >50 suicides per 100,000 person years, compared to 12/100,000 in the general population), namely: (1) people on unfit for work benefits that were never married, (2) males on unfit for work benefits, and (3) those aged 55–69 who live alone, were never married and have a relatively low household income. Additionally, we found two sub-populations where the rate was higher than expected based on individual risk factors alone: widowed males, and people aged 25–39 with a low level of education. Interpretation: Our model is effective at finding ultra-high risk groups which can be targeted using sub-population level interventions. Additionally, it is effective at identifying high-risk groups that would not be considered risk groups based on conventional risk factor analysis.

Contains fulltext : 307282.pdf (Publisher’s version ) (Open Access), Background: while there are many benefits for young people to use social media, adverse effects such as cyberbullying, online challenges, social comparison and imitation may provoke and aggravate suicidal thoughts and behaviors. The influence of social media on mental health and suicidal thoughts and behaviours has been amply studied, but there is little empirical evidence for its potential role in adolescent suicides. The current study aimed to inform digital suicide prevention strategies by examining the meaning of social media in the lives of young suicide victims and elucidating the harmful and supportive effects of social media use on their wellbeing and distress. Methods: data were analyzed from a psychological autopsy study of 35 adolescents who died by suicide in the Netherlands (43% of all adolescents who died by suicide in that year). These were 18 girls and 17 boys. All were under the age of twenty years, with an average of seventeen years. Interpretative Phenomenological Analysis was performed of 55 semi structured interviews with peers and parents of the decedents. Results: young people benefitted from peer support and recovery stories. However, various themes were discussed relating to the harmful effects of social media, including dependency, triggers and imitation, challenges, cybervictimization and psychological entrapment. The themes of dependency and triggers and imitation were more salient in young females. A group of girls cultivated an online identity around their suicidal thoughts and behaviours. Next-of-kin, particularly parents, faced various challenges to talk to the adolescents about social media use, including technological illiteracy, online anonymity, and the youths’ closedness. Conclusions: based on the findings, we recommend education to stimulate the digital literacy of parents, health workers and educators, supporting conscientious social media use in young people, and extending the prevention of cyberbullying. We encourage future r, 11 p.

Item does not contain fulltext, Inleiding: In Nederland betreft 31% van de suïcides op het spoor een jong persoon (tot 30 jaar). Jongeren zijn wellicht oververtegenwoordigd omdat zij impulsiever kunnen handelen en minder toegang hebben tot andere dodelijke middelen. Omdat het aantal suïcides onder jongeren stijgt, heeft dit onderzoek als doel om inzicht te krijgen in de kenmerken van jongeren die op het spoor overlijden. Methode: Dit onderzoek gebruikt microdata van het CBS en interviewdata van een psychosociaal autopsieonderzoek in de periode 2017-2021. Er zijn chi-kwadraattoetsen, logistische regressieanalyses en kwalitatieve analyses uitgevoerd om kenmerken van spoorsuïcides te identificeren. Resultaten: In totaal overleden 1.366 jongeren door zelfdoding, van wie 304 jongeren op het spoor. Dit waren vooral jonge mannen. Nederlandse herkomst, onderwijs volgen, laag opgeleid zijn en woonachtig bij ouders zijn waren kenmerken die vaker voorkwamen bij spoorsuïcides dan bij andere methoden, waarvan alleen onderwijs volgen sterk samenhing met spoorsuïcides. Opvallende thema’s in de interviews waren problemen op school, het niet kunnen realiseren van een zelfstandig leven en psychische problemen van jonge mannen met autisme. Beschouwing en conclusie: Dit onderzoek geeft inzicht in de kenmerken van jongeren die zijn overleden door zelfdoding op het spoor. Naast fysieke maatregelen is in het onderwijs suïcidepreventie nodig en moeten er betere signalering en hulp komen voor jongeren met autisme.

