Machine Learning Assessment of Early Life Factors Predicting Suicide Attempt in Adolescence or Young Adulthood

Neural activity during inhibitory control predicts suicidal ideation with machine learning

Suicide is a leading cause of death in the US and worldwide. Current strategies for preventing suicide are often focused on the identification and treatment of risk factors, especially suicidal ideation (SI). Hence, developing data-driven biomarkers of SI may be key for suicide prevention and intervention. Prior attempts at biomarker-based prediction models for SI have primarily used expensive neuroimaging technologies, yet clinically scalable and affordable biomarkers remain elusive. Here, we investigated the classification of SI using machine learning (ML) on a dataset of 76 subjects with and without SI(+/-) (n = 38 each), who completed a neuro-cognitive assessment session synchronized with electroencephalography (EEG). SI+/- groups were matched for age, sex, and mental health symptoms of depression and anxiety. EEG was recorded at rest and while subjects engaged in four cognitive tasks of inhibitory control, interference processing, working memory, and emotion bias. We parsed EEG signals in physiologically relevant theta (4-8 Hz), alpha (8-13 Hz), and beta (13-30 Hz) frequencies and performed cortical source imaging on the neural signals. These data served as SI predictors in ML models. The best ML model was obtained for beta band power during the inhibitory control (IC) task, demonstrating high sensitivity (89%), specificity (98%). Shapley explainer plots further showed top neural predictors as feedback-related power in the visual and posterior default mode networks and response-related power in the ventral attention, fronto-parietal, and sensory-motor networks. We further tested the external validity of the model in an independent clinically depressed sample (n = 35, 12 SI+) that engaged in an adaptive test version of the IC task, demonstrating 50% sensitivity and 61% specificity in this sample. Overall, the study suggests a promising, scalable EEG-based biomarker approach to predict SI that may serve as a target for risk identification and intervention.

Suicide attempts and non-suicidal self-injury in Chinese adolescents: Predictive models using a neural network model

INTRODUCTION

Suicide attempts (SA) are a significant contributor to suicide deaths, and non-suicidal self-injury (NSSI) can increase the risk of SA. Many adolescents experience both NSSI and SA, which are affected by various factors. This study aimed to identify the risk factors and essential warning signs of SA, establish a predictive model for SA using multiple dimensions and large samples, and provide a multidimensional perspective for clinical diagnosis and intervention.

METHODS

A total of 9140 participants aged 12-18 years participated in an online survey; 6959 participants were included in the statistical analysis. A multilayer perceptron algorithm was used to establish a prediction model for adolescent SA (with or without); adolescents with NSSI behavior were extracted as a subgroup to establish a prediction model.

RESULTS

Both the prediction model performance of the SA group and the NSSI-SA subgroup were strong, with high accuracy, and AUC values of 0.93 and 0.88, indicating good discrimination. Decision curve analysis (DCA) demonstrated that the clinical intervention value of the prediction results was high and that the clinical intervention benefits of the NSSI-SA subgroup were greater than those of the SA group.

CONCLUSIONS

Our study demonstrated that the predictive model has a high degree of accuracy and discrimination, thereby identifying significant factors associated with adolescent SA. As long as adolescents exhibit NSSI behavior, relative suicide interventions should be implemented to prevent future hazards. This study can provide guidance and more nuanced insights for clinical diagnosis as well as a foundation for clinical treatment.

Predicting inmate suicidal behavior with an interpretable ensemble machine learning approach in smart prisons

The convergence of smart technologies and predictive modelling in prisons presents an exciting opportunity to revolutionize the monitoring of inmate behaviour, allowing for the early detection of signs of distress and the effective mitigation of suicide risks. While machine learning algorithms have been extensively employed in predicting suicidal behaviour, a critical aspect that has often been overlooked is the interoperability of these models. Most of the work done on model interpretations for suicide predictions often limits itself to feature reduction and highlighting important contributing features only. To address this research gap, we used Anchor explanations for creating human-readable statements based on simple rules, which, to our knowledge, have never been used before for suicide prediction models. We also overcome the limitation of anchor explanations, which create weak rules on high-dimensionality datasets, by first reducing data features with the help of SHapley Additive exPlanations (SHAP). We further reduce data features through anchor interpretations for the final ensemble model of XGBoost and random forest. Our results indicate significant improvement when compared with state-of-the-art models, having an accuracy and precision of 98.6% and 98.9%, respectively. The F1-score for the best suicide ideation model appeared to be 96.7%.

