Predictive Machine Learning Models for Assessing Lebanese University Students' Depression, Anxiety, and Stress During COVID-19.

University students are experiencing a mental health crisis. COVID-19 has exacerbated this situation. We have surveyed students in 2 universities in Lebanon to gauge their mental health challenges. We have constructed a machine learning (ML) approach to predict symptoms of depression, anxiety, and stress based on demographics and self-rated health measures. Our approach involved developing 8 ML predictive models, including Logistic Regression (LR), multi-layer perceptron (MLP) neural network, support vector machine (SVM), random forest (RF) and XGBoost, AdaBoost, Naïve Bayes (NB), and K-Nearest neighbors (KNN). Following their construction, we compared their respective performances. Our evaluation shows that RF (AUC = 78.27%), NB (AUC = 76.37%), and AdaBoost (AUC = 72.96%) have provided the highest-performing AUC scores for depression, anxiety, and stress, respectively. Self-rated health is found to be the top feature in predicting depression, while age was the top feature in predicting anxiety and stress, followed by self-rated health. Future work will focus on using data augmentation approaches and extending to multi-class anxiety predictions.

A cross-sectional study of university students' mental health and lifestyle practices amidst the COVID-19 pandemic.

OBJECTIVES: University students are regarded as the backbone of society, and their mental health during a pandemic may have a substantial impact on their performance and life outcomes. The purpose of this study was to assess university students' mental health, specifically depression, anxiety, and stress, during Lebanon's extended COVID-19 pandemic, as well as the sociodemographic factors and lifestyle practices associated with it. METHODS: An online anonymous survey assessed the rates of mental health problems during COVID-19, controlling for socio-demographics and other lifestyle practices, in 329 undergraduate and graduate university students. Instruments utilized were the Patient Health Questionnaire (PHQ-9) for depression, the Beck Anxiety Inventory (21-BAI) for anxiety, and the Perceived Stress Scale (PSS-10) for stress. The study employed descriptive statistics and multiple logistic regression models to analyze the association between depression, anxiety, and stress with sociodemographic and lifestyle factors. Results were evaluated using adjusted odds ratios and confidence intervals, with a significance level of 0.05. RESULTS: Moderate to severe rates of depression, anxiety and stress among students were reported by 75.9%, 72.2%, and 89.3%, respectively. The odds of anxiety and stress were higher among women compared to men. Students who used private counseling services had higher odds of anxiety and stress than those who did not. Overall rated health was a major predictor of depression and anxiety, with the "poor" and "fair" overall-reported health groups having higher odds than the "Excellent" group. When compared to those who did not smoke, students who increased their smoking intake had higher odds of depression, anxiety and stress. Students who reduced their alcohol consumption had lower odds of anxiety compared to those who did not consume alcohol. Students who reduced their physical activity had higher odds than those who increased it. Finally, students who slept fewer than seven hours daily had higher odds of depression than those who slept seven to nine hours. CONCLUSION: Our findings indicate a national student mental health crisis, with exceptionally high rates of moderate to severe depression, anxiety, and stress. Factors such as gender, university program, overall rated health, importance of religion in daily decisions, private counseling, smoking cigarettes, alcohol consumption, physical activity, and sleeping, were all found to have an impact on mental health outcomes. Our study highlights the need for university administrators and mental health professionals to consider targeted mental health programming for students, particularly for women and those with poor or fair overall perceived health.

Coping with the COVID-19 pandemic: A cross-sectional study to investigate how mental health, lifestyle, and socio-demographic factors shape students' quality of life.

PURPOSE: The high prevalence of COVID-19 has had an impact on the Quality of Life (QOL) of people across the world, particularly students. The purpose of this study was to investigate the social, lifestyle, and mental health aspects that are associated with QOL among university students in Lebanon. METHODS: A cross-sectional study design was implemented using a convenience sampling approach. Data collection took place between November 2021 and February 2022, involving 329 undergraduate and graduate students from private and public universities. Quality of life was assessed using the Quality-of-Life Scale (QOLS). Descriptive statistics, Cronbach's alpha, and linear regression-based methods were used to analyze the association between QOL and socio-demographic, health-related, lifestyle, and mental health factors. The significance level for statistical analysis was predetermined at α = 0.05. RESULTS: The study participants' average (SD) QOL score was 76.03 (15.6) with a Cronbach alpha of 0.911. QOL was positively associated with importance of religion in daily decisions (ß = 6.40, p = 0.006), household income (ß = 5.25, p = 0.017), general health ratings (ß Excellent/poor = 23.52, p <0.001), access to private counseling (ß = 4.05, p = 0.020), physical exercise (ß = 6.67, p <0.001), and a healthy diet (ß = 4.62, p = 0.026); and negatively associated with cigarette smoking (ß increased = -6.25, p = 0.030), internet use (ß ≥4 hours = -7.01, p = 0.005), depression (ß = -0.56, p = 0.002) and stress (ß = -0.93, p <0.001). CONCLUSION: In conclusion, this study reveals the key factors that positively and negatively influence students' quality of life (QOL). Factors such as religion, higher income, and a healthy diet improve QOL, while depression, stress, excessive internet use, and cigarette smoking negatively impact it. Universities should prioritize initiatives like physical activity promotion, affordable nutritious options, destigmatizing mental health, counseling services, and self-help interventions to support student well-being and enhance their QOL.