Contains fulltext : 307280.pdf (Publisher’s version ) (Open Access), Background: Around 700,000 people die by suicide each year. While the global number of suicides declined over the last decade, the rates remained unchanged in the Netherlands. With this study, we aimed to provide guiding principles for the implementation of a national standardized psychological autopsy to better understand and prevent suicide, by exploring stakeholder perceptions and needs, and barriers to implementation. Methods: We interviewed 47 representative stakeholders from various fields (e.g., mental healthcare professionals, policy advisors, researchers). A semi structured interview design was used, based on the RE-AIM and Consolidated Framework for Implementation Research (CFIR) theoretical frameworks. Results: Themes relating to stakeholder perceptions and needs for a standardized psychological autopsy included valorization, accountability, integrability and the needs of the bereaved. Stakeholders believed that participation in a psychological autopsy can help bereaved in their process of grief but noted that evidence to frame the psychological autopsy as postvention is insufficient. The primary focal point should accordingly be to better understand and prevent suicide. Several key limitations of the proposed psychological autopsy approach were detailed, both methodological and implementational. Conclusion: The stakeholder analysis delineates guiding principles for implementation. Stakeholders believe that a standardized psychological autopsy has merit, provided that key considerations, including valorization and accountability, are integrated in its design. Routine evaluation should be ensured. The findings may guide policy makers and researchers in their endeavors to support a learning, community-based approach for suicide prevention based on a standardized psychological autopsy.

Background: Preventatives measures to combat the spread of COVID− 19 have introduced social isolation, loneliness and financial stress. This study aims to identify whether the COVID-19 pandemic is related to changes in suicide-related problems for help seekers on a suicide prevention helpline. Methods: A retrospective cohort study was conducted using chat data from a suicide prevention helpline in the Netherlands. The natural language processing method BERTopic was used to detect common topics in messages from December 1, 2019 until June 1, 2020 (N = 8589). Relative topic occurrence was compared before and during the lock down starting on March 23, 2020. The observed changes in topic usage were likewise analyzed for male and female, younger and older help seekers and help seekers living alone. Results: The topic of the COVID-19 pandemic saw an 808% increase in relative occurrence after the lockdown. Furthermore, the results show that help seeker increased mention of thanking the counsellor (+ 15%), and male and young help seekers were grateful for the conversation (+ 45% and + 32% respectively). Coping methods such as watching TV (− 21%) or listening to music (− 15%) saw a decreased mention. Plans for suicide (− 9%) and plans for suicide at a specific location (− 15%) also saw a decreased mention. However, plans for suicide were mentioned more frequently by help seekers over 30 years old (+ 11%) or who live alone and (+ 52%). Furthermore, male help seekers talked about contact with emergency care (+ 43%) and panic and anxiety (+ 24%) more often. Negative emotions (+ 22%) and lack of self-confidence (+ 15%) were mentioned more often by help seekers under 30, and help seekers over 30 saw an increased mention of substance abuse (+ 9%). Conclusion: While mentions of distraction, social interaction and plans for suicide decreased, expressions of gratefulness for the helpline increased, highlighting the importance of contact to help seekers during the lockdown. Help seeke

Contains fulltext : 235991.pdf (Publisher’s version ) (Open Access), Objectives: There is limited insight into gender differences in suicide-related communication (SRC) in youths. SRC is defined as "the act of conveying one's own suicide ideation, intent or behaviours to another person". Increasing our understanding of SRC in youths will enable us to recognize and specify needs of female versus male youths. The current study explores SRC in a sample of Dutch suicide victims aged under 20 and examines gender differences. Methods: Interview data from a psychological autopsy study of 35 youths who died by suicide in the Netherlands in 2017 were analysed. Qualitative analyses were performed to examine explicit SRC throughout the youths' lives and implicit SRC during the last months prior to suicide. We employed the Constant Comparative Method to explore patterns in the debut, form, frequency, medium, content, type of recipient, and SRC in the last months prior to suicide death. Results: We identified commonalities in the SRC of youths, including the content of suicide notes and an emphasis on suicide method and preparation in the last months. Girls, however, had an earlier debut of SRC, a higher frequency of explicit SRC, and more often directed SRC towards varied types of recipients compared to boys. Moreover, SRC of girls seemed focused on coping and achieving support from others more than SRC of boys. The SRC of boys in comparison to girls was often ambiguous or diluted by "humorous" connotations. Conclusion: Unique patterns in SRC of boys and girls posed corresponding challenges for next of kin to interpret communications and respond adequately to SRC. The early debut of girls' SRC highlights the importance of early screening and prevention efforts in girls, while the late debut and ambiguity in boys' SRC implores professionals and next of kin to encourage young males to be unequivocal about suicide ideation or intent.