Psychological pain and sociodemographic factors classified suicide attempt and non-suicidal self-injury in adolescents

This study aimed to utilize machine learning to explore the psychological similarities and differences between suicide attempt (SA) and non-suicidal self-injury (NSSI), with a particular focus on the role of psychological pain. A total of 2385 middle school students were recruited using cluster sampling. The random forest algorithm was used with 25 predictors to develop classification models of SA and NSSI, respectively, and to estimate the importance scores of each predictor. Based on these scores and related theories, shared risk factors (control feature set) and distinct risk factors (distinction feature set) were selected and tested to distinguish between NSSI and SA. The machine learning algorithm exhibited fair to good performance in classifying SA history [Area Under Curves (AUCs): 0.65-0.87] and poor performance in classifying NSSI history (AUC: 0.61-0.68). The distinction feature set comprised pain avoidance, family togetherness, and deviant peer affiliation, while the control feature set included pain arousal, painful feelings, and crisis events. The distinction feature set slightly but stably outperformed the control feature set in classifying SA from NSSI. The three-dimensional psychological pain model, especially pain avoidance, might play a dominant role in understanding the similarities and differences between SA and NSSI.

Role of machine learning algorithms in suicide risk prediction: a systematic review-meta analysis of clinical studies

OBJECTIVE

Suicide is a complex and multifactorial public health problem. Understanding and addressing the various factors associated with suicide is crucial for prevention and intervention efforts. Machine learning (ML) could enhance the prediction of suicide attempts.

METHOD

A systematic review was performed using PubMed, Scopus, Web of Science and SID databases. We aim to evaluate the performance of ML algorithms and summarize their effects, gather relevant and reliable information to synthesize existing evidence, identify knowledge gaps, and provide a comprehensive list of the suicide risk factors using mixed method approach.

RESULTS

Forty-one studies published between 2011 and 2022, which matched inclusion criteria, were chosen as suitable. We included studies aimed at predicting the suicide risk by machine learning algorithms except natural language processing (NLP) and image processing. The neural network (NN) algorithm exhibited the lowest accuracy at 0.70, whereas the random forest demonstrated the highest accuracy, reaching 0.94. The study assessed the COX and random forest models and observed a minimum area under the curve (AUC) value of 0.54. In contrast, the XGBoost classifier yielded the highest AUC value, reaching 0.97. These specific AUC values emphasize the algorithm-specific performance in capturing the trade-off between sensitivity and specificity for suicide risk prediction. Furthermore, our investigation identified several common suicide risk factors, including age, gender, substance abuse, depression, anxiety, alcohol consumption, marital status, income, education, and occupation. This comprehensive analysis contributes valuable insights into the multifaceted nature of suicide risk, providing a foundation for targeted preventive strategies and intervention efforts.

CONCLUSIONS

The effectiveness of ML algorithms and their application in predicting suicide risk has been controversial. There is a need for more studies on these algorithms in clinical settings, and the related ethical concerns require further clarification.

Question-based computational language approach outperforms rating scales in quantifying emotional states

Psychological constructs are commonly quantified with closed-ended rating scales. However, recent advancements in natural language processing (NLP) enable the quantification of open-ended language responses. Here we demonstrate that descriptive word responses analyzed using NLP show higher accuracy in categorizing emotional states compared to traditional rating scales. One group of participants (N = 297) generated narratives related to depression, anxiety, satisfaction, or harmony, summarized them with five descriptive words, and rated them using rating scales. Another group (N = 434) evaluated these narratives (with descriptive words and rating scales) from the author's perspective. The descriptive words were quantified using NLP, and machine learning was used to categorize the responses into the corresponding emotional states. The results showed a significantly higher number of accurate categorizations of the narratives based on descriptive words (64%) than on rating scales (44%), questioning the notion that rating scales are more precise in measuring emotional states than language-based measures.

Bridge symptoms between parenting styles and proximal psychological risk factors associated with adolescent suicidal thoughts: a network analysis

BACKGROUND

Parenting styles and the associated proximal psychological factors are suggested to increase suicidal risks in adolescents. However, how the two factors interact and confer risks on the emergence of adolescent suicidal thoughts remains unclear. Herein, we used a network approach to investigate their interrelationship and explore whether the network properties predict adolescent suicidal thoughts.

