Portugal has the sixth highest road fatality rate among European Union members. This is a problem of different dimensions with serious consequences in people’s lives. This study analyses daily data from police and government authorities on road traffic accidents that occurred between 2016 and 2019 in a district of Portugal. This paper looks for the determinants that contribute to the existence of victims in road traffic accidents, as well as the determinants for fatalities and/or serious injuries in accidents with victims. We use logistic regression models, and the results are compared to the machine-learning model results. For the severity model, where the response variable indicates whether only property damage or casualties resulted in the traffic accident, we used a large sample with a small imbalance. For the serious injuries model, where the response variable indicates whether or not there were victims with serious injuries and/or fatalities in the traffic accident with victims, we used a small sample with very imbalanced data. Empirical analysis supports the conclusion that, with a small sample of imbalanced data, machine-learning models generally do not perform better than statistical models; however, they perform similarly when the sample is large and has a small imbalance.

Background. The mental health of university students has worsened over time, and it is young people who have suffered the most from the COVID-19 pandemic in terms of mental health. Anxiety and depression are the most common symptoms reported by university students and are often the cause of disabilities, either in academic performance or in other spheres of life. Aim. The aim of this study was to both assess the prevalence of depressive and anxiety symptoms in Portuguese university students and analyze the factors associated with these symptoms. Methods. A quantitative cross-sectional study with a sample of 3,399 university students from seven Portuguese higher education institutions was conducted. The following questionnaires were used: the generalized anxiety disorder assessment scale (GAD-7), the patient health questionnaire (PHQ-9), and a study-created sociodemographic questionnaire. The Kendall correlation coefficient, chi-square test of independence, Spearman correlation coefficient, Shapiro-Wilk test, Mann–Whitney-Wilcoxon test, and Kruskall-Wallis test were used to analyze the association between variables. The statistical analysis was done using the software R Statistics (Version 4.0.4), using a significance level of 0.05. Results. Mild to severe anxiety symptoms were reported by 75% of the participants, and 61.2% described mild to severe depressive symptoms. Of the sample, 19.5% reported a previous diagnosis of a mental disorder, with 38.7% diagnosed after the pandemic began. Additionally, 23% reported taking medication for mental health issues, and 26.7% had considered self-harm or harbored thoughts of being “better off dead.” The study found lower anxiety and depressive symptoms ( ) among men, students with higher socioeconomic status, those who frequently traveled home, individuals without prior mental health diagnoses, those with better academic performance, and those who avoided substances like coffee, tobacco, cannabis, and other illegal psychoactive substances. Interestingly, students in romantic relationships exhibited more anxiety symptoms ( ). Moreover, participants who believed they had experienced moral or sexual harassment displayed higher levels of anxiety and depressive symptoms ( ). Conclusions. There was a decrease in the mental health of university students after the pandemic compared to prepandemic studies, and the proportion of students with anxiety and depressive symptoms was alarming. There is an urgent need to implement programs in universities to promote students’ mental health.

Mental health problems are prevalent among university students, underscoring the need to improve access to effective interventions. Mental healthcare utilization is influenced by general and country-specific factors. This study aimed to identify and compare preferences and barriers to help-seeking for mental health problems among university students in three European countries. A cross-sectional, web-based survey was conducted with a sample of 4960 university students from Portugal (n = 3399), Germany (n = 680), and Sweden (n = 881). Depressive symptoms (9-item Patient Health Questionnaire) and overall mental health (5-item Mental Health Index) were assessed. Students responded to questions regarding help-seeking preferences for and barriers to mental health problems. Rates of moderate to severe depressive symptoms ranged from 37.5 to 51.0 % and were highest among German students. A majority (76.3-89.3 %) of students indicated they would talk to a friend in case of mental health problems. Readiness to seek help was particularly high among Portuguese students. Readiness to use internet-based interventions was low among all students. Up to 51 % of students reported uncertainty regarding where they could seek help. Students with depressive symptoms versus those without were less likely to speak with a friend about emotional problems but were more likely to consider taking medications. Students with depressive symptoms were also more likely to endorse several help-seeking barriers. Reducing structural barriers, improving awareness of treatment options and increasing acceptance of help-seeking for emotional problems may improve uptake of mental health services among students in these European countries.