A Machine Learning Study to Predict Anxiety on Campuses in Lebanon.

University students are experiencing a mental health crisis across the world. COVID-19 has exacerbated this situation. We have conducted a survey among university students in two universities in Lebanon to gauge mental health challenges experienced by students. We constructed a machine learning approach to predict anxiety symptoms among the sample of 329 respondents based on student survey items including demographics and self-rated health. Five algorithms including logistic regression, multi-layer perceptron (MLP) neural network, support vector machine (SVM), random forest (RF) and XGBoost were used to predict anxiety. Multi-Layer Perceptron (MLP) provided the highest performing model AUC score (AUC=80.70%) and self-rated health was found to be the top ranked feature to predict anxiety. Future work will focus on using data augmentation approaches and extending to multi-class anxiety predictions. Multidisciplinary research is crucial in this emerging field.

Integrating Diversity, Equity, and Inclusion Into an Academic Department of Psychiatry and Behavioral Sciences.

This article highlights one department's efforts to bolster diversity, equity, and inclusion as an exemplar for other academic departments. It offers an approach for building an infrastructure and leadership group and details accomplishments associated with strategic plan priorities related to visibility, values, stakeholder education, recruitment, retention, promotion, and community engagement. It also delineates challenges encountered in transforming a departmental culture to one that is more diverse, equitable, and inclusive and strategies for overcoming these challenges. Finally, it discusses next steps and recommendations for other academic departments.

Learning to be interprofessional advocates in the public sector.

Engaging in advocacy is an ethical responsibility for behavioral health professionals, as reflected in professional competencies across disciplines and in personal accounts of wanting to affect change at various levels of patients'/clients' and communities' ecologies. However, the literature is replete with examples of barriers to routine advocacy engagement, including lack of an organized structure into which efforts can be embedded. There exists the desire among behavioral health professionals to engage in more advocacy work, yet a shared sense of not knowing how to incorporate this work into existing professional roles. One way to address these barriers is to establish more collaborative advocacy work environments within the public sector settings that employ behavioral health professionals. This article offers the first descriptive account of developing, implementing, and maintaining such a collaborative interprofessional advocacy workgroup. To that end, this case study is one example of such a group, the Atlanta Behavioral Health Advocates, based within the Emory University School of Medicine in the Department of Psychiatry and Behavioral Sciences and situated also within Grady Health System, a public health care system. This paper details our experiences forming and engaging in this group, which we believe can serve as a model for others developing similar advocacy workgroups in public sector settings. (PsycInfo Database Record (c) 2020 APA, all rights reserved).

Waterpipe smoking among college students in the United States: a review of the literature.

OBJECTIVE: To review the literature on college student waterpipe use with a focus on undergraduates in the United States. PARTICIPANTS: Undergraduate students. METHODS: Studies were accessed using the databases PubMed, MEDLINE, PsycINFO, and Academic Search Premier. Searches included combinations of the following keywords: "waterpipe," "hookah," "shisha," "nargila," "argileh," "hubble bubble," "college," "university," and "student." RESULTS: Results demonstrate that approximately 1 in 5 American college students report past-year waterpipe use. Results also suggest that there are a number of established correlates of waterpipe smoking, including male gender, Arab ethnicity, cigarette smoking, and the belief that waterpipe smoking is less harmful than cigarette smoking. CONCLUSIONS: Despite its harmful health effects, waterpipe smoking is quite common among college students. Future research with better methodologies and theoretical frameworks are needed to advance the field.

Argileh use among college students in the United States: an emerging trend.

OBJECTIVE: This study examined the prevalence and predictors of argileh (hookah pipe) use among a sample of nonselected college students. METHOD: Participants were 602 students (24% male; 43% white; mean age=22.06) at a large, ethnically diverse, urban university. All participants completed an online survey designed to assess various types of substance use. RESULTS: More than 15% of the sample reported having used argileh at least once in their lifetime, exceeding the percentage of students who had tried stimulants, barbiturates, cocaine, Ecstasy, heroin, or psychedelics. Arab ethnicity and cigarette smoking were the strongest predictors of argileh use; however, a substantial percentage of non-Arabs and nonsmokers also had tried argileh. CONCLUSIONS: Findings suggest that, in comparison with other substances, the prevalence of argileh use is high among college students in the United States. Physical health implications of these findings are discussed.