Contains fulltext : 234918.pdf (Publisher’s version ) (Open Access), In this study, we examined the feasibility and added value of including peer informants in a psychological autopsy study of youth suicides. Peer semi-structured interview data from 16 cases were analyzed qualitatively and compared to parent data. Results show that peers added information to parents' narratives in general and particularly on social relationships, bullying, school experiences, social media, and family relations. Peers also provided additional information on the presence of certain issues (such as social media contagion) as well as on the emotional impact from certain adverse events that seemed to have functioned as precipitating factors. We conclude that including peers in psychological autopsy studies of youth suicides is feasible and of added value but that more research is desirable. The results initially can be used in the design of psychological autopsies so that the maximum amount of information about each suicide will be learned.

Purpose: In 2017, the European Alliance against Depression (EAAD) programme was introduced in the Netherlands through the creation of six local Suicide Prevention Action Networks (SUPRANET Community). This programme consists of interventions on four levels: (1) a public awareness campaign, (2) training local gatekeepers, (3) targeting high-risk persons in the community and (4) training of primary care professionals. This study aims to gain insight into the effectiveness of the SUPRANET programme on attitudinal changes in the general public by studying the exposure–response relationship. Methods: A repeated cross-sectional design, using general population surveys to measure key variables over time. The surveys were conducted in the six intervention regions (N = 2586) and in the Netherlands as a whole as a control region (N = 4187) and include questions on socio-demographic variables, brand awareness of the Dutch helpline, perceived taboo on suicide, attitudes towards depression and help-seeking. To examine the exposure–response relationship, regions were differentiated into 3 groups: low, medium and high exposure of the SUPRANET programme. Results: The results revealed that respondents in the intervention regions considered professional help to be more valuable and were more likely to be familiar with the Dutch helpline than respondents in the control region. In the exposure–response analyses, the grading of effects was too small to reach statistical significance. Conclusion: Our study provides the first evidence for the effectiveness of the SUPRANET Community programme on creating attitudinal change in the general public.

Background: The working environment of a suicide prevention helpline requires high emotional and cognitive awareness from chat counselors. A shared opinion among counselors is that as a chat conversation becomes more difficult, it takes more effort and a longer amount of time to compose a response, which, in turn, can lead to writer's block. Objective: This study evaluates and then designs supportive technology to determine if a support system that provides inspiration can help counselors resolve writer's block when they encounter difficult situations in chats with help-seekers. Methods: A content-based recommender system with sentence embedding was used to search a chat corpus for similar chat situations. The system showed a counselor the most similar parts of former chat conversations so that the counselor would be able to use approaches previously taken by their colleagues as inspiration. In a within-subject experiment, counselors' chat replies when confronted with a difficult situation were analyzed to determine if experts could see a noticeable difference in chat replies that were obtained in 3 conditions: (1) with the help of the support system, (2) with written advice from a senior counselor, or (3) when receiving no help. In addition, the system's utility and usability were measured, and the validity of the algorithm was examined. Results: A total of 24 counselors used a prototype of the support system; the results showed that, by reading chat replies, experts were able to significantly predict if counselors had received help from the support system or from a senior counselor (P=.004). Counselors scored the information they received from a senior counselor (M=1.46, SD 1.91) as significantly more helpful than the information received from the support system or when no help was given at all (M=-0.21, SD 2.26). Finally, compared with randomly selected former chat conversations, counselors rated the ones identified by the content-based recommendation system as s