METHODS

Self-report questionnaires were completed by 1171 students aged 12-16. Network analyses were performed by Gaussian graphical models estimating the adolescent psychosocial network structure of parenting styles and psychological variables including depression, anxiety, affective lability, rumination, and resilience. Furthermore, we re-examined the network by adding a variable measuring active suicidal thoughts. Moreover, we conducted linear regressions to examine the predictive utility of bridge symptoms for adolescent suicidal thoughts.

RESULTS

Resilience, Afraid, Rumination, Concentration, and affective lability (Anger) had the highest bridge strengths in the adolescent psychosocial network. Among the identified bridge symptoms, Resilience was negatively correlated with active suicidal thoughts (regularized edge weights = -0.181, bootstrapped 95% CIs: [-0.043, -0.155]), whereas affective lability (from Anxiety to Depression, Anger), Rumination, and Afraid were positively correlated with active suicidal thoughts, with edge weights (bootstrapped 95% CIs) ranging from 0.057 (0.001, 0.112) to 0.081(0.026, 0.136). Regression analysis showed that bridge strength was significantly correlated with active suicidal thoughts (R2 = 0.432, P = 0.001).

CONCLUSION

Negative parenting styles may drive and maintain suicidal thoughts by modifying the key proximal psychological variables. Our findings highlight the important role of bridge symptoms, which may serve as vital targets for triggering adolescent suicide.

Predicting internalizing symptoms with machine learning: identifying individuals that need care

Objective The current project aims to identify individuals in urgent need of mental health care, using a machine learning algorithm (random forest). Comparison/contrast with conventional regression analyses is discussed. Participants: A total of 2,409 participants were recruited from an anonymous university, including undergraduate and graduate students, faculty, and staff. Methods: Answers to a COVID-19 impact survey, the Patient Health Questionnaire-9 (PHQ-9), and the Generalized Anxiety Disorder-7 (GAD-7) were collected. The total scores of PHQ-9 and GAD-7 were regressed on six composites that were created from the questionnaire items, based on their topics. A random forest was trained and validated. Results: Results indicate that the random forest model was able to make accurate, prospective predictions (R2 = .429 on average) and we review variables that were deemed predictively relevant. Conclusions: Overall, the study suggests that predictive models can be clinically useful in identifying individuals with internalizing symptoms based on daily life disruption experiences.

Machine learning-based prediction for self-harm and suicide attempts in adolescents

This study aimed to use machine learning (ML) models to predict the risk of self-harm and suicide attempts in adolescents. We conducted secondary analysis of cross-sectional data from the Longitudinal Study of Australian Children dataset. Several key variables at the age of 14-15 years were used to predict self-harm or suicide attempt at 16-17 years. Random forest classification models were used to select the optimal subset of predictors and subsequently make predictions. Among 2809 participants, 296 (10.54%) reported an act of self-harm and 145 (5.16%) reported attempting suicide at least once in the past 12 months. The area under the receiver operating curve was fair for self-harm (0.7397) and suicide attempt (0.7220), which outperformed the prediction strategy solely based on prior suicide or self-harm attempt (AUC: 0.6). The most important factors identified were similar, and included depressed feelings, strengths and difficulties questionnaire scores, perceptions of self, and school- and parent-related factors. The random forest classification algorithm, an ML technique, can effectively select the optimal subset of predictors from hundreds of variables to forecast the risks of suicide and self-harm among adolescents. Further research is needed to validate the utility and scalability of ML techniques in mental health research.

Understanding suicidality in Pacific adolescents in New Zealand using network analysis

INTRODUCTION

Pacific adolescents in New Zealand (NZ) are three to four times more likely than NZ European adolescents to report suicide attempts and have higher rates of suicidal plans. Suicidal thoughts, plans, and attempts, termed suicidality in this study, result from a complex dynamic interplay of factors, which emerging methodologies like network analysis aim to capture.

METHODS

This study used cross-sectional network analysis to model the relationships between suicidality, self-harm, and individual depression symptoms, whilst conditioning on a multi-dimensional set of variables relevant to suicidality. A series of network models were fitted to data from a community sample of New Zealand-born Pacific adolescents (n = 550; 51% male; Mean age (SD) = 17 (0.35)).

RESULTS

Self-harm and the depression symptom measuring pessimism had the strongest associations with suicidality, followed by symptoms related to having a negative self-image about looks and sadness. Nonsymptom risk factors for self-harm and suicidality differed markedly.

