Attempts to use artificial intelligence (AI) in psychiatric disorders show moderate success, highlighting the potential of incorporating information from clinical assessments to improve the models. This study focuses on using large language models (LLMs) to detect suicide risk from medical text in psychiatric care.

To extract information about suicidality status from the admission notes in electronic health records (EHRs) using privacy-sensitive, locally hosted LLMs, specifically evaluating the efficacy of Llama-2 models.

We compared the performance of several variants of the open source LLM Llama-2 in extracting suicidality status from 100 psychiatric reports against a ground truth defined by human experts, assessing accuracy, sensitivity, specificity and F1 score across different prompting strategies.

A German fine-tuned Llama-2 model showed the highest accuracy (87.5%), sensitivity (83.0%) and specificity (91.8%) in identifying suicidality, with significant improvements in sensitivity and specificity across various prompt designs.

The study demonstrates the capability of LLMs, particularly Llama-2, in accurately extracting information on suicidality from psychiatric records while preserving data privacy. This suggests their application in surveillance systems for psychiatric emergencies and improving the clinical management of suicidality by improving systematic quality control and research.

Affective responses to the menstrual cycle vary widely. Some individuals experience severe symptoms like those with premenstrual dysphoric disorder, while others have minimal changes. The reasons for these differences are unclear, but prior studies suggest stressor exposure may play a role. However, research in at-risk psychiatric samples is lacking.

In a large clinical sample, we conducted a prospective study of how lifetime stressors relate to degree of affective change across the cycle. 114 outpatients with past-month suicidal ideation (SI) provided daily ratings (n = 6187) of negative affect and SI across 1–3 menstrual cycles. Participants completed the Stress and Adversity Inventory (STRAIN), which measures different stressor exposures (i.e. interpersonal loss, physical danger) throughout the life course, including before and after menarche. Multilevel polynomial growth models tested the relationship between menstrual cycle time and symptoms, moderated by stressor exposure.

Greater lifetime stressor exposure predicted a more pronounced perimenstrual increase in active SI, along with marginally significant similar patterns for negative affect and passive SI. Additionally, pre-menarche stressors significantly increased the cyclicity of active SI compared to post-menarche stressors. Exposure to more interpersonal loss stressors predicted greater perimenstrual symptom change of negative affect, passive SI and active SI. Exploratory item-level analyses showed that lifetime stressors moderated a more severe perimenstrual symptom trajectory for mood swings, anger/irritability, rejection sensitivity, and interpersonal conflict.

These findings suggest that greater lifetime stressor exposure may lead to heightened emotional reactivity to ovarian hormone fluctuations, elevating the risk of psychopathology.

Suicide is one of the major causes of premature death in patients diagnosed with a schizophrenia-spectrum psychotic disorder. However, associations between psychotic-like experiences in youth and suicidality in later life remain under-researched.

We aimed to investigate any associations between early experiences of thought interference and auditory-verbal hallucinations (AVHs) with first-rank symptoms of schizophrenia and suicidal thoughts and behaviours in adulthood.

This study used data from the Avon Longitudinal Study of Parents and Children (ALSPAC). We calculated combined thought interference score at ages 11 years 8 months, 13 years 1 month, 14 years 1 month and 16 years 6 months. We also assessed AVHs at the same age points. For outcome variables, we used specific variables measuring delusions of control, AVHs and suicidality at 24 years of age. We carried out logistic regressions and mediation analyses to assess the relationships among these variables.

Thought interference and AVHs at all ages throughout childhood and adolescence were associated with suicidal thoughts and behaviours, and also with clinically more significant symptoms of delusions of control and AVHs at age 24. Substance use-induced psychotic-like experiences mediated a large proportion of the relationship between early psychotic-like experiences and suicidality in later life.

Thought interference and AVHs in childhood and adolescence are associated with first-rank symptoms and suicidality in adulthood. Mental health interventions in children and adolescents need to take into account the impact of specific psychotic-like experiences and allow for the early detection of thought interference and AVH-related symptoms.

Suicidal thoughts and behaviors are elevated among active-duty service members (ADSM) and veterans compared to the general population. Hence, it is a priority to examine maintenance factors underlying suicidal ideation among ADSM and veterans to develop effective, targeted interventions. In particular, interpersonal risk factors, hopelessness, and overarousal have been robustly connected to suicidal ideation and intent.

