Prediction of suicidal ideation with associated risk factors among university students in the southern part of Bangladesh: Machine learning approach

BACKGROUND

The prevalence of suicidal ideation has become an urgent issue, particularly among adolescents. The primary objective of this research is to determine the prevalence of suicidal ideation among students in the southern region of Bangladesh and to predict this phenomenon using machine learning (ML) models.

METHODS

The data collection process involved using a simple random sampling technique to gather information from university students located in the southern region of Bangladesh during the period spreading from April 2022 to June 2022. Upon accounting for missing values and non-response rates, the ultimate sample size was determined to be 584, with 51.5 % of participants identifying as male and 48.5 % female.

RESULTS

A significant proportion of students, precisely 19.9 %, reported experiencing suicidal ideation. Most participants were female (77 %) and unmarried (78 %). Within the machine learning (ML) framework, KNN exhibited the highest accuracy score of 91.45 %. In addition, the Random Forest (RF), and Categorical Boosting (CatBoost) algorithms exhibited comparable levels of accuracy, achieving scores of 90.60 and 90.59 respectively.

LIMITATIONS

Using a cross-sectional design in research limits the ability to establish causal relationships.

CONCLUSION

Mental health practitioners can employ the KNN model alongside patients' medical histories to detect those who may be at a higher risk of attempting suicide. This approach enables healthcare professionals to take appropriate measures, such as counselling, encouraging regular sleep patterns, and addressing depression and anxiety, to prevent suicide attempts.

Mental health conditions and adherence to direct oral anticoagulants in patients with incident atrial fibrillation: A nationwide cohort study

OBJECTIVE

Medication adherence is essential for effective stroke prevention in patients with atrial fibrillation (AF). We aimed to assess whether adherence to direct oral anticoagulants (DOACs) in AF patients is affected by the presence of mental health conditions (MHCs).

METHODS

The nationwide FinACAF cohort covered 74,222 AF patients from all levels of care receiving DOACs during 2011-2018 in Finland. Medication possession ratio (MPR) was used to quantify adherence. Patients with MPR ≥0.90 were defined adherent. MHCs of interest were depression, bipolar disorder, anxiety disorder and schizophrenia.

RESULTS

The patients' (mean age 75.4 ± 9.5 years, 50.8% female) mean MPR was 0.84 (SD 0.22), and 59.5% had MPR ≥0.90. Compared to patients without MHC, the adjusted ORs (95% CI) for adherent DOAC use emerged slightly lower in patients with depression (0.92 (0.84-0.99)) and bipolar disorder (0.77 (0.61-0.97)) and unsignificant in patients with anxiety disorder (1.08 (0.96-1.21)) and schizophrenia (1.13 (0.90-1.43)). However, when only persistent DOAC therapy was analyzed, no MHC was associated with poor adherence, and instead anxiety disorder was associated with adherent DOAC use (1.18 (1.04-1.34)).

CONCLUSION

Adherence to DOACs in AF patients in Finland was relatively high, and no meaningful differences between patients with and without MHCs were observed.

Using the Theory of Planned Behavior to Predict Korean College Students' Help-Seeking Intention

When dealing with the mental health concerns of college students, access to professional mental health services is necessary to enable early identification and prevention of severe mental health issues. Accordingly, this study used the theory of planned behavior (TPB) as a theoretical framework to determine the predictors of help-seeking intentions among college students in Korea. The authors developed a TPB questionnaire to measure attitudes, subjective norms, behavioral control, and intentions for seeking help and subsequently validated it via the confirmatory factor analysis (CFA). The authors considered mental health condition as a pre-existing factor that influences TPB variables. In addition, they deemed knowledge of professional mental health services as a factor influencing perceived behavioral control regarding help-seeking behavior among Korean college students. The research hypotheses were stated as follows: (H1) mental health conditions would influence TPB variables, which would in turn influence their intentions to seek help, and (H2) knowledge about professional mental health services would influence perceived behavioral control. With 300 undergraduate and graduate students, our results confirmed that mental health condition and knowledge about professional mental health services were associated with TPB variables, and all of the TPB variables we examined predicted intention to seek help.

Ethical Practices and Legal Challenges in Mental Health Research

Considerations of justice and concern for well-being support conducting mental health research and addressing ethical concerns specific to mental health research are critical. We discuss these concerns, provide recommendations to enable the ethical conduct of mental health research, and argue that participants' interests should be given primary weight in resolving apparent dilemmas. We also comment on provisions of two legislative actions in India relevant to mental health research: Rights of Persons with Disability Act 2016 and the Mental Health Care Act 2017. Both conform to the 2006 United Nations Convention on Rights of Persons with Disabilities of which India is a signatory. Both provide protections and enumerate rights relevant to people with mental health conditions but with differing focus. The commonalities and differences between the three are discussed in the background of international literature on research in mental health conditions. Studies involving deception and future directions for ethical requirements regarding genetic research are discussed.

Comparing Educational Music Therapy Interventions via Stages of Recovery with Adults in an Acute Care Mental Health Setting: A Cluster-Randomized Pilot Effectiveness Study

The purpose of this cluster-randomized pilot effectiveness study was to compare two different group-based educational music therapy interventions with a control condition as measured by the stage model of recovery in adults on an acute care mental health unit. Participants (N = 69) were cluster-randomized to one of three single-session conditions: educational lyric analysis (ELA), educational songwriting (ESW), or control. ELA and ESW conditions targeted motivations for and factors contributing to recovery. Results indicated no significant between-group difference. However, ELA and ESW conditions tended to have slightly more favorable stage of recovery mean scores than the control condition. Generally, educational music therapy may be clinically relevant for impacting stage of recovery within the temporal parameters of a single session. As ELA and ESW conditions had similar results, the specific educational music therapy intervention did not affect results. Implications for clinical practice, limitations, and suggestions for future research are provided.