CONCLUSIONS

Depression symptoms varied widely in terms of their contribution to suicidality, highlighting the valuable information gained from analysing depression at the symptom-item level. Reducing the sources of pessimism and building self-esteem presented as potential targets for alleviating suicidality amongst Pacific adolescents in New Zealand. Suicide prevention strategies need to include risk factors for self-harm.

Statistical and artificial intelligence techniques to identify risk factors for suicide in children and adolescents

BACKGROUND

Suicidal Behaviors and Thoughts are a relevant public health issue that includes suicidal ideation, non-suicidal self-harm, attempted suicide, and failed suicides. Since there is a progression of suicidal behaviors, whereby suicide is more likely to be completed if there have already been previous behaviors or attempts to harm oneself, WHO has highlighted the need to detect early predictors of such suicidal behaviors, which can help identify individuals at risk, plan prevention strategies and implement specific therapeutic interventions, particularly in young people, thus reducing the number of deaths. This retrospective observational study aimed to identify early predictors of suicidal risk in 237 inpatients admitted for Suicidal Behaviors and Thoughts at Child and Adolescent Psychiatry Emergency Unit of the Meyer Children's Hospital, Florence, Italy.

METHODS

The study was subdivided into three phases: data collection, statistical analysis, and neural network. For each patient, we collected epidemiological and psychopathological data. We stratified the inpatients into two groups: "suicidal volition patients" and "suicidal motivation patients."

RESULTS

The hospitalization rate for suicidal behaviors and thoughts showed a growing trend from 2016 to 2020 (27.69 to 45.28%). Under 12 years of age, diagnosis of disruptive, impulse-control and conduct disorder, previous specialist care, history of attempted suicide, and intoxication as methods of suicide were statistically correlated to an increased risk of suicidal behaviors. Artificial intelligence, with an accuracy of 86.7%, confirmed these risk factors.

LIMITATIONS

The most important limitation of the study is its retrospective nature.

CONCLUSIONS

Our study identifies new early predictors of suicidal risk: age less than 12, diagnosis of disruptive, impulse-control and conduct disorder. In addition, suicidal volition behavior emerges as an important and underestimated risk factor. The use of artificial intelligence methods could be supporting the clinician in assessing suicidal risk.

Suicide risk detection using artificial intelligence: the promise of creating a benchmark dataset for research on the detection of suicide risk

Suicide is a leading cause of death that demands cross-disciplinary research efforts to develop and deploy suicide risk screening tools. Such tools, partly informed by influential suicide theories, can help identify individuals at the greatest risk of suicide and should be able to predict the transition from suicidal thoughts to suicide attempts. Advances in artificial intelligence have revolutionized the development of suicide screening tools and suicide risk detection systems. Thus, various types of AI systems, including text-based systems, have been proposed to identify individuals at risk of suicide. Although these systems have shown acceptable performance, most of them have not incorporated suicide theories in their design. Furthermore, directly applying suicide theories may be difficult because of the diversity and complexity of these theories. To address these challenges, we propose an approach to develop speech- and language-based suicide risk detection systems. We highlight the promise of establishing a benchmark textual and vocal dataset using a standardized speech and language assessment procedure, and research designs that distinguish between the risk factors for suicide attempt above and beyond those for suicidal ideation alone. The benchmark dataset could be used to develop trustworthy machine learning or deep learning-based suicide risk detection systems, ultimately constructing a foundation for vocal and textual-based suicide risk detection systems.

Psychosocial and neurocognitive correlates of suicidal thoughts and behaviours amongst siblings of persons with and without neurodevelopmental conditions

OBJECTIVE

Siblings of individuals with neurodevelopmental conditions (NDCs) have greater incidence of neuropsychiatric diagnoses and neurocognitive difficulties compared to siblings of persons without NDCs. Despite suicidality being labelled a global health crisis (WHO, 2014) and NDC siblings experiencing risk factors implicated in suicidality, no previous studies examined suicidality amongst adolescent and young adult siblings of persons with NDCs. Our study aimed to bridge this gap.

METHOD

The present study used Bayesian analyses and risk classification models to examine individual and environmental risk factors associated with suicidal thoughts and behaviours amongst siblings of persons with and without NDCs (n = 267; 132 NDC, 135 control group, mean age 20.61, range 14-27, 76.40% female, 76.78% White Caucasian), as measured using self-report survey data and remote self-administered cognitive tests.