To identify the suicidal ideation risk factors that are most relevant, we employed network analysis to examine between-subjects (cross-sectional), contemporaneous (within seconds), and temporal (across four hours) group-level networks of suicidal ideation and related risk factors in a sample of ADSM and veterans (participant n = 92, observations n = 10 650). Participants completed ecological momentary assessment (EMA) surveys four times a day for 30 days, where they answered questions related to suicidal ideation, interpersonal risk factors, hopelessness, and overarousal.

The between-subjects and contemporaneous networks identified agitation, not feeling close to others, and ineffectiveness as the most central symptoms. The temporal network revealed that feeling ineffective was most likely to influence other symptoms in the network over time.

Our findings suggest that ineffectiveness, low belongingness, and agitation are important drivers of moment-to-moment and longitudinal relations between risk factors for suicidal ideation in ADSM and veterans. Targeting these symptoms may disrupt suicidal ideation.

The mental health of sexual minority (SM) individuals remains overlooked and understudied in Czechia. We aimed to estimate (1) the prevalence rate and (2) the relative risk of common mental disorders and (3) the mental distress severity among the Czech SM people compared with the heterosexual population. In addition, we aimed to investigate help-seeking for mental disorders in SM people.

We used data from a cross-sectional, nationally representative survey of Czech community-dwelling adults, consisting of 3063 respondents (response rate = 58.62%). We used the Mini-International Neuropsychiatric Interview to assess the presence of mental disorders. In individuals scoring positively, we established help-seeking in the past 12 months. We assessed symptom severity using the 9-item Patient Health Questionnaire and the 7-item Generalized Anxiety Disorder scale. We computed the prevalence of mental disorders and the treatment gap with 95% confidence intervals. To assess the risk of having a mental disorder, we used binary logistic regression.

We demonstrated that the prevalence of current mental disorders was 18.85% (17.43–20.28), 52.27% (36.91–67.63), 33.33% (19.5–47.17) and 25.93% (13.85–38) in heterosexual, gay or lesbian, bisexual and more sexually diverse individuals, respectively. Suicidal thoughts and behaviours were present in 5.73% (4.88–6.57), 25.00% (11.68–38.32), 22.92% (10.58–35.25) and 11.11% (2.45–19.77) of heterosexual, gay or lesbian, bisexual and more sexually diverse individuals, respectively. After confounder adjustment, gay or lesbian individuals were more likely to have at least one current mental disorder compared with heterosexual counterparts (odds ratio = 3.51; 1.83–6.76). For bisexual and sexually more diverse individuals, the results were consistent with a null effect (1.85; 0.96–3.45 and 0.89; 0.42–1.73). The mean depression symptom severity was 2.96 (2.81–3.11) in heterosexual people and 4.68 (2.95–6.42), 7.12 (5.07–9.18) and 5.17 (3.38–6.95) in gay or lesbian, bisexual and more sexually diverse individuals, respectively. The mean anxiety symptom severity was 1.97 (1.85–2.08) in heterosexual people and 3.5 (1.98–5.02), 4.63 (3.05–6.2) and 3.7 (2.29–5.11) in gay or lesbian, bisexual and more sexually diverse individuals, respectively. We demonstrated broadly consistent levels of treatment gap in heterosexual and SM individuals scoring positively for at least one current mental disorder (82.91%; 79.5–85.96 vs. 81.13%; 68.03–90.56).

We provide evidence that SM people in Czechia have substantially worse mental health outcomes than their heterosexual counterparts. Systemic changes are imperative to provide not only better and more sensitive care to SM individuals but also to address structural stigma contributing to these health disparities.

Gender dysphoria is associated with suicidality among transgender and gender-diverse (TGD) people. Gender dysphoria also results in a stress on appearance.

The objectives of this study were to examine: (a) whether appearance anxiety mediates the effect of gender dysphoria on suicidality; and (b) whether gender identity moderates the mediating effect of appearance anxiety.

