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.
CONCLUSIONS: Machine learning has great potential for improving estimates of future suicidal behaviour and monitoring changes in risk over time. Further research can address important challenges and potential opportunities that may contribute to significant advances in suicide prediction.
PURPOSE: The objective of this study is to examine the social risk factors that drive older people to have suicidal feelings or tendencies and the extent to which these factors arise from the changes that occur in their social environment as a result of the process of modernization and industrialization.
METHODS: This study employed the phenomenological approach through qualitative data collection technique. A total of 20 informants comprising 10 males and 10 females of Malay, Chinese and Indian ethnicity were selected for the study using purposive sampling technique. In-depth interviews were conducted with the informants. Data were transcribed and subsequently analyzed thematically using the NVivo 11 software.
RESULTS: The findings revealed five conditions that led older people toward suicidal intentions. These include social and cultural changes, lack of social support, conflict in religious belief, influence of economic uncertainty and socio-economic status, and depression as a result of the changes in their social environment.
CONCLUSION: The implication of this research is that these factors affect older people directly as they struggle to adapt and respond to the major changes that occur in the social structure of the society they live in, stemming from the process of modernization and industrialization. Efforts to enact better policies and services for older people need to be addressed especially in developing countries based on assessment of their needs, weaknesses, strengths, and capabilities by incorporating elements of the worldview of the older people based on their experiences of daily lives.
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.
CONCLUSIONS: The PSS-SF should be considered as a unidimensional instrument with potential in enhancing our understanding and measurement of psychological strains with reduced response burden.
METHOD: A self-administered questionnaire was used to collect the data. We used F and χ2 tests and correlation analyses to report descriptive statistics. Multi-group path models with (i) a zero-inflated Poisson distribution and, (ii) a Binomial distribution were used to model the number of occurrences of suicidal ideation, and occurrence of a suicide attempt, respectively.
RESULTS: Religiosity was negatively associated with acceptability of suicide, but it was positively related to punishment after death across the 11 countries. Religiosity was negatively associated with ever experiencing suicidal ideation, both directly and indirectly through its association with attitudes towards suicide, especially the belief in acceptability of suicide. Neither positive nor negative religious coping were related to suicidal ideation. However, religiosity was negatively related to suicide attempts among those who experienced suicidal ideation at least once. This association was mediated through the belief in acceptability of suicide and religious coping. Negative religious coping was positively associated with suicide attempts probably because it weakened the protective effects of religiosity.
CONCLUSIONS: Findings from this study suggest that the effects of religiosity in the suicidal process operate through attitudes towards suicide. We therefore conclude that clinical assessment as well as research in suicidology may benefit from paying due attention to attitudes towards suicide.
METHODS: The sample consisted of 7427 college students (56% female) who reported to be affiliated with Islam. Data on self-construal, social support, negative life-events, acceptability of suicide, suicidal ideation, and suicide attempts were collected with self-administered questionnaires.
RESULTS: Acceptability of suicide and the experience of negative life-events were positively, and perceived social support was negatively associated with suicidal ideation. Interdependent self-construal was negatively related to the acceptability of suicide and positively associated with perceived social support, implying a negative indirect effect on suicidal ideation although its direct effect was positive. The number of negative life-events was the strongest positive predictor of ever attempting suicide. The interdependent self-construal moderated the association of negative life-events with suicide attempts.
LIMITATIONS: Cross-sectional and self-report nature of the study were its major limitations. Participants may have suppressed their responses about suicide because of religious and legal reasons.
CONCLUSION: Remarkable similarities across 11 country samples emerged in the linkages between cultural and interpersonal factors with suicidality. Our findings highlight the value of a nuanced approach to suicidality, that can recognize the differences in the processes associated with suicidal ideation and suicide attempts, as well as the need to consider the interplay of a broad range of personal, interpersonal, and cultural influences.
STUDY DESIGN: The study design is a cross-sectional self-report study conducted across 42 countries.
METHODS: A cross-sectional, self-report study was conducted in 42 countries, with a total of 82,243 participants included in the final data set.
RESULTS: The study provides an overview of suicide ideation rates across 42 countries and confirms the structural validity of the P4 screener. The findings indicated that sexual and gender minority individuals exhibited higher rates of suicidal ideation. The P4 screener showed adequate reliability, convergence, and discriminant validity, and a cutoff score of 1 is recommended to identify individuals at risk of suicidal behavior.
CONCLUSIONS: The study supports the reliability and validity of the P4 suicide screener across 42 diverse countries, highlighting the importance of using a cross-cultural suicide risk assessment to standardize the identification of high-risk individuals and tailoring culturally sensitive suicide prevention strategies.
DATA AND METHODOLOGY: Data were obtained by a questionnaire survey in a large public hospital in a big metropolitan city of China. The final sample consisted of 1012 respondents with 237 (23.4%) being male and 775 (76.6%) being female. The respondents were of three groups: (1) Believers (n = 34; 3.5%); (2) Non-Believers or Atheists (n = 547; 55.8%); and (3) Agnostics or Fence-Sitters (n = 400; 40.8%). Suicidality was measured by the NCS-Suicidality Scale, and standard measures were employed for other major variables.
FINDINGS: In line with other recent studies in China, the religion rate among the urban adults remained low (3.5%). However, about 40.8% of the respondents chose "don't know" and could be fence-sitters on the issue of religious belief. Many of them are involved in various folk beliefs which may not be considered as religious. The religious believers were at higher risk of suicidality and depression than the atheists and the fence-sitters. However, the fence-sitters were higher than the believers and atheists on psychological strains, and they were higher on depression compared to the atheists.
CONCLUSION: The religious believers and religious fence-sitters have higher psychopathologic risks and suicidal risk than the atheist group. Religion as of low prevalence in Chinese societies is a social value deviant from the norm and its practitioners are likely to be marginalized or stigmatized. The Strain Theory of Suicide is used for detailed explanations.