RESULTS

NDC siblings had higher rates of current nonsuicidal self-injury (NSSI; 18.94% versus 14.07%, δ = -0.32), suicidal ideation (25.76% versus 8.89%, δ = -0.40) and history of suicide attempts (18.18% versus 4.44%, δ = -0.43) compared to controls. Classification models using boosting and random forest demonstrated adequate performance: positive predictive value 0.86-0.91, negative predictive value 0.81-0.90, false negative rates 0.11-0.24. Cognitive inflexibility, alexithymia, inattention, bullying, depression, NSSI, and eating or psychotic disorder history had the highest relative importance in predicting lifetime suicidality. Poorer executive functioning (measured by the Wisconsin Card Sorting Task, Sustained Attention to Response Task, Stop Signal Task, and N-Back 2-back task) was strongly correlated with suicidality.

CONCLUSIONS

Screening for proximal and modifiable risk factors is critical to inform suicidal behaviour intervention and prevention programs for at-risk siblings.

The Influence of Insecure Attachment to Parents on Adolescents' Suicidality

Insecure attachment has been identified as a risk factor for adolescent psychopathology and, consequently, for suicidal behavior. We aimed to highlight the relationship between the attachment styles of adolescents and their suicidal behavior and to investigate the role of each parent in the suicidality pathway of adolescents. The sample consisted of 217 adolescent inpatients who were at the highest risk for suicidal behavior and who were hospitalized in the Unit for Intensive Child and Adolescent Psychiatry. Self-report questionnaires assessing their attachment to their parents, their acquired capability for attempting suicide, their suicidality, and a number of traumatic life events were administered. The results showed a higher level of attachment avoidance rather than attachment anxiety among the most at-risk adolescents. An acquired capability for suicide (ACS) mediated the positive correlation between adolescents' attachment avoidance in relation to the mother or father and their suicidality. The suppressive mediating effect of an ACS on the association between attachment anxiety in relation to the father and suicidality was detected. The odds ratio for attempted suicide was more than two times higher for adolescents who were insecurely attached to their father compared to adolescents who were insecurely attached to their mother. Our results confirmed the importance of attachment, especially paternal attachment, in developing suicidality during adolescence. Preventive and clinical interventions should target these important domains with the aim of decreasing suicidality among adolescents.

Identifying the suicidal ideation risk group among older adults in rural areas: Developing a predictive model using machine learning methods

AIMS

The aim of this study was to develop a predictive model that can identify the suicidal ideation risk group among older adults in rural areas using machine learning methods.

DESIGN

This study applied an exploratory, descriptive and cross-sectional design.

METHODS

The participants were older adults (N = 650) aged over 65 living in rural areas of South Korea. Self-report questionnaires were used to collect the demographics, suicidal ideation, depression, socioeconomic information and basic health information from September to October 2020. The collected data were analysed using machine learning methods with R statistical software 4.1.0.

RESULTS

The predictive models indicated that depression, pain, age and loneliness were significant factors of suicidal ideation. Good performance was observed based on the area under the receiver operating characteristic curve in the decision tree, random forest and logistic regression. Finally, the evaluation of model performance indicated moderate to high sensitivity and specificity.

CONCLUSION

The predictive models using machine learning methods may be useful to predict the risk of suicidal ideation. Furthermore, depression with pain, age and feelings of loneliness should be included in the initial screening to assess suicide risk among older adults in rural areas.

IMPACT

Identifying suicidal risk among older adults is challenging. Thus, employing predictive models that can assess depression, pain, age and loneliness can enable public healthcare providers to detect suicidal risk groups. Particularly, the presented models from this study can facilitate healthcare providers with initiating early interventions to prevent suicide among older adults in clinical and community nursing care settings.

REPORTING METHOD

The reporting of this study (Observational, cross-sectional study) conforms to the STROBE statement.

PATIENT OR PUBLIC CONTRIBUTION

No patient or public contribution. This study did not involve patients, service users, caregivers or members of the public.

IMPLICATION FOR THE PROFESSION AND/OR PATIENTS CARE

Applying this model may help to prevent geriatric suicide because the nursing staff will have a greater awareness regarding the suicide ideation risk of older adults, thereby reducing the possibility of their suicide.