A total of 117 769 college and university students were recruited in this cross-sectional study from Jilin Province, China. After screening based on participants’ gender identity, 2352 TGD young people (aged from 15 to 25 years) were divided into three subgroups: female to male (FTM), male to female (MTF) and non-binary. Self-report inventories measured gender dysphoria, suicidality and appearance anxiety. A structural equation model was run to examine the relationships among TGD gender identity, gender dysphoria, appearance anxiety and suicidality.

Among TGD young people, gender dysphoria was significantly positively associated with suicidality (β = 0.15, 95% CI = 0.11–0.18, P < 0.001). Appearance anxiety partially mediated the association between gender dysphoria and suicidality (β = 0.07, 95% CI = 0.05–0.08, P < 0.001). Gender identity moderated the mediating effects: compared with individuals with FTM identity, among those with MTF and non-binary identities, gender dysphoria showed stronger positive effects on appearance anxiety, and appearance anxiety showed greater effects in mediating the association between gender dysphoria and suicidality.

Among TGD young people, gender dysphoria is significantly associated with suicidality via appearance anxiety, with gender identity moderating the mediating effects. Diverse treatments should consider the heterogeneity of TGD subgroups, with the aim of limiting the tendency of gender dysphoria to trigger appearance anxiety, thus further buffering against the risk of suicide.

Previous cross-sectional and case–control studies have proposed that decreased vitamin D levels are positively correlated with the risk of suicidality in adults. However, limited studies have examined the association between vitamin D and suicidality in adolescents. This study aimed to investigate the relationship between serum vitamin D and suicidality risk among early adolescents.

Data were obtained from a Chinese early adolescent cohort. In this cohort, seventh-grade students from a middle school in Anhui Province were invited to voluntarily participate in the baseline assessments and provide peripheral blood samples (in September 2019). The participants were followed up annually (in September 2020 and September 2021). Serum 25-hydroxyvitamin D [25(OH)D] and vitamin D–related single-nucleotide polymorphisms at baseline were measured in November 2021. Traditional observational and Mendelian randomization (MR) analyses were performed to examine the relationship between serum 25(OH)D at baseline and the risk of baseline and incident suicidality (i.e., suicidal ideation [SI], plans and attempts).

Traditional observational analysis did not reveal a significant linear or non-linear association of serum 25(OH)D concentration with the risks of baseline and 2-year incident suicidality in the total sample (P > .05 for all). Sex-stratified analysis revealed a non-linear association between the 25(OH)D concentration and the risk of baseline SI in women (Poverall = .002; Pnon-linear = .001). Moreover, the risk of baseline SI in the 25(OH) insufficiency group was lower than that in the 25(OH) deficiency group in the total sample (odds ratio [OR] = 0.69, 95% confidence interval [CI] = 0.51–0.92, P = .012). This difference remained significant in women (OR = 0.59, 95% CI = 0.40–0.87, P = .008) but not in men (OR = 0.78, 95% CI = 0.53–1.15, P = .205). Additionally, both linear and non-linear MR analyses did not support the causal effect of serum 25(OH)D concentration on the risk of baseline, 1-year and 2-year incident suicidality (P > .05 for all).

This study could not confirm the causal effect of vitamin D on suicidality risk among Chinese early adolescents. Future studies must confirm these findings with a large sample size.

Prospective studies on the mental health of university students highlighted a major concern. Specifically, young adults in academia are affected by markedly worse mental health status than their peers or adults in other vocations. This situation predisposes to exacerbated disability-adjusted life-years.

We enroled 1,388 students at the baseline, 557 of whom completed follow-up after 6 months, incorporating their demographic information and self-report questionnaires on depressive, anxiety and obsessive–compulsive symptoms. We applied multiple regression modelling to determine associations – at baseline – between demographic factors and self-reported mental health measures and supervised machine learning algorithms to predict the risk of poorer mental health at follow-up, by leveraging the demographic and clinical information collected at baseline.

Approximately one out of five students reported severe depressive symptoms and/or suicidal ideation. An association of economic worry with depression was evidenced both at baseline (when high-frequency worry odds ratio = 3.11 [1.88–5.15]) and during follow-up. The random forest algorithm exhibited high accuracy in predicting the students who maintained well-being (balanced accuracy = 0.85) or absence of suicidal ideation but low accuracy for those whose symptoms worsened (balanced accuracy = 0.49). The most important features used for prediction were the cognitive and somatic symptoms of depression. However, while the negative predictive value of worsened symptoms after 6 months of enrolment was 0.89, the positive predictive value is basically null.