Objective: This study aimed to establish differences between suicide decedents and a reference population across various health care settings.Methods: This population-wide registration study combined death statistics, sociodemographic data and health care data from Statistics Netherlands. From 2010 to 2016, 12,015 suicide cases and a random reference group of 132,504 were included and assigned to one of the three health care settings; mental health (MH) care, primary care or no care. Logistic regression analyses were performed to determine differences in suicide risk factors across settings.Results: In the 1–2 year period before suicide, 52% of the suicide decedents received MH care, 41% received GP care only and 7% received neither. Although sociodemographic factors showed significant differences across settings, the suicide risk profiles were not profoundly distinctive. A decreasing trend in suicide risk across health care settings became apparent for male gender, income level and being in a one-person or one-parent household, whereas for other factors (middle and older age, non-Western migration background, couples without children and people living in more sparsely populated areas), risk of suicide increased when health care setting became more specialized.Limitations: Because of the data structure, 18 months of suicide decedents’ health care use were compared with two years health care use of the reference group, which likely led to an underestimation of the reported differences.Conclusion: Although there are differences between suicide decedents and a reference group across health care settings, these are not sufficiently distinctive to advocate for a setting-specific approach to suicide prevention.

This dataset contains all data and analysis scripts to the research conducted for the JMIR paper: "Content-based Recommender Support System for Counselors in a Suicide Prevention Chat Helpline: Design and Evaluation Study"

Background: In 2017, the European Alliance against Depression (EAAD) was introduced in The Netherlands through the creation of six Suicide Prevention Action Networks (SUPRANET Community). The intervention was launched with a national suicide prevention awareness campaign. This campaign aims to encourage the general public to talk about suicide. This study aimed to gain insight into the effectiveness of the campaign in achieving attitudinal change in the general public, as stigmas related to mental health disorders and -services are an important reason for insufficient help-seeking. Methods: A repeated cross-section design, using general population surveys (N = 6,773) to measure key variables over time. The survey includes questions on socio-demographic variables, campaign visibility, brand awareness of the Dutch helpline, perceived taboo on suicide, attitudes towards depression and help-seeking. Results: The public awareness campaign was predominantly visible among the younger generation. Respondents who indicated having seen the public awareness campaign showed more openness towards seeking professional help and were considerably more likely to be familiar with the Dutch helpline than those who reported not having seen the campaign. Campaign awareness also seemed to relate to a higher perceived taboo on suicide and a lower estimation of the value of professional help. Limitations: Due to the nature of the intervention, we used a quasi-experimental design. Self-report can lead to desirability bias, especially when measuring attitudes and stigmas. Conclusions: Our results strengthen the idea that awareness campaigns can make a contribution to informing the general public about mental health services and improving help-seeking behaviour.

Background: Suicide is a complex issue. Due to the relative rarity of the event, studies into risk factors are regularly limited by sample size or biased samples. The aims of the study were to find risk factors for suicide that are robust to intercorrelation, and which were based on a large and unbiased sample. Methods: Using a training set of 5854 suicides and 596,416 control cases, we fit a logistic regression model and then evaluate the performance on a test set of 1425 suicides and 594,893 control cases. The data used was microdata of Statistics Netherlands (CBS) with data on each inhabitant of the Netherlands. Results: Taking the effect of possible correlating risk factors into account, those with a higher risk for suicide are men, middle-aged people, people with low income, those living alone, the unemployed, and those with mental or physical health problems. People with a lower risk are the highly educated, those with a non-western immigration background, and those living with a partner. Conclusion: We confirmed previously known risk factors such as male gender, middle-age, and low income and found that they are risk factors that are robust to intercorrelation. We found that debt and urbanicity were mostly insignificant and found that the regional differences found in raw frequencies are mostly explained away after correction of correlating risk factors, indicating that these differences were primarily caused due to the differences in the demographic makeup of the regions. We found an AUC of 0.77, which is high for a model predicting suicide death and comparable to the performance of deep learning models but with the benefit of remaining explainable.