An explainable predictive model for suicide attempt risk using an ensemble learning and Shapley Additive Explanations (SHAP) approach

Machine learning approaches have been used to develop suicide attempt predictive models recently and have been shown to have a good performance. However, those proposed models have difficulty interpreting and understanding why an individual has suicidal attempts. To overcome this issue, the identification of features such as risk factors in predicting suicide attempts is important for clinicians to make decisions. Therefore, the aim of this study is to propose an explainable predictive model to predict and analyse the importance of features for suicide attempts. This model can also provide explanations to improve the clinical understanding of suicide attempts. Two complex ensemble learning models, namely Random Forest and Gradient Boosting with an explanatory model (SHapley Additive exPlanations (SHAP)) have been constructed. The models are used for predictive interpretation and understanding of the importance of the features. The experiment shows that both models with SHAP are able to interpret and understand the nature of an individual's predictions with suicide attempts. However, compared with Random Forest, the results show that Gradient Boosting with SHAP achieves higher accuracy and the analyses found that history of suicide attempts, suicidal ideation, and ethnicity as the main predictors for suicide attempts.

Cognitive Flexibility and Impulsivity Deficits in Suicidal Adolescents

Although neurocognitive deficits have been documented in adolescents with suicidal ideation (SI) and suicide attempts (SA), it is unclear whether certain impairments differentiate these groups, potentially suggesting heightened risk for SA. Focus on specific facets of impulsivity and cognitive control may indicate distinctions between adolescents with SA vs. SI. The current study examined dimensions of impulsivity and cognitive control in 141 adolescents with SA (n = 41) vs. SI without SA (n = 49) vs. typically-developing controls (TDCs; n = 51). Adolescents completed cross-sectional neurocognitive tasks via the Cambridge Neuropsychological Testing Automated Battery, in addition to demographic and clinical measures. Analyses involved ANOVAs and ANCOVAs. Results indicated that adolescents with SA demonstrated less set shifting/cognitive flexibility (reduced ability to adapt to/disengage from stimuli) and greater impulsive decision making (reduced ability to collect/evaluate information before making decisions) compared to TDCs. In addition, both TDCs and adolescents with SA had greater response inhibition (increased ability to stop motor responses that have begun/become prepotent) than those with SI. Similar results were found when analyzing female adolescents separately. There were no significant differences for male adolescents, potentially due to the small subsample (n = 40). There were no significant findings for spatial planning/problem solving or visuospatial working memory. Findings suggest: 1) less set shifting/cognitive flexibility and greater impulsive decision making for adolescents with SA vs. TDCs; and 2) greater response inhibition for TDCs and adolescents with SA vs. SI. Such information may be useful for improving risk assessments (adding neurocognitive tasks) and targeted treatments (incorporating cognitive remediation) for this impaired population.

Prediction of suicidal ideation among Chinese college students based on radial basis function neural network

Background

Suicide is one of the leading causes of death for college students. The predictors of suicidal ideation among college students are inconsistent and few studies have systematically investigated psychological symptoms of college students to predict suicide. Therefore, this study aims to develop a suicidal ideation prediction model and explore important predictors of suicidal ideation among college students in China.

Methods

We recruited 1,500 college students of Sichuan University and followed up for 4 years. Demographic information, behavioral and psychological information of the participants were collected using computer-based questionnaires. The Radial Basis Function Neural Network (RBFNN) method was used to develop three suicidal ideation risk prediction models and to identify important predictive factors for suicidal ideation among college students.

Results

The incidence of suicidal ideation among college students in the last 12 months ranged from 3.00 to 4.07%. The prediction accuracies of all the three models were over 91.7%. The area under curve scores were up to 0.96. Previous suicidal ideation and poor subjective sleep quality were the most robust predictors. Poor self-rated mental health has also been identified to be an important predictor. Paranoid symptom, internet addiction, poor self-rated physical health, poor self-rated overall health, emotional abuse, low average annual household income per person and heavy study pressure were potential predictors for suicidal ideation.

Conclusions

The study suggested that the RBFNN method was accurate in predicting suicidal ideation. And students who have ever had previous suicidal ideation and poor sleep quality should be paid consistent attention to.

The effect of social network strain on suicidal ideation among middle-aged adults with adverse childhood experiences in the US: A twelve-year nationwide study

Objective

Building on literature that measured the association between social network strain (SNS) and suicidal ideation using conventional regression analyses, we examined the effect of SNS, due to adverse childhood experiences (ACEs), on suicidal ideation using instrumental variables (IV) to eliminate the potential biases that may have occurred in earlier studies due to residual confounding.

