METHODS: Data came from a large sample of 11,412 Chinese undergraduate students. A bifactor-IRT model, specifying one general strain factor and four specific strains factors, was examined for fit to the sample data. A detailed item analysis, with analysis of the differential item functioning (DIF) of the items across gender, was undertaken to evaluate the dimensionality of the PSS. The associations among the PSS scale scores with scores on the concurrent measures, assessing psychache and suicidal behaviors, were examined.

RESULTS: IRT-derived specific bifactor indices showed that the PSS was unidimensional, and thus the PSS total scores should be reported. Unidimensional subset of 5 items identified (Item 9, Item 12, Item 14, Item 16, and Item 20), using bifactor-IRT modeling and incremental validation, were selected to construct a potential short form of the PSS (PSS-SF). The PSS-SF scale scores demonstrated strong psychometric properties and associations with scores on the concurrent measures assessing relevant constructs.

LIMITATIONS: This study used cross-sectional data from a non-clinical sample of Chinese undergraduate students.

METHODS: Using a whole-group sampling method, we assessed SI in 2192 (male = 834, female = 1358) medical students on three occasions over a period of one year. The Suicidal Ideation Self-Assessment Scale (SISAS) and the Childhood Trauma Questionnaire-Short Form (CTQ-SF) were used to assess SI and CT. The growth mixture modeling (GMM) was used to classify the developmental trajectory of SI.

METHODS: A total of 176 adolescents in selected urban areas in the states of Wilayah Persekutuan and Selangor were selected. The Suicide Ideation Scale (SIS) was used to measure the level of severity or tendency of suicidal ideation. The Multidimensional Scale of Perceived Social Support (MSPSS) was used to measure the perceived social support received by the respondent while the Spiritual Wellbeing Scale (SWBS) was used to measure the religious wellbeing (RWB), the existential wellbeing (EWB) and the overall score of spiritual wellbeing (SWB).

RESULTS: The study found that both RWB and EWB showed significant negative correlation with suicidal ideation. Similarly, support from family and friends also showed a negative correlation with suicidal ideation. Further analysis using multiple regressions showed that RWB and SWB, and family support predict suicidal ideation in adolescents.

METHODS: Participants comprised 1912 college students (16-28 years old, 47.2% female) from three universities in Jilin Province, China, who completed the self-report assessments of psychological strains (40 items Psychological Strains Scale) and suicidal behaviors (Suicidal Behaviors Questionnaire-Revised). The demographic characteristics included four variables: health status, psychological status, academic status and economic status.

RESULTS: Approximately 15.0% (286/1912) of participants were classified as having suicide risk, based on the cut-off scores of the SBQ-R. The prevalence of suicidal behaviors among males and females was 11.9% (120/1009) and 18.4% (166/903), respectively. Value strain (OR = 1.075, 95%CI: 1.057-1.094), aspiration strain (OR = 1.082, 95%CI: 1.064-1.101), deprivation strain (OR = 1.073, 95%CI: 1.052-1.093), and coping strain (OR = 1.095, 95%CI: 1.075-1.116) were risk factors for suicidality in college students. Coping strain (OR = 1.050, 95%CI: 1.023-1.077) was still positively associated with suicide risk in multivariate logistic regression. Logistic regression analysis indicated that coping strain had the highest correlation with suicidal behaviors.

LIMITATIONS: The directionality of the relationships cannot be deduced because this study is cross-sectional.

OBJECTIVES: This study examined the relationship between suicide attempts and bullying among school adolescents in Malaysia.

METHODS: Data from the Malaysia NHMS 2017, a nationwide study that adopted a two-stage cluster sampling design, were analysed. The survey used a self-administered questionnaire in bilingual language adapted from GSHS developed by WHO. Participants were secondary school students aged 13 -17 in all states. Descriptive and multiple logistic regression analyses were performed using IBM SPSS version 28.

OBJECTIVE: To examine the risk and protective factors contributing to suicidality among undergraduate college students in seven provinces in China.

METHODS: We conducted a cross-sectional study involving 13,387 college students from seven universities in Ningxia, Shandong, Shanghai, Jilin, Qinghai, Shaanxi, and Xinjiang. Data were collected using self-report questionnaires.

RESULTS: Higher scores in the psychological strain, depression, anxiety, stress, and psychache (psychological risk factors for suicidality) and lower scores in self-esteem and purpose in life (psychological protective factors against suicidality) were associated with increased suicidality among undergraduate students in China. Demographic factors which were associated with higher risks of suicidality were female gender, younger age, bad academic results, were an only child, non-participation in school associations, and had an urban household registration. Perceived good health was protective against suicidality.

METHODS: A search of four databases was conducted: Web of Science, PubMed, Dimensions, and Scopus for research papers dated between January 2016 and September 2021. The search keywords are 'data mining', 'machine learning' in combination with 'suicidal behaviour', 'suicide', 'suicide attempt', 'suicidal ideation', 'suicide plan' and 'self-harm'. The studies that used machine learning techniques were synthesized according to the countries of the articles, sample description, sample size, classification tasks, number of features used to develop the models, types of machine learning techniques, and evaluation of performance metrics.

RESULTS: Thirty-five empirical articles met the criteria to be included in the current review. We provide a general overview of machine learning techniques, examine the feature categories, describe methodological challenges, and suggest areas for improvement and research directions. Ensemble prediction models have been shown to be more accurate and useful than single prediction models.