Background Suicidal behaviour is difficult to detect in the general practice. Machine learning (ML) algorithms using routinely collected data might support General Practitioners (GPs) in the detection of suicidal behaviour. In this paper, we applied machine learning techniques to support GPs recognizing suicidal behaviour in primary care patients using routinely collected general practice data. Methods This case-control study used data from a national representative primary care database including over 1.5 million patients (Nivel Primary Care Database). Patients with a suicide (attempt) in 2017 were selected as cases (N = 574) and an at risk control group (N = 207,308) was selected from patients with psychological vulnerability but without a suicide attempt in 2017. RandomForest was trained on a small subsample of the data (training set), and evaluated on unseen data (test set). Results Almost two-third (65%) of the cases visited their GP within the last 30 days before the suicide (attempt). RandomForest showed a positive predictive value (PPV) of 0.05 (0.04–0.06), with a sensitivity of 0.39 (0.32–0.47) and area under the curve (AUC) of 0.85 (0.81–0.88). Almost all controls were accurately labeled as controls (specificity = 0.98 (0.97–0.98)). Among a sample of 650 at-risk primary care patients, the algorithm would label 20 patients as high-risk. Of those, one would be an actual case and additionally, one case would be missed. Conclusion In this study, we applied machine learning to predict suicidal behaviour using general practice data. Our results showed that these techniques can be used as a complementary step in the identification and stratification of patients at risk of suicidal behaviour. The results are encouraging and provide a first step to use automated screening directly in clinical practice. Additional data from different social domains, such as employment and education, might improve accuracy.

Contains fulltext : 224905.pdf (publisher's version ) (Open Access), Background: Suicidal behaviour is difficult to detect in the general practice. Machine learning (ML) algorithms using routinely collected data might support General Practitioners (GPs) in the detection of suicidal behaviour. In this paper, we applied machine learning techniques to support GPs recognizing suicidal behaviour in primary care patients using routinely collected general practice data. Methods: This case-control study used data from a national representative primary care database including over 1.5 million patients (Nivel Primary Care Database). Patients with a suicide (attempt) in 2017 were selected as cases (N = 574) and an at risk control group (N = 207,308) was selected from patients with psychological vulnerability but without a suicide attempt in 2017. RandomForest was trained on a small subsample of the data (training set), and evaluated on unseen data (test set). Results: Almost two-third (65%) of the cases visited their GP within the last 30 days before the suicide (attempt). RandomForest showed a positive predictive value (PPV) of 0.05 (0.04-0.06), with a sensitivity of 0.39 (0.32-0.47) and area under the curve (AUC) of 0.85 (0.81-0.88). Almost all controls were accurately labeled as controls (specificity = 0.98 (0.97-0.98)). Among a sample of 650 at-risk primary care patients, the algorithm would label 20 patients as high-risk. Of those, one would be an actual case and additionally, one case would be missed. Conclusion: In this study, we applied machine learning to predict suicidal behaviour using general practice data. Our results showed that these techniques can be used as a complementary step in the identification and stratification of patients at risk of suicidal behaviour. The results are encouraging and provide a first step to use automated screening directly in clinical practice. Additional data from different social domains, such as employment and education, might improve accuracy.

Contains fulltext : 222224.pdf (publisher's version ) (Open Access), Objectives: In the Netherlands, there was a sharp increase in the number of suicides among 10- to 19-year-olds in 2017. A multi-method psychological autopsy study (PA) was conducted to assess feasibility, identify related factors, and study the interplay of these factors to inform suicide prevention strategies. Methods: Coroners identified youth suicides in 2017 in their records and then general practitioners (GPs) contacted the parents of these youths. Over a period of 7 months, 66 qualitative interviews were held with the parents, peers, and teachers, providing information on precipitating factors and five topics involving 35 cases (17 boys and 18 girls, mean age 17 years). Furthermore, 43 parents and care professionals filled in questionnaires to examine risk and care-related factors. Qualitative and quantitative analyses were performed. Results: Although registration problems faced by coroners and resistance to contacting bereaved families by GPs hampered the recruitment, most parents highly appreciated being interviewed. Several adverse childhood experiences played a role at an individual level, such as (cyber) bullying, parental divorce, sexual abuse, as well as complex mental disorders, and previous suicide attempts. Two specific patterns stood out: (1) girls characterized by insecurity and a perfectionist attitude, who developed psychopathology and dropped out of school, and (2) boys with a developmental disorder, such as autism, who were transferred to special needs education and therefore felt rejected. In addition, adolescents with complex problems had difficulty finding appropriate formal care. Regarding potential new trends, contagion effects of social media use in a clinical setting and internet use for searching lethal methods were found. Conclusion: This first national PA study showed that, as expected, a variety of mostly complex clusters of problems played a role in youth suicides. An infrastructure is needed to continuously monitor, evaluate, and