Methods

This retrospective cohort study linked longitudinal data from the National Survey of Midlife Development in the United States (MIDUS) Refresher Biomarker Project (2012–2016), the MIDUS Refresher Project (2011–2014), the MIDUS 2 Biomarker Project (2004–2009), and the MIDUS 2 Project (2004–2006). Participants completed a phone interview, self-administered survey, and biomarker data collection. Exposure indicators included self-reported suicidal ideation, ACEs, and SNS from family, spouse, and friends. IV analysis was used to evaluate the continuous local average treatment effect of SNS on suicidal ideation when SNS only varied due to variation in ACEs.

Results

Our sample included 1703 middle-aged adults (52.9% females), which were followed up for 12 years. An IV probit model controlling for sociodemographic characteristics found a one-standard-deviation reduction in SNS reduced suicidal ideation by 22.6% (p < 0.01). A comprehensively controlled IV probit model found that a one-standard-deviation reduction in SNS is associated with a 21.4% (p = 0.05) decrease in suicidal ideation.

Conclusions

The causal pathway from SNS (due to ACEs) to suicidal ideation among middle-aged adults was established using IV analysis in this large-scale longitudinal study. The magnitude of this effect is sufficient to warrant the development of programs to improve social network relationships among family, friends, and spouses/partners. Suicide prevention programs addressing SNS may significantly reduce suicidal ideation among middle-aged Americans who have experienced ACEs.

•

Social Network Strain (SNS) from family, spouse, and friends is common.

•

SNS derives from demands, criticisms, disappointments, and irritations.

•

SNS varies strongly with Adverse Childhood Experiences (ACEs).

•

Reductions in SNS due to fewer ACEs decrease suicidal ideation.

•

A one standard-deviation reduction in SNS lowers suicidal ideation by 20%.

Emotional and attention-deficit/hyperactivity disorder symptoms of preterm vs. full-term children during COVID-19 pandemic restrictions

BACKGROUND

Preterm children are at higher risk of developing mental health problems than full-term children. Deterioration of children's mental health was observed during COVID-19 pandemic restrictive measures. Our study compared emotional and attention-deficit/hyperactivity disorder (ADHD) symptoms during school closure between preterm and full-term children.

METHODS

Data from two French birth cohorts-ELFE and EPIPAGE-2-were used. In 2011, infants born ≥22 weeks' gestation were recruited. Parents completed the Strengths and Difficulties Questionnaire when the children were 9 years old and experiencing school closure. Multivariate multinomial logistic regression models were used.

RESULTS

Subjects included 4164 full-term and 1119 preterm children. In univariate analyses, compared to full-term children: extremely and very preterm children more frequently had abnormal and borderline ADHD scores (odds ratio [OR] 1.86, 95% confidence interval [CI] 1.50-2.30, OR 1.42, 95% CI 1.08-1.85, respectively) and abnormal emotional scores (OR 1.86, 95% CI 1.43-2.40); moderate to late preterm children more often had abnormal ADHD scores (OR 1.33, 95% CI 1.01-1.78). The associations did not remain when previous symptoms at 5 years old were considered.

CONCLUSIONS

School closure during lockdown did not appear to increase the risk of mental health problems in preterm compared to full-term children.

IMPACT STATEMENT

Preterm children are at higher risk of developing mental health problems than full-term children. Deterioration in children's mental health was observed during COVID-19 pandemic restrictions. However, whether preterm children were a particularly vulnerable subgroup during school closure is unclear. In univariate analyses, extremely and very preterm children more often had abnormal and borderline ADHD symptoms and abnormal emotional symptom scores than full-term children. The associations did not remain significantly associated when previous symptoms were considered. Preterm compared to full-term children more often suffer from ADHD and emotional symptoms, but school closure during lockdown did not appear to increase this risk.

A machine-learning model to predict suicide risk in Japan based on national survey data

OBJECTIVE

Several prognostic models of suicide risk have been published; however, few have been implemented in Japan using longitudinal cohort data. The aim of this study was to identify suicide risk factors for suicidal ideation in the Japanese population and to develop a machine-learning model to predict suicide risk in Japan.

MATERIALS AND METHODS

Data was obtained from Wave1 Time 1 (November 2016) and Time 2 (March 2017) of the National Survey for Stress and Health in Japan, were incorporated into a suicide risk prediction machine-learning model, trained using 65 items related to trauma and stress. The study included 3,090 and 2,163 survey respondents >18 years old at Time 1 and Time 2, respectively. The mean (standard deviation, SD) age was 44.9 (10.9) years at Time 1 and 46.0 (10.7) years at Time 2. We analyzed the participants with increased suicide risk at Time 2 survey. Model performance, including the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity, were also analyzed.

