Machine learning identifies different related factors associated with depression and suicidal ideation in Chinese children and adolescents

BACKGROUND

Depression and suicidal ideation often co-occur in children and adolescents, yet they possess distinct characteristics. This study sought to identify the different related factors associated with depression and suicidal ideation.

METHODS

A nationwide cross-sectional survey collected data from Chinese children and adolescents aged 8 to 18 (N = 160,962; 48.91 % girls). The survey included inquiries about demographics, depression, suicidal ideation, anxiety, perceived stress, academic burnout, internet addiction, non-suicidal self-injury, bullying, and being bullied. Fifteen machine learning algorithms were conducted to identify the different related factors associated with depression and suicidal ideation. Additionally, we conducted external validation on an independent sample of 1,812,889 children and adolescents.

RESULTS

Our findings revealed seven related factors linked to depression and six associated with suicidal ideation, with average accuracy rates of 86.86 % and 85.82 %, respectively. For depression, the most influential factors were anxiety, perceived stress, academic burnout, internet addiction, non-suicidal self-injury, experience of bullying, and age. Similarly, anxiety, non-suicidal self-injury, perceived stress, internet addiction, academic burnout, and age emerged as paramount factors for suicidal ideation. Moreover, these related factors showed notable variations in their predictive capacities for depression and suicidal ideation across different subgroups.

CONCLUSION

Anxiety emerged as the predominant shared factor for both depression and suicidal ideation, whereas the other related factors displayed distinct predictive patterns for each condition. These findings highlight the critical need for tailored strategies from public mental health service providers and policymakers to address the pressing concerns of depression and suicidal ideation.

Difference and Analysis of Evaluating Psychological Monitors' Interview and Classmates' Being Interviewed About Suicide

In recent years, suicide has become the leading cause of unnatural death among college students in China. Psychological monitors, as class cadres who manage affairs related to mental health within their classes, are critical in identifying and intervening in psychological crises among their classmates. In China, however, talking about death is a cultural taboo, and many mental health workers have expressed concern about their implementation of interviews about suicide with others. Generally speaking, interviews with suicidal classmates are usually conducted by professional psychological experts and psychological monitors (psychological monitors are non-professional peer counselors in China). Such classmates that have undergone both the aforementioned types of interviews were investigated in this paper. However, this paper focuses on two issues. Firstly, what are the perceptions of classmates who have been interviewed toward the experience of being interviewed by psychological monitors? Secondly, what are the psychological monitors' perceptions of their implementation of interviews about suicide with classmates? In this study, 1,664 classmates who had been interviewed and 1,320 psychological monitors were surveyed by means of an online questionnaire. The results showed that classmates who have been interviewed perceived their experience of being interviewed by a psychological monitor about suicide more positively than the psychological monitors who viewed their implementation of interviews about suicide with classmates. Among the classmates who have been interviewed, three categories of classmates have more positive perceptions of their experience of being interviewed by a psychological monitor about suicide. Category one is males. Category two is those who were willing to seek help from the psychological monitors. Category three is those who had a more correct attitude toward mental illness. Among the psychological monitors, three categories of psychological monitors have more positive perceptions of their implementation of interviews about suicide with classmates. Category one is those who have the experience of implementing interviews with their classmates. Category two is those who have received training. Category three is those who had a more correct attitude toward mental illness. Psychological monitors can interview classmates confidently, and the training of psychological monitors on mental health knowledge should be strengthened in universities.

Nonsuicidal self-injury behaviour in a city of China and its association with family environment, media use and psychopathology

INTRODUCTION

It is not clear whether there are differences in the risk factors for nonsuicidal self-injury (NSSI) between children and early adolescents. Clarifying this question is crucial for identifying actionable prevention strategies for NSSI in these two age groups.

METHOD

The study, comprising 8611 children and early adolescents (4409 (51.2%) children, 4202 (48.8%) early adolescents), was based on the baseline data of the Chengdu Positive Child Development (CPCD) in China. NSSI behaviours, emotional and behavioural problems and family environment were assessed and obtained via self-reports and parent reports.

RESULTS

Overall, 2520 (29.26%) participants reported having ever engaged in NSSI. There was a higher lifetime NSSI rate in males than in females during childhood, contrasting with higher NSSI rates in females than in males during early adolescence. Furthermore, NSSI shared similar risk factors, including major family conflict and poor relationships with caregivers, in both age groups. Specifically, in children, the risk of NSSI increased along with thought and attention problems (OR, 95% CI: 1.194, 1.106-1.288 and 1.114, 1.028-1.207, respectively), whereas in early adolescents, it increased with anxiety and depressive problems (OR, 95% CI: 1.259, 1.116-1.422).