Road traffic accidents (RTAs) are a problem with repercussions in several dimensions: social, economic, health, justice, and security. Data science plays an important role in its explanation and prediction. One of the main objectives of RTA data analysis is to identify the main factors associated with a RTA. The present study aims to contribute to the identification of the determinants for the type of RTA: collision, crash, or pedestrian running-over. These factors are essential for identifying specific countermeasures because there is a relevant relationship between the type of RTA and its severity. Daily RTA data from 2016 to 2019 in a district of Portugal were analyzed. A statistical multinomial logit model was fitted. The identified determinants for the type of RTA were geographical (municipality, location, and parking areas), meteorological (air temperature and weather), time of the day (hour, day of the week, and month), driver’s characteristics (gender and age), vehicle’s features (type and age) and road characteristics (road layout and type). The multinomial model results were compared with several machine learning algorithms, since the original data of the type of RTA are severely imbalanced. All models showed poor performance. However, when combining these models with ROSE for class balancing, their performance improved considerably, with the random forest algorithm showing the best performance.

Sleep disorders have significant health impacts and affect children’s performance and wellbeing. This study aims to characterise the sleep habits of Portuguese primary school children considering socioeconomic factors, daily lifestyle, presence of electronic devices in the bedrooms, and the practice of physical and sports activity (PSA) and to identify clinical factors that may be related to a child’s insufficient sleeping time. This study involved 1438 primary students. Sleep habits and problems were assessed using the short version of the Children’s Sleep Habits Questionnaire (CSHQ). The mean sleep duration was 9 h 37 min/ per night (SD = 44 min). The prevalence of global sleep disturbances was 25.8%. The main factors we identified to be positively associated with a child’s sleep deficit (i.e., <10 h) were: being older than 7 years, living further away from school, having electronic devices in the bedroom, going to bed and eating dinner later, less daily time of PSA, and having higher scores on the sleep duration subscales. Sleeping and eating habits, electronic devices in the bedroom, and a low level of engagement with PSA are associated with children’s sleep disturbance and shorter sleep duration.

The mental health of university students is a global concern, with high rates of depression and anxiety that need to be addressed. We aimed to compare the mental health of Portuguese, Swedish and German university students in the health and social sciences following the Covid-19 pandemic and to analyze the factors associated with depressive and anxious symptoms in each country. A cross-sectional study with a sample of students from Portugal, Germany and Sweden was conducted. Data from online questionnaires, including a sociodemographic and clinical questionnaire, the Patient Health Questionnaire (PHQ-9), the General Anxiety Disorder (GAD-7) and the MHI-5 (Mental Health Inventory) was collected from October to December 2022. The sample was composed of 1670 university students. The prevalence of mild to severe depressive symptoms was 72.7 % in Germany, 62.9 % in Sweden, and 60.3 % in Portugal and the prevalence of mild to severe anxiety symptoms was 78.6 % in Portugal, 73.7 % in Germany, and 66.9 % in Sweden. Being a female student, having a previous mental health disorder diagnosis, and poor academic performance were associated with higher severity of depression and anxiety symptoms in all three countries. Country-specific factors associated with more depressive and/or anxiety symptoms were younger age, smoking, low socioeconomic level and living away from home. Swedish students who do not consume alcohol had more anxiety symptoms and German students who do not consume alcohol had more depressive symptoms. The high prevalence of depressive and anxiety symptoms among students in the three countries highlights the need to address modifiable factors that contribute to this mental health burden. Our results, which are in line with international trends, underline the need for policy reforms that target the main determinants of mental health, in particular by improving socio-economic conditions. Addressing these factors could play a crucial role in improving mental health outcomes in this population.