In this study, machine learning was used to assess the prediction of the magnitude of depression changes in college students based on various psychological variable information.

A group of college students from a certain school completed two assessments in October 2021 and March 2022, respectively. We collected baseline levels of depression, demographic variables, parenting styles, college students' mental health information, personality information, coping styles, SCL-90, and social support information. We applied logistic regression, random forest, support vector machine, and k-nearest neighbor machine learning methods to predict the magnitude of depression changes in college students. We selected the best-performing model and outputted the importance of features collected at different time points.

Whether it is predicting the magnitude of positive changes or negative changes in depression, support vector machines (SVM) had the best prediction performance (with an accuracy of 89.4% for predicting negative changes in depression and an accuracy of 91.9% for predicting positive changes in depression). The baseline level of depression, father's emotional expression, and mother's emotional expression were all important predictors for predicting the negative and positive changes in depression among college students.

Machine learning models can predict the extent of depression changes in college students. The baseline level of depression, as well as the emotional state of both fathers and mothers, play a significant role in predicting the negative and positive changes associated with depression in college students. This provides new insights and methods for future psychological health research and practice.

Knowledge about the causes of mental illness is a crucial component of mental health literacy. Poor understanding of the etiology of mental illness can lead to stigmatizing behaviors and hinder access to appropriate help. The current cross-sectional study examined the general population's causal beliefs about seven mental illnesses and explored the factor structure of the revised causal beliefs scale.

Four thousand one hundred ninety-five respondents were randomly assigned a vignette and were asked questions on their recognition of the mental illness depicted, causal beliefs, and prior experience related to the mental illness (similar problems, had a mental health-related job or family and friends with similar problems). Exploratory and confirmatory factor analyses were used to examine the factor structure of the causal beliefs scale. Multivariable linear regression was used to examine its predictors.

Factor analyses revealed a four-factor structure of causal beliefs: physical, psychosocial, personality, and biogenetic. Causal beliefs differed across the vignettes. Compared to schizophrenia, biogenetic beliefs were less likely to be endorsed for all mental illnesses except dementia, while personality beliefs were more likely to be endorsed for depression with suicidality. Compared to respondents who did not recognize the mental illness, those with correct recognition were more likely to endorse biogenetic and psychosocial beliefs, and less likely to endorse physical and personality beliefs.

Factor structure of the original causal beliefs scale was found to be valid in the Singapore population. Individuals who correctly recognized the mental illness appeared to comprehend its etiology well. However, some misconceptions about the etiology of mental illness persist, particularly with regards to relating obsessive-compulsive disorder to physical factors (e.g., virus) and depression with suicidality to personality flaws. As future awareness campaigns continue to address the gaps in literacy levels, careful promotion of certain causal beliefs is crucial to avoid conveying unintended messages.

To investigate the mediating role of depression in the relationship between nighttime sleep duration and cognitive function among middle-aged and older adult patients with multimorbidity, providing insights for mitigating cognitive decline.

Utilizing data from the China Health and Retirement Longitudinal Study (CHARLS) (2015 and 2020 waves), 4,210 participants with ≥2 chronic conditions were included. Correlation, regression, and mediation analyses were conducted to examine associations between sleep duration, depression, and cognitive function.

The prevalence of cognitive impairment was 35.7%. Nighttime sleep duration showed a weak positive correlation with cognitive function (r = 0.071, p < 0.01) and a stronger negative correlation with depression (r = -0.251, p < 0.01). Depression was negatively correlated with cognitive function (r = -0.262, p < 0.01). Mediation analysis revealed that depression fully mediated the sleep-cognition relationship [indirect effect: 0.120, 95% CI (0.100-0.141); direct effect nonsignificant].

Depression fully mediates the association between nighttime sleep duration and cognitive function in multimorbidity patients. Interventions targeting sleep hygiene and mental health may synergistically alleviate cognitive decline in this population.

Body mass index (BMI) is widely used as an indicator of physical health and has been associated with various psychological and social outcomes. While previous studies have explored the link between BMI and mental wellbeing, findings remain inconsistent, especially among young adults. This study aimed to examine the associations between BMI and self-reported happiness among young adults in Taiwan.

A cross-sectional study was conducted using secondary datasets from the Taiwan National Physical Activity Survey, a nationally representative survey of the Taiwanese population. A total of 10,638 young adults aged 18-44 years were enrolled in this study between August and October 2020. Demographic characteristics, self-reported health status, self-evaluations (comprising height, body weight, BMI, and happiness levels), and residence zip codes were among the data obtained through the national telephone survey.

The results revealed that, participants in very happy (β = 3.167, p < 0.001), happy (β = 3.239, p < 0.001), fair (β = 3.058, p < 0.001), and unhappy (β = 2.942, p < 0.001) groups exhibited a significantly higher BMI than did participants in very unhappy group. After adjusting for potential confounders, the very happy, happy, fair, and unhappy groups showed statistically associated with underweight risk reduction (OR = 0.196, 95% CI: 0.061-0.633; OR = 0.258, 95% CI: 0.085-0.785; OR = 0.271, 95% CI: 0.083-0.882; OR = 0.222, 95% CI: 0.069-0.714).