Students’ severe mental health problems reached worrying levels, and demographic factors were poor predictors of mental health outcomes. Further research including people with lived experience will be crucial to better assess students’ mental health needs and improve the predictive outcome for those most at risk of worsening symptoms.

Midlife adults are experiencing a crisis of deaths of despair (i.e. deaths from suicide, drug overdose, and alcohol-related liver disease). We tested the hypothesis that a syndrome of despair-related maladies at midlife is preceded by psychopathology during adolescence.

Participants are members of a representative cohort of 1037 individuals born in Dunedin, New Zealand in 1972–73 and followed to age 45 years, with 94% retention. Adolescent mental disorders were assessed in three diagnostic assessments at ages 11, 13, and 15 years. Indicators of despair-related maladies across four domains – suicidality, substance misuse, sleep problems, and pain – were assessed at age 45 using multi-modal measures including self-report, informant-report, and national register data.

We identified and validated a syndrome of despair-related maladies at midlife involving suicidality, substance misuse, sleep problems, and pain. Adults who exhibited a more severe syndrome of despair-related maladies at midlife tended to have had early-onset emotional and behavioral disorders [β = 0.23, 95% CI (0.16–0.30), p < 0.001], even after adjusting for sex, childhood SES, and childhood IQ. A more pronounced midlife despair syndrome was observed among adults who, as adolescents, were diagnosed with a greater number of mental disorders [β = 0.26, 95% CI (0.19–0.33), p < 0.001]. Tests of diagnostic specificity revealed that associations generalized across different adolescent mental disorders.

Midlife adults who exhibited a more severe syndrome of despair-related maladies tended to have had psychopathology as adolescents. Prevention and treatment of adolescent psychopathology may mitigate despair-related maladies at midlife and ultimately reduce deaths of despair.

Evidence from pandemic and pre-pandemic studies conducted globally indicates that people with disabilities (PWDs) have a higher risk for suicidality. However, none of these studies has assessed suicidality among PWDs in Bangladesh.

The purpose of this study was to determine the prevalence of and factors associated with suicidal ideation among PWDs during the COVID-19 pandemic in Bangladesh.

Using a snowball sampling technique, a cross-sectional survey was conducted from February to April 2021 among PWDs from six districts in the northern region of Bangladesh. Information related to sociodemographic factors, clinical characteristics, behavioural factors and suicidal ideation was collected. Chi-squared test and logistic regression were used to describe the data and explain the relationship of factors associated with suicidal ideation.

The prevalence of COVID-19-related past-year suicidal ideation was 23.9%. The factors associated with suicidal ideation included: age above 35 years, being female, acquiring a disability later in life, lack of sleep and current substance use. In addition, higher education appeared to be a protective factor against suicidal ideation.

This study highlighted that PWDs had an increased risk of suicide; that is, one-fourth of them had past-year suicidal ideation. This may have been because of COVID-19-related restrictions and stressors. Thus, the government and policy makers need to pay more attention to developing effective suicide assessment, treatment and management strategies, especially for at-risk groups, to minimise the impact of the COVID-19 outbreak.

Among asylum seekers in a high-risk unstable post-displacement context, we aimed to investigate the prevalence of and risk for suicidal ideation (study 1), and then to test whether and how Mindfulness-Based Trauma Recovery for Refugees (MBTR-R) may prevent or treat suicidal ideation (study 2).

Study 1 was conducted among a community sample of N = 355 (31.8% female) East African asylum seekers in a high-risk urban post-displacement setting in the Middle East (Israel). Study 2 was a secondary analysis of a randomised waitlist-control trial of MBTR-R among 158 asylum-seekers (46.2% female) from the same community and post-displacement setting.

Prevalence of suicidal ideation was elevated (31%). Post-migration living difficulties, as well as posttraumatic stress, depression, anxiety and their multi-morbidity were strongly associated with suicidal ideation severity. Likewise, depression and multi-morbidity prospectively predicted the onset of suicidal ideation. Relative to its incidence among waitlist-control (23.1%), MBTR-R prevented the onset of suicidal ideation at post-intervention assessment (15.6%) and 5-week follow-up (9.8%). Preventive effects of MBTR-R on suicidal ideation were mediated by reduced posttraumatic stress, depression, anxiety and their multi-morbidity. MBTR-R did not therapeutically reduce current suicidal ideation present at the beginning of the intervention.

