Undergraduate students are often impacted by depression, anxiety, and stress. In this context, machine learning may support mental health assessment. Based on the following research question: “How do machine learning models perform in the detection of depression, anxiety, and stress among undergraduate students?”, we aimed to evaluate the performance of these models. PubMed, Embase, PsycINFO, and Web of Science databases were searched, aiming at studies meeting the following criteria: publication in English; targeting undergraduate university students; empirical studies; having been published in a scientific journal; and predicting anxiety, depression, or stress outcomes via machine learning. The certainty of evidence was analyzed using the GRADE. As of January 2024, 2,304 articles were found, and 48 studies met the inclusion criteria. Different types of data were identified, including behavioral, physiological, internet usage, neurocerebral, blood markers, mixed data, as well as demographic and mobility data. Among the 33 studies that provided accuracy assessment, 30 reported values that exceeded 70%. Accuracy in detecting stress ranged from 63% to 100%, anxiety from 53.69% to 97.9%, and depression from 73.5% to 99.1%. Although most models present adequate performance, it should be noted that 47 of them only performed internal validation, which may overstate the performance data. Moreover, the GRADE checklist suggested that the quality of the evidence was very low. These findings indicate that machine learning algorithms hold promise in Public Health; however, it is crucial to scrutinize their practical applicability. Further studies should invest mainly in external validation of the machine learning models.

Introduction: Epidemiological data suggest substantial issues on the mental health of university students worldwide. Self-compassion is associated with lower rates of psychological distress and better positive mental health. Thus, we have developed a app-based intervention based on self-compassion principles targeting the prevention and promotion of mental health in college students. The current pilot study assessed adherence to intervention, preliminary mental health benefits, and satisfaction and acceptability with the app among Brazilian college students.Methods: The study employed a pre-experimental single-group design along with pre-test and post-test assessments (n = 23). A mixed methods approach was utilized to comprehensively assess the outcomes of the intervention.Results: The overall adherence rate for the intervention was 37.87%, with 26.26% of participants successfully completing all modules. Among the 21 outcomes assessed, 15 exhibited statistically significant results. Notably, there was a substantial increase in self-compassion, demonstrating a large effect size (d = 1.15), and a moderate effect size reduction in stress (d = 0.62) and anxiety (d = 0.52). All satisfaction indicators for the intervention received scores above 7. The intervention was well-received by participants who completed it, although a potential barrier identified was the volume of text within the app and the need to adopt a more playful and concise format for the intervention.Discussion: Despite a notable participant dropout, the adherence to intervention aligns with patterns observed in other online interventions conducted in real-world settings. The observed mental health benefits, high satisfaction levels, and positive acceptance underscore the rationale for pursuing a subsequent randomized clinical trial.

Emotional self-regulation is a relevant factor for human development capable of minimizing emotional difficulties in the face of adverse events, as was particularly useful during the COVID-19 pandemic. The present study aimed to evaluate emotional self-regulation in Brazilian health science university students and its relationship with positive psychology constructs (subjective well-being, hope, optimism, spirituality, self-compassion, and self-efficacy) and psychological distress (depression, anxiety, and stress). This was a prospective, cross-sectional, observational, analytic study of 1062 Brazilian undergraduate students with data collected using self-administered online questionnaires. Students in the first years of their undergraduate degree programs had significantly higher dysregulation scores than those in the final years. Multiple linear regression yielded a model that explained 71.8% of the variation in emotion dysregulation. The correlations of emotion dysregulation were significant and strong, scoring negatively with self-compassion, optimism, and subjective well-being and positively with psychological distress.

Introduction: Depression in aging may lead to loss of autonomy and worsening of comorbidities. Understanding how positive attributes contribute to healthier and happier aging has been one of the purposes of Positive Psychology. However, the literature still lacks studies that evaluate how depression in the elderly is related to constructs considered positive.Objective: The present study aimed comparing scores of constructs of spiritual well-being, social support, self-esteem, life satisfaction, affection, optimism, and hope in the elderly with minimal, mild, moderate, and severe depression and healthy controls in order to investigate possible indirect and mediated relationships between positive constructs and depression.Methods: A cross-sectional study was conducted with elderly, 62 of whom were diagnosed with different severity of Major Depression (DSM-V) (minimum, mild, moderate, and severe according to the Beck Depression Inventory — BDI) and 66 healthy controls matched by age, sex and schooling. The instruments used were adapted and validated versions of the Spirituality Self-Rating Scale, the Rosenberg Self-Esteem Scale, the Medical Outcomes Social Scale of Support, the Life Satisfaction Scale, the Positive and Negative Affect Schedule, the Revised Life Orientation Test, and the Adult Dispositional Hope Scale. After comparing the means of scores between groups, an analysis of normalized partial association networks was performed to investigate the direct and mediated relationships between depression and other evaluated constructs.Results: Scores of spiritual well-being, social support, self-esteem, life satisfaction, positive affect, optimism, negative affects, and hope differed significantly between the control group and the degrees of depression (p< 0.001). The analysis of normalized partial association networks has shown that the relations of depression with the constructs of life satisfaction, self-esteem, and social support are mediated, while the constructs of dispositional hope, positive affect, spiritual well-being, and optimism are indirectly related to depression. The social class was also positively related to depression.Conclusion: Depression in different degrees is associated with a reduction in the scores of instruments that evaluate positive attributes. The constructs directly associated with depression are spiritual well-being, optimism, positive affect, and dispositional hope. The others had mediated relationship. These results may contribute to the planning of future interventions for the prevention of depression among the elderly.

Background: Despite the availability of antiretroviral therapy (ART) in many countries, people living with HIV still experience difficulties with treatment. We propose a new smartphone mobile application to assist in adherence to ART. This study aimed to describe this new mobile application’s development (content construction and usability), feasibility testing (recruitment, retention rates [attendance], satisfaction) and primary perceived benefits. Methods: Two consecutive studies were conducted. First, people living with HIV, health care workers and experts in information technology provided feedback to improve the content and usability of the app. After changes in the app were implemented according to the feedback, a second study was performed to assess the feasibility and perceived benefits. Effects on self-reported adherence and perceived well-being were also assessed. Results: Scores of participants (N = 11) showed differences in adherence (effect size .43) and well-being (effect size .45) after using the app. However, the differences did not reach statistical significance. Observing scores individually, six out of 11 participants improved their overall adherence scores, and seven out of 11 participants improved their perceived well-being scores. Recruitment was 95%, and attendance at sessions was 62.5%. In general, the participants were satisfied with the intervention and viewed the app as an informative tool. Conclusion: The results are promising and allow us to recommend further studies with the app.

Pedagogical Agent Gestures to Improve Learner Comprehension of Abstract Concepts in Hints: 10.4018/IJICTE.2016070106: In most Intelligent Tutoring Systems, the help messages (hints) are not very clear for students as they are only presented textually and have little