Overall, this study revealed that happiness levels were positively associated with BMI, and the increments of happiness levels may have reducing the risk of underweight occurrence.

Cardiac rehabilitation (CR) programmes are effective, but they are underutilized. Digitally enabled CR programmes (DeCR) offer alternative means of healthcare delivery. We aimed to assess the effects of a DeCR programme on cardiovascular risk factors and healthcare utilization.

In this observational cohort study that used propensity score matching, privately insured Australian patients, recruited nationally following a cardiac hospitalization, were given a digital app and received weekly telehealth consultations. Risk factors were assessed before and after the intervention. Propensity scoring methods were used to compare differences in 30-day, 90-day, and 12-month rehospitalizations, hospital-days, and mortality rates in the DeCR group with patients who undertook: (i) usual care (n = 266) or (ii) face-to-face CR (F2F-CR, n = 115). Overall, 172 intervention patients (70% men, age 68 ± 10 years, 36% living in regional/remote areas) were enrolled (59% agreed to participate and 91% completed final follow-up). The DeCR group had significant improvements in most risk factors. Rehospitalization and mortality rates were similar between the DeCR group and both comparison groups at all time points (all P > 0.05). Patients in the DeCR group spent significantly fewer days in hospital compared with usual care within 30-days (P = 0.026), 90-days (P = 0.003), and 12-months (P = 0.04) post-discharge. Cardiac-related rehospitalization bed days were reduced at 30-days (P = 0.005) and 90-days (P = 0.017) but not 12-months (P = 0.20). There were no group differences between DeCR and F2F-CR across any outcomes (all P > 0.05).

DeCR was associated with lower healthcare utilization than usual care, yet comparable compared with F2F-CR. DeCR represents a suitable option for cardiac patients post-discharge.

We investigated whether a digitally enabled cardiac rehabilitation (DeCR) programme, delivered to patients following a heart disease hospitalization, improved patients' cardiovascular disease risk factors and whether they had a reduction in rehospitalizations, spent fewer days in hospital and improved survival compared with matched controls who undertook either face-to-face cardiac rehabilitation (F2F-CR) or usual care.• DeCR was associated with similar healthcare utilization outcomes compared with F2F-CR. This suggests that the potential benefits of DeCR may be comparable. Additionally, DeCR programmes create an opportunity for patients to choose the style of CR to undertake and have an advantage of broader access.• The DeCR group spent significantly fewer readmission days in hospital compared with the usual care group, which may reflect differences in the nature of rehospitalizations when they occur.

Participating in religious activities benefits older adults' mental health; however, the effects of grave visitation, a significant religious practice in Japan, on older adults' mental health remain unclear. Therefore, this study examined the relationship between grave visitation frequency and depressive symptoms.

A prospective cohort study of 273 community-dwelling older adults in Japan was conducted with baseline (2018) and follow-up (2022) assessments. Participants were categorized by visitation frequency: more or less than once a week. Changes in visitation frequency were classified as continued high, decreased, continued low, or increased. Depressive symptoms were assessed using the Geriatric Depression Scale (GDS-15). Multivariable linear regressions were used to examine the association between visitation and depressive symptoms.

Lower visitation at baseline was associated with worse GDS-15 scores in the follow-up. Those with decreased or continued low visitation had significantly worse depressive symptoms. After adjusting for baseline GDS-15 scores and covariates, the decreased group had significantly worse depressive symptoms than the continued high group.

The findings indicate that changes in grave visitation frequency are significantly associated with depressive symptoms.

Supporting older adults' access to grave visitation through transportation or community programs may help maintain their well-being and emotional health.

Lesbian, gay, and bisexual (LGB) individuals are more than twice as likely to experience anxiety and depression compared with heterosexuals. Minority stress theory posits that stigma and discrimination contribute to chronic stress, potentially affecting clinical treatment. We compared psychological therapy outcomes between LGB and heterosexual patients by gender.

Retrospective cohort data were obtained from seven NHS talking therapy services in London, from April 2013 to December 2023. Of 100,389 patients, 94,239 reported sexual orientation, 7,422 identifying as LGB. The primary outcome was reliable recovery from anxiety and depression. Secondary outcomes were reliable improvement, depression and anxiety severity, therapy attrition, and engagement. Analyses were stratified by gender and employed multilevel regression models, adjusting for sociodemographic and clinical covariates.

After adjustment, gay men had higher odds of reliable recovery (OR: 1.23, 95% CI: 1.13-1.34) and reliable improvement (OR: 1.16, 95% CI: 1.06-1.28) than heterosexual men, with lower attrition (OR: 0.88, 95% CI: 0.80-0.97) and greater reductions in depression (MD: 0.51, 95% CI: 0.28-0.74) and anxiety (MD: 0.45, 95% CI: 0.25-0.65). Bisexual men (OR: 0.67, 95% CI: 0.54-0.83) and bisexual women (OR: 0.84, 95% CI: 0.77-0.93) had lower attrition than heterosexuals. Lesbian and bisexual women, and bisexual men, attended slightly more sessions (MD: 0.02-0.03, 95% CI: 0.01-0.04) than heterosexual patients. No other differences were observed.