Findings warn of a public health crisis of suicidality among forcibly displaced people in high-risk post-displacement settings. Although preliminary, novel randomised waitlist-control evidence for preventive effects of MBTR-R for suicidal ideation is promising. Together, findings indicate the need for scientific, applied and policy attention to mental health post-displacement in order to prevent suicide among forcibly displaced people.

Several studies showed the high suicide risk of patients with attention deficit and hyperactivity disorder (ADHD), however most of these studies had cross-sectional design.

The aim of the current study was to review systematically those studies which investigated the suicide risk among ADHD patients with longitudinal design.

The systematic search was made on OVID Medline, PsychInfo, PubMed, Scopus, and Web of Science. The search terms were (ADHD OR attention deficit hyperactivity disorder) AND (suicide OR suicidal OR suicidality) AND (follow-up OR longitudinal study OR prospective study). Inclusion criteria were: written in English; participants under 18 years at the baseline; longitudinal, prospective studies; ADHD population at the baseline and at the follow-up; suicide behavior as primary outcome. Exclusion criteria were: the study did not contain empirical data, and reviews/meta-analyses and studies which aimed to investigate the drug treatment efficacy of ADHD.

18 papers were included in the systematic review. 10 articles were published in the last 5 years. 9 studies enrolled children aged under 12 at baseline. The follow-up periods varied between 2 and 17 years. 17 studies found a significant positive association between ADHD diagnosis at baseline and the future suicidal behavior and/or attempts at the follow-up. The affective comorbidity showed an association with the future suicide risk.

These results highlight the importance of screening suicidality in patient with ADHD and consider it during treatment. Further studies are needed to clarify the role of the treatment and comorbidities of ADHD in the increased suicide risk.

No significant relationships.

There has been increasing evidence of hormonal changes during reproductive events that lead to mood changes. However, studies on the severity of psychological problems according to the menopausal stage are limited. Thus, this study aimed to investigate the association between menopausal stages, depression and suicidality.

A total of 45 177 women who underwent regular health check-ups between 2015 and 2018 at Kangbuk Samsung Hospital were included. Participants were stratified into four groups (pre-menopause, early transition, late transition and post-menopause) based on the Stages of Reproductive Aging Workshop Criteria. The Center for Epidemiological Studies-Depression scale (CESD) was used to evaluate depressive symptoms, and the degree of depressive symptoms was classified as moderate (CESD score 16–24) or severe (CESD score ⩾ 25). To measure suicide risk, we administered questionnaires related to suicidal ideation.

Overall, the prevalence of CESD scores of 16–24 and ⩾ 25 was 7.6 and 2.8%, respectively. Menopausal stages were positively associated with depressive symptoms in a dose-dependent manner. Multivariable-adjusted prevalence ratios (PRs, 95% confidence intervals) for CESD scores of 16–24 comparing the stages of the early menopausal transition (MT), late MT and post-menopause to pre-menopause was 1.28 (1.16–1.42), 1.21 (1.05–1.38) and 1.58 (1.36–1.84), respectively. The multivariable-adjusted PRs for CESD scores ⩾ 25 comparing the stages of the early MT, late MT and post-menopause to pre-menopause were 1.31 (1.11–1.55), 1.39 (1.12–1.72), 1.86 (1.47–2.37), respectively. In addition, the multivariable-adjusted PRs for suicidal ideation comparing the early MT, late MT and post-menopause stages to the pre-menopause stage were 1.24 (1.12–1.38), 1.07 (0.93–1.24) and 1.46 (1.25–1.70) (p for trend <0.001), respectively.

These findings indicate that the prevalence of depressive symptoms and suicidal ideation increases with advancing menopausal stage, even pre-menopause.

Despite the potential benefits of open communication about possible desires to die for patients receiving palliative care, health professionals tend to avoid such conversations and often interpret desires to die as requests for medical aid in dying. After implementing trainings to foster an open, proactive approach toward desire to die, we requested trained health professionals to lead and document desire to die-conversations with their patients. In this article, we explore how trained health professionals experience an open (proactive) approach to desire to die-conversations with their patients.