CONCLUSIONS

The findings suggested the need for difference in preventive strategies for NSSI in the two age groups. It may be more efficacious to screen for NSSI in children with thought and attention problems and in early adolescents with anxiety and depressive problems.

What's the harm in asking? A systematic review and meta-analysis on the risks of asking about suicide-related behaviors and self-harm with quality appraisal

Research emphasizes the importance of asking about suicidality. Unfortunately, misperceptions of harm remain which can compromise clinical care, research, and public health surveillance efforts. Our objective was to evaluate the empirical evidence on whether and how asking about suicide related behaviors (SRB), such as suicidal ideation and suicide attempts, and non-suicidal self-injury (NSSI) results in harmful outcomes. We reviewed and rated seventeen studies and conducted a systematic review and random-effects meta-analysis on eight studies comparing those asked vs. not asked on immediate and later SRB, NSSI, and psychological distress (PD). Forest plots demonstrated no statistically significant effects of asking on SRB, NSSI, or PD. Eight RCTs provided the strongest evidence and demonstrated either low or unclear risk of bias, and the remaining cohort studies were of low to moderate quality. With the current available evidence, we found no harmful outcomes of asking, however more RCTs with a low risk of bias are required to firmly conclude that asking through self-report and interview methods does not further exacerbate distress, SRB and NSSI compared to those not asked.

Associations between self-injury and involvement in cyberbullying among mentally distressed adolescents in Scania, Sweden

AIMS

To investigate associations between self-injury and involvement in cyberbullying as a bully, victim or bully-victim among mentally distressed adolescents.

METHODS

Data from the public health survey of children and adolescents in Scania, Sweden 2016 were used. A questionnaire was answered anonymously in school by 9143 students in 9th grade compulsory school (response rate 77%) and 7949 students in 2nd grade of upper secondary school (response rate 73%). Students with past year (broadly defined) mental distress at least 2 weeks in a row (33% of boys and 63% of girls) were asked if they had performed self-injury (i.e. cut, superficially cut or otherwise injured themselves) past year, and those with data on self-injury and cyberbullying were included in the present study ( n=6841). Associations between self-injury and cyberbullying were investigated by multiadjusted logistic regression analysis.

RESULTS

Among mentally distressed students, self-injury was reported by 11.7% of boys and 25.9% of girls. Age-adjusted analysis showed increasingly higher odds of self-injury among cyberbullies, cybervictims and cyberbully-victims, using non-involved as reference group (OR boys: 1.8, 2.3, 3.0; girls: 2.1, 3.2, 4.8). Associations weakened after adjustment for several potential confounders but remained significant for all cyberbullying groups except male cyberbullies, among whom significance was lost after adjustment for smoking, alcohol and narcotics.

CONCLUSIONS

Peer victimization in cyber space is associated with self-injury, especially among victims and bully-victims. Decreasing peer victimization is a priority, and school and health professionals need to be aware of the associations between cyberbullying and self-injury among mentally distressed adolescents.

Using Data Linkage to Investigate Inconsistent Reporting of Self-Harm and Questionnaire Non-Response

The objective of this study was to examine agreement between self-reported and medically recorded self-harm, and investigate whether the prevalence of self-harm differs in questionnaire responders vs. non-responders. A total of 4,810 participants from the Avon Longitudinal Study of Parents and Children (ALSPAC) completed a self-harm questionnaire at age 16 years. Data from consenting participants were linked to medical records (number available for analyses ranges from 205-3,027). The prevalence of self-harm leading to hospital admission was somewhat higher in questionnaire non-responders than responders (2.0 vs. 1.2%). Hospital attendance with self-harm was under-reported on the questionnaire. One third reported self-harm inconsistently over time; inconsistent reporters were less likely to have depression and fewer had self-harmed with suicidal intent. Self-harm prevalence estimates derived from self-report may be underestimated; more accurate figures may come from combining data from multiple sources.

Interventions for self-harm in children and adolescents

BACKGROUND

Self-harm (SH; intentional self-poisoning or self-injury) is common in children and adolescents, often repeated, and strongly associated with suicide. This is an update of a broader Cochrane review on psychosocial and pharmacological treatments for deliberate SH first published in 1998 and previously updated in 1999. We have now divided the review into three separate reviews; this review is focused on psychosocial and pharmacological interventions for SH in children and adolescents.

OBJECTIVES

To identify all randomised controlled trials of psychosocial interventions, pharmacological agents, or natural products for SH in children and adolescents, and to conduct meta-analyses (where possible) to compare the effects of specific treatments with comparison types of treatment (e.g., treatment as usual (TAU), placebo, or alternative pharmacological treatment) for children and adolescents who SH.

SEARCH METHODS

For this update the Cochrane Depression, Anxiety and Neurosis Group (CCDAN) Trials Search Co-ordinator searched the CCDAN Specialised Register (30 January 2015).