Despite significant mental health burdens and stressors, LGB individuals had similar, if not marginally better, outcomes and engagement with psychological therapy compared with heterosexual patients.

To explore whether people 'other' when making judgements about 'harmful' drinking and the drinking contexts (e.g., pub with friends) and features of drinking contexts (e.g., location, company) perceived as being indicative of harmful drinking.

Focus group design with arts-based methods.

Risky drinkers (AUDIT-C ≥ 5; n = 20) in four focus groups, drew and discussed contexts and features of contexts they thought indicated harmful drinking. Reflexive thematic analysis was conducted alongside content analysis of drawings informed by themes and prior research.

There are three deductive themes. The first theme semblance of control referred to people's tendency to differentiate their own drinking practices as controlled and safe in relation to the out-of-control behaviours of a harmful drinker. This was seen in the content analysis of drawings where participants tended to draw drinking contexts which were different to those they drank in. The drinking practices perceived as being indicative of harmful drinking were further explored in the second theme harmful drinking contexts. This theme was made up of four subthemes: mental harms, physical harms, social harms and societal harms which were discussed as being differentially associated with different types of drinking contexts. The final theme, features which make drinking 'harmful', focused on the features of drinking contexts which participants felt were more indicative of harm. There were seven subthemes: alone, home, amount, drink type, having responsibilities, reason for drinking and timing/pattern.

Drinking contexts fed into the construction of othering narratives among risky drinkers. This has implications for alcohol harm reduction campaigns.

Parent-Child Interaction Therapy-Toddler (PCIT-T) and Circle of Security-Parenting (COS-P) are two attachment-based early parenting programs with emerging evidence bases. Most of the research has, however, been quantitative in nature. Understanding caregiver perspectives and acceptability of the programs is therefore needed. This study aimed to address this gap in research by examining perspectives of parents who participated in PCIT-T or COS-P at an Australian community-based child behavior clinic for treatment of toddler behavior problems. Twenty-nine mothers were purposively recruited to participate in a semi-structured post-program interview (COS-P: n = 10; PCIT-T: n = 19). Data were analyzed using an inductive thematic analysis approach. Results of thematic analysis showed that parents in both groups experienced a range of positive gains (for the toddler, themselves as a parent, and for relationships). Participants in both groups identified the clinician as a key facilitator of positive program outcomes, and time commitment as a barrier. For the COS-P group, the group process and treatment journey were identified as facilitators, and inconsistent attendance from group attendees was a barrier. The PCIT-T group viewed the live coaching and the manualized protocol as facilitators. Results suggest that both COS-P and PCIT-T are viewed positively by parents and identify several parent-identified facilitators/barriers.

Mood disorders, including bipolar disorder (BP) and major depressive disorder (MDD), are characterized by significant psychological and behavioral fluctuations, with mobility patterns serving as potential markers of emotional states.

This study explores the diagnostic and monitoring capabilities of Fourier transform, a frequency-domain analysis method, in mood disorders by leveraging GPS data as an objective measure.

A total of 62 participants (BP: n=20, MDD: n=27, and healthy controls: n=15) contributed 5177 person-days of data over observation periods ranging from 5 days to 6 months. Key GPS indicators-location variance (LV), transition time (TT), and entropy-were identified as reflective of mood fluctuations and diagnostic differences between BP and MDD.

Fourier transform analysis revealed that the maximum power spectra of LV and entropy differed significantly between BP and MDD groups, with patients with BP exhibiting greater periodicity and intensity in mobility patterns. Notably, participants with BP demonstrated consistent periodic waves (eg, 1-d, 4-d, and 9-d cycles), while such patterns were absent in those with MDD. In addition, after adjusting for age, gender, and employment status, only the power spectrum of LV remained a significant predictor of depressed mood (odds ratio [OR] 0.9976, 95% CI 0.9956-0.9996; P=.02). Daily GPS data showed stronger correlations with ecological momentary assessment (EMA)-reported mood states compared to weekly or monthly aggregations, emphasizing the importance of day-to-day monitoring. Depressive states were associated with reduced LV (OR 0.975, 95% CI 0.957-0.993; P=.008) and TT (OR 0.048, 95% CI 0.012-0.200; P<.001) on weekdays, and lower entropy (OR 0.662, 95% CI 0.520-0.842; P=.001) on weekends, indicating that mobility features vary with social and temporal contexts.

This study underscores the potential of GPS-derived mobility data, analyzed through Fourier transform, as a noninvasive and real-time diagnostic and monitoring tool for mood disorders. The findings suggest that the intensity of mobility patterns, rather than their frequency, may better differentiate BP from MDD. Integrating GPS data with EMAs could enhance the precision of clinical assessments, provide early warnings for mood episodes, and support personalized interventions, ultimately improving mental health outcomes. This approach represents a promising step toward digital phenotyping and advanced mental health monitoring strategies.