RESULTS

The model showed a good performance (AUC = 0.830, 95% confidence interval = 0.795-0.866). Overall, the model achieved an accuracy of 78.8%, sensitivity of 75.4%, specificity of 80.4%, positive predictive value of 63.4%, and negative predictive value of 87.9%. The most important risk factor for suicide risk was the participants' Suicidal Ideation Attributes Scale score, followed by the Sheehan Disability Scale score, Patient Health Questionnaire-9 scores, Cross-Cutting Symptom Measure (CCSM-suicidal ideation domain, Dissociation Experience Scale score, history of self-harm, Generalized Anxiety Disorder-7 score, Post-Traumatic Stress Disorder check list-5 score, CCSM-dissociation domain, and Impact of Event Scale-Revised scores at Time 1.

CONCLUSIONS

This prognostic study suggests the ability to identify patients at a high risk of suicide using an online survey method. In addition to confirming several well-known risk factors of suicide, new risk measures related to trauma and trauma-related experiences were also identified, which may help guide future clinical assessments and early intervention approaches.

Prediction of recurrent suicidal behavior among suicide attempters with Cox regression and machine learning: a 10-year prospective cohort study

BACKGROUND

Research on predictors and risk of recurrence after suicide attempt from China is lacking. This study aims to identify risk factors and develop prediction models for recurrent suicidal behavior among suicide attempters using Cox proportional hazard (CPH) and machine learning methods.

METHODS

The prospective cohort study included 1103 suicide attempters with a maximum follow-up of 10 years from rural China. Baseline characteristics, collected by face-to-face interviews at least 1 month later after index suicide attempt, were used to predict recurrent suicidal behavior. CPH and 3 machine learning algorithms, namely, the least absolute shrinkage and selection operator, random survival forest, and gradient boosting decision tree, were used to construct prediction models. Model performance was accessed by concordance index (C-index) and the time-dependent area under the receiver operating characteristic curve (AUC) value for discrimination, and time-dependent calibration curve along with Brier score for calibration.

RESULTS

The median follow-up time was 7.79 years, and 49 suicide attempters had recurrent suicidal behavior during the study period. Four models achieved comparably good discrimination and calibration performance, with all C-indexes larger than 0.70, AUC values larger than 0.65, and Brier scores smaller than 0.06. Mental disorder emerged as the most important predictor across all four models. Suicide attempters with mental disorders had a 3 times higher risk of recurrence than those without. History of suicide attempt (HR = 2.84, 95% CI: 1.34-6.02), unstable marital status (HR = 2.81, 95% CI: 1.38-5.71), and older age (HR = 1.51, 95% CI: 1.14-2.01) were also identified as independent predictors of recurrent suicidal behavior by CPH model.

CONCLUSIONS

We developed four models to predict recurrent suicidal behavior with comparable good prediction performance. Our findings potentially provided benefits in screening vulnerable individuals on a more precise scale.

A machine learning approach for predicting suicidal thoughts and behaviours among college students

Suicidal thoughts and behaviours are prevalent among college students. Yet little is known about screening tools to identify students at higher risk. We aimed to develop a risk algorithm to identify the main predictors of suicidal thoughts and behaviours among college students within one-year of baseline assessment. We used data collected in 2013–2019 from the French i-Share cohort, a longitudinal population-based study including 5066 volunteer students. To predict suicidal thoughts and behaviours at follow-up, we used random forests models with 70 potential predictors measured at baseline, including sociodemographic and familial characteristics, mental health and substance use. Model performance was measured using the area under the receiver operating curve (AUC), sensitivity, and positive predictive value. At follow-up, 17.4% of girls and 16.8% of boys reported suicidal thoughts and behaviours. The models achieved good predictive performance: AUC, 0.8; sensitivity, 79% for girls, 81% for boys; and positive predictive value, 40% for girls and 36% for boys. Among the 70 potential predictors, four showed the highest predictive power: 12-month suicidal thoughts, trait anxiety, depression symptoms, and self-esteem. We identified a parsimonious set of mental health indicators that accurately predicted one-year suicidal thoughts and behaviours in a community sample of college students.