Between April 2018 and March 2020, health professionals recorded their conversation-experiences on documentation sheets by answering seven open questions. A subsample was invited to offer deeper insights through semi-structured qualitative interviews. Interviews and documentation sheets were transcribed verbatim and analyzed thematically, then findings from both sources were compared and synthesized.

Overall, N = 29 trained health professionals documented N = 81 open desire to die-conversations. A subsample of n = 13 health professionals participated in qualitative interviews. Desire to die-conversations after the training were reported as a complex but overall enriching experience, illustrated in seven themes: (1) beneficial (e.g., establishing good rapport) and (2) hindering aspects (e.g., patients’ emotional barriers) of desire to die-conversations, (3) follow-up measures, (4) ways of addressing desire to die, as well as (5) patient reactions to it. The interviews offered space for health professionals to talk about (6) content of desire to die-conversation and (7) (self-)reflection (e.g., on patients’ biographies or own performance).

As part of an open (proactive) approach, desire to die-conversations hold potential for health professionals’ (self-)reflection and a deeper understanding of patient background and needs. They may lead to a strengthened health professional–patient relationship and potentially prevent suicide.

To assess the likelihood of attaining response/remission of depressive symptoms with esketamine nasal spray (ESK) plus standard of care (SoC) vs placebo nasal spray (PBO) plus SoC at 4 weeks in patients with major depressive disorder and active suicidal ideation with intent (MDSI) without early response.

A post hoc analysis of pooled data from ASPIRE I and ASPIRE II evaluated ESK plus SoC vs PBO plus SoC in adults with MDSI without response (≥50% improvement from baseline in Montgomery-Åsberg Depression Rating Scale [MADRS] score) at 24 hours after the first dose or at week 1 after the first two doses (ie, 24-hour and week 1 nonresponders). Response and remission (MADRS score ≤ 12) rates were assessed on day 25.

The analysis included 362 patients (n = 182, ESK plus SoC; n = 180, PBO plus SoC). Among 24-hour nonresponders, more patients receiving ESK plus SoC vs PBO plus SoC achieved response (63.9% vs 48.0%, P = .010) and remission (35.1% vs 24.4%, P = .074) at day 25. Odds of response/remission were higher with ESK plus SoC vs PBO plus SoC (response: 1.89, 95% CI, 1.17-3.05; remission: 1.48, 95% CI, 0.93-2.35). Similar findings were observed among week 1 nonresponders for response (48.4% vs 34.5%, P = .075), remission (25.0% vs 13.1%, P = .060), and odds of response/remission (response: 2.03, 95% CI, 1.22-3.40; remission: 1.63, 95% CI, 1.01-2.62).

Patients with MDSI not responding within the first week of treatment with ESK plus SoC may still benefit from a full 4-week treatment course.

Predictive values of multiple serum biomarkers for suicidal behaviours (SBs) have rarely been tested. This study sought to evaluate and develop a panel of multiple serum biomarkers for predicting SBs in outpatients receiving a 12-month pharmacotherapy programme for depressive disorders.

At baseline, 14 serum biomarkers and socio-demographic/clinical characteristics including previous suicidal attempt and present suicidal severity were evaluated in 1094 patients with depressive disorders without a bipolar diagnosis. Of these, 884 were followed for increased suicidal severity and fatal/non-fatal suicide attempt outcomes over a 12-month treatment period. Individual and combined effects of serum biomarkers on these two prospective SBs were estimated using logistic regression analysis after adjustment for relevant covariates.

Increased suicidal severity and fatal/non-fatal suicide attempt during the 12-month pharmacotherapy were present in 155 (17.5%) and 38 (4.3%) participants, respectively. Combined cortisol, total cholesterol, and folate serum biomarkers predicted fatal/non-fatal suicide attempt, and these with interleukin-1 beta and homocysteine additionally predicted increased suicidal severity, with clear gradients robust to adjustment (p values < 0.001).

Application of multiple serum biomarkers could considerably improve the predictability of SBs during the outpatient treatment of depressive disorders, potentially highlighting the need for more frequent monitoring and risk appraisal.