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.

Purpose: This study examined the effect of the type, level and amount of physical activity in falls and fall-related injuries. Method: Participants were 506 community-dwelling adults aged >50 years (390 women: 67.7 ± 6.8 years and 116 men: 69.6 ± 6.6 years). Falls, fall-related injuries (slight and severe), and physical activity (type, level and energy expenditure) were evaluated by questionnaires. Confounders included co-morbidities, fear of falling, environmental hazards and physical fitness. Results: After adjustment for confounders, logistic analysis revealed that the likelihood of falling decreased by 2% for each 100 metabolic expenditure (MET-min/week) of total physical activity and increased by 5% for each 100 MET-min/week of vigorous-intensity physical activity; total physical activity >1125 MET-min/week and vigorous physical activity <500 MET-min/week were identified as cut-off values discriminating non-fallers from fallers. Compared to the low physical activity level, increased physical activity levels diminished the likelihood of the occurrence of severe fall-related injuries by 76% (moderate) and 58% (high; p < 0.05) in fallers. Conclusions: Being active, especially sufficiently active, reduces fall-related injuries by decreasing falls and by safeguarding against severe injuries when falls occur. At least 1125 MET-min/week of total physical activity including >500 MET-min/week of vigorous intensity seems to prevent falls and, therefore, fall-related injuries.

Objective The aim of this study was to analyze the contribution of sex to the occurrence of falls, accounting for comorbidities and differences in physical fitness. Design This was a cross-sectional study of 587 community-dwelling adults who were older than 50 yrs. Falls, comorbidities (number of diseases and physical impairments), and physical fitness (body composition, lower and upper body strength and flexibility, agility, aerobic endurance, and balance) were evaluated via questionnaires, bioimpedance, and Fullerton batteries, respectively. Results Compared with the men, the women presented a 10% higher fall prevalence, 1.7 more diseases/impairments, 10% more body fat, 26% less lean body mass, and poorer physical capacity (P < 0.05). Multivariate logistic regression revealed that male sex (odds ratio [OR], 2.723; 95% confidence interval [CI], 1.190–6.230) increased the likelihood of falling, after adjustment for comorbidities (OR, 1.213; 95% CI, 1.109–1.328), lean mass (OR, 0.958; 95% CI, 0.927–0.989), fat mass (OR, 1.053; 95% CI, 1.021–1.086), and balance (OR, 0.942; 95% CI, 0.914–0.971), which were the main risk factors of falls. Conclusions Women are more susceptible to falling, presumably because they have poorer health and physical fitness than do men. However, when the values for comorbidities, lean and fat body mass, and balance were similar, the men demonstrated a higher probability of falling. Age is not a significant risk factor of falls under favorable conditions of health, body composition, and balance.