SELECTION CRITERIA

We included randomised controlled trials comparing psychosocial or pharmacological treatments with treatment as usual, alternative treatments, or placebo or alternative pharmacological treatment in children and adolescents (up to 18 years of age) with a recent (within six months) episode of SH resulting in presentation to clinical services.

DATA COLLECTION AND ANALYSIS

Two reviewers independently selected trials, extracted data, and appraised study quality, with consensus. For binary outcomes, we calculated odds ratios (OR) and their 95% confidence intervals (CI). For continuous outcomes measured using the same scale we calculated the mean difference (MD) and 95% CI; for those measured using different scales we calculated the standard mean difference (SMD) and 95% CI. Meta-analysis was only possible for two interventions: dialectical behaviour therapy for adolescents and group-based psychotherapy. For these analyses, we pooled data using a random-effects model.

MAIN RESULTS

We included 11 trials, with a total of 1,126 participants. The majority of participants were female (mean = 80.6% in 10 trials reporting gender). All trials were of psychosocial interventions; there were none of pharmacological treatments. With the exception of dialectical behaviour therapy for adolescents (DBT-A) and group-based therapy, assessments of specific interventions were based on single trials. We downgraded the quality of evidence owing to risk of bias or imprecision for many outcomes.Therapeutic assessment appeared to increase adherence with subsequent treatment compared with TAU (i.e., standard assessment; n = 70; k = 1; OR = 5.12, 95% CI 1.70 to 15.39), but this had no apparent impact on repetition of SH at either 12 (n = 69; k = 1; OR 0.75, 95% CI 0.18 to 3.06; GRADE: low quality) or 24 months (n = 69; k = 1; OR = 0.69, 05% CI 0.23 to 2.14; GRADE: low quality evidence). These results are based on a single cluster randomised trial, which may overestimate the effectiveness of the intervention.For patients with multiple episodes of SH or emerging personality problems, mentalisation therapy was associated with fewer adolescents scoring above the cut-off for repetition of SH based on the Risk-Taking and Self-Harm Inventory 12 months post-intervention (n = 71; k = 1; OR = 0.26, 95% CI 0.09 to 0.78; GRADE: moderate quality). DBT-A was not associated with a reduction in the proportion of adolescents repeating SH when compared to either TAU or enhanced usual care (n = 104; k = 2; OR 0.72, 95% CI 0.12 to 4.40; GRADE: low quality). In the latter trial, however, the authors reported a significantly greater reduction over time in frequency of repeated SH in adolescents in the DBT condition, in whom there were also significantly greater reductions in depression, hopelessness, and suicidal ideation.We found no significant treatment effects for group-based therapy on repetition of SH for individuals with multiple episodes of SH at either the six (n = 430; k = 2; OR 1.72, 95% CI 0.56 to 5.24; GRADE: low quality) or 12 month (n = 490; k = 3; OR 0.80, 95% CI 0.22 to 2.97; GRADE: low quality) assessments, although considerable heterogeneity was associated with both (I(2) = 65% and 77% respectively). We also found no significant differences between the following treatments and TAU in terms of reduced repetition of SH: compliance enhancement (three month follow-up assessment: n = 63; k = 1; OR = 0.67, 95% CI 0.15 to 3.08; GRADE: very low quality), CBT-based psychotherapy (six month follow-up assessment: n = 39; k = 1; OR = 1.88, 95% CI 0.30 to 11.73; GRADE: very low quality), home-based family intervention (six month follow-up assessment: n = 149; k = 1; OR = 1.02, 95% CI 0.41 to 2.51; GRADE: low quality), and provision of an emergency card (12 month follow-up assessment: n = 105, k = 1; OR = 0.50, 95% CI 0.12 to 2.04; GRADE: very low quality). No data on adverse effects, other than the planned outcomes relating to suicidal behaviour, were reported.

AUTHORS' CONCLUSIONS

There are relatively few trials of interventions for children and adolescents who have engaged in SH, and only single trials contributed to all but two comparisons in this review. The quality of evidence according to GRADE criteria was mostly very low. There is little support for the effectiveness of group-based psychotherapy for adolescents with multiple episodes of SH based on the results of three trials, the evidence from which was of very low quality according to GRADE criteria. Results for therapeutic assessment, mentalisation, and dialectical behaviour therapy indicated that these approaches warrant further evaluation. Despite the scale of the problem of SH in children and adolescents there is a paucity of evidence of effective interventions. Further large-scale trials, with a range of outcome measures including adverse events, and investigation of therapeutic mechanisms underpinning these interventions, are required. It is increasingly apparent that development of new interventions should be done in collaboration with patients to ensure that these are likely to meet their needs. Use of an agreed set of outcome measures would assist evaluation and both comparison and meta-analysis of trials.