Lifestyle predictors of depression and anxiety during COVID-19: a machine learning approach

Abstract Introduction Recent research has suggested an increase in the global prevalence of psychiatric symptoms during the COVID-19 pandemic. This study aimed to assess whether lifestyle behaviors can predict the presence of depression and anxiety in the Brazilian general population, using a model developed in Spain. Methods A web survey was conducted during April-May 2020, which included the Short Multidimensional Inventory Lifestyle Evaluation (SMILE) scale, assessing lifestyle behaviors during the COVID-19 pandemic. Depression and anxiety were examined using the PHQ-2 and the GAD-7, respectively. Elastic net, random forest, and gradient tree boosting were used to develop predictive models. Each technique used a subset of the Spanish sample to train the models, which were then tested internally (vs. the remainder of the Spanish sample) and externally (vs. the full Brazilian sample), evaluating their effectiveness. Results The study sample included 22,562 individuals (19,069 from Brazil, and 3,493 from Spain). The models developed performed similarly and were equally effective in predicting depression and anxiety in both tests, with internal test AUC-ROC values of 0.85 (depression) and 0.86 (anxiety), and external test AUC-ROC values of 0.85 (depression) and 0.84 (anxiety). Meaning of life was the strongest predictor of depression, while sleep quality was the strongest predictor of anxiety during the COVID-19 epidemic. Conclusions Specific lifestyle behaviors during the early COVID-19 epidemic successfully predicted the presence of depression and anxiety in a large Brazilian sample using machine learning models developed on a Spanish sample. Targeted interventions focused on promoting healthier lifestyles are encouraged.

Would the Brazilian population support the alcohol policies recommended by the World Health Organization?

ABSTRACT OBJECTIVE To evaluate the support of the Brazilian population to the alcohol-policies proposed by the World Health Organization to decrease alcohol harm (specifically: to decrease alcohol availability and advertising, and to increase pricing). In addition, we evaluated the factors associated with being against those policies. METHODS Data from 16,273 Brazilians, aged 12-65 years, interviewed in the 3rd Brazilian Household Survey on Substance Use (BHSU-3) were analyzed. The BHSU-3 is a nationwide, probability survey conducted in 2015. Individuals were asked if they would be against, neutral, or in favor of seven alcohol policies grouped as: 1) Strengthen restrictions on alcohol availability; 2) Enforce bans or restrictions on alcohol advertising, sponsorship, and promotion; and 3) Raise prices on alcohol through excise taxes and pricing. Generalized linear models were fitted to evaluate factors associated with being against each one of those policies and against all of policies. RESULTS Overall, 28% of the Brazilians supported all the above mentioned policies, whereas 16% were against them. The highest rate of approval refers to restricting advertising (53%), the lowest refers to increasing prices (40%). Factors associated with being against all policies were: being male (AOR = 1.1; 95%CI: 1.0-1.3), not having a religion (AOR = 1.4; 95%CI: 1.1-1.8), being catholic (AOR = 1.3; 95%CI: 1.1-1.5), and alcohol dependence (AOR = 1.6; 95%CI: 1.1-2.4). CONCLUSIONS The Brazilian government could count on the support of most of the population to restrict alcohol advertising. This information is essential to tackle the lobby of the alcohol industry and its clever marketing strategy.

Satisfaction and burden of mental health personnel: data from healthcare services for substance users and their families

Objective: To evaluate satisfaction and burden of mental health personnel providing mental health services for substance users and their families. Method: Five hundred twenty-seven mental health workers who provide treatment for substance users in five Brazilian states were interviewed. Data on sociodemographic characteristics and measures of satisfaction (SATIS-BR) and burden of mental health personnel (IMPACTO-BR) were collected. Results: Type of mental health service and educational attainment were associated with degree of satisfaction and burden. Therapeutic community workers and those with a primary education level reported being more satisfied with the treatment offered to patients, their engagement in service activities, and working conditions. Workers from psychosocial care centers, psychosocial care centers focused on alcohol and other drugs, and social care referral centers (both general and specialized), as well as workers with a higher education, reported feeling overburdened. Conclusion: This study offers important information regarding the relationship of mental health personnel with their work. Care providers within this sample reported an overall high level of job satisfaction, while perceived burden differed by type of service and educational attainment. To our knowledge, this is the first study with a sample of mental health professionals working with substance users across five Brazilian states.

Have drivers at alcohol outlets changed their behavior after the new traffic law?

Objective: In an attempt to reduce high levels of traffic crashes, a new legislation was approved in Brazil in 2008. This study aimed to assess behavioral change among drivers who had drunk at alcohol outlets (AO) after implementation of the law. Method: A three-stage probability sampling survey was conducted in Porto Alegre, state of Rio Grande do Sul, Brazil. Individuals seen leaving AOs after drinking were approached (n=3,018). Selected drivers (n=683) answered a structured interview, were breathalyzed, and had saliva specimens collected for drug screening. Results: Overall, 60.3% (SE 4.5) of drivers reported they did not change their behavior. Among those who reported behavioral changes, most reported drinking less as their main strategy toward safer driving behavior. Variables independently associated with behavior change included having drunk at a high outlet density area (odds ratio [OR] 1.7 [1.1-2.8]) and having a favorable opinion about the law (OR 4.3 [2.1-8.9]). Conclusions: Our findings suggest that awareness of the law has not been enough to promote behavioral change. As most drivers had a favorable opinion of the law and this variable was found to be the strongest predictor of behavior change, efforts to better integrate education and enforcement seem to be pivotal and might be well received by the population. .