Introduction Psychotherapy may reduce suicidal thoughts and behaviour, but its effectiveness is not well examined. Furthermore, conventional meta-analyses are unable to test possible effects of moderators affecting this relationship. This protocol outlines the building of a comprehensive database of the literature in this research field. In addition, we will conduct an individual patient data meta-analysis (IPD-MA) to establish the effectiveness of psychotherapy in reducing suicidality, and to examine which factors moderate the efficacy of these interventions. Methods and analysis To build a comprehensive database, randomised controlled trials examining the effect of any psychotherapy targeting any psychiatric disorder on suicidal thoughts or behaviour will be identified by running a systematic search in PubMed, Embase, PsycINFO, Web of Science, Scopus and The Cochrane Central Register of Controlled Trials from data inception to 12 August 2019. For the IPD-MA, we will focus on adult outpatients with suicidal ideation or behaviour. In addition, as a comparison group we will focus on a control group (waiting-list, care as usual or placebo). A 1-stage IPD-MA will be used to determine the effectiveness of psychotherapy on suicidal ideation, suicide attempts and/or suicide deaths, and to investigate potential patient-related and intervention-related moderators. Subgroup and sensitivity analyses will be conducted to test the robustness of the findings. Additionally, a conventional MA will be conducted to determine the differences between studies that provided IPD and those that did not. IPD-MA may determine the effectiveness of psychotherapy in reducing suicidality and provide insights into the moderating factors influencing the efficacy of psychotherapy. Answering these questions will inform mental healthcare practitioners about optimal treatments for different groups of individuals with suicidal ideation and/or behaviour and consequently help to reduce suicide risk. Eth

In 2000 to 2016 the highest number of suicides among Dutch youths under 20 in any given year was 58 in 2013. In 2017 this number increased to 81 youth suicides. To get more insight in what types of youths died by suicide, particularly in recent years (2013-2017) we looked at micro-data of Statistics Netherlands and counted suicides among youths till 23, split out along gender, age, regions, immigration background and place in household and compared this to the general population of youths in the Netherlands. We also compared the demographics of young suicide victims to those of suicide victims among the population as a whole. We found higher suicide rates among male youths, older youths, those of Dutch descent and youths living alone. These differences were generally smaller than in the population as a whole. There were also substantial geographical differences between provinces and healthcare regions. The method of suicide is different in youth compared to the population as a whole: relatively more youth suicides by jumping or lying in front of a moving object and relatively less youth suicides by autointoxication or drowning, whereas the most frequent method of suicide among both groups is hanging or suffocation.

Recognizing the importance of digital communication, major suicide prevention helplines have started offering crisis intervention by chat. To date there is little evidence supporting the effectiveness of crisis chat services. To evaluate the reach and outcomes of the 113Online volunteer-operated crisis chat service, 526 crisis chat logs were studied, replicating the use of measures that were developed to study telephone crisis calls. Reaching a relatively young population of predominantly females with severe suicidality and (mental) health problems, chat outcomes for this group were found to be comparable to those found for crisis calls to U.S. Lifeline Centers in 2003-2004, with similar but not identical associations with specific helpers' styles and attitudes. Our findings support a positive effect of the 113Online chat service, to be enhanced by practice standards addressing an apparent lack of focus on the central issue of suicidality during chats, as well as by the development of best practices specific for online crisis intervention.