Search

Background Populational ageing has been increasing in a remarkable rate in developing countries. In this scenario, preventive strategies could help to decrease the burden of higher demands for healthcare services. Machine learning algorithms have been increasingly applied for identifying priority candidates for preventive actions, presenting a better predictive performance than traditional parsimonious models. Methods Data were collected from the Health, Well Being and Aging (SABE) Study, a representative sample of older residents of São Paulo, Brazil. Machine learning algorithms were applied to predict death by diseases of respiratory system (DRS), diseases of circulatory system (DCS), neoplasms and other specific causes within 5 years, using socioeconomic, demographic and health features. The algorithms were trained in a random sample of 70% of subjects, and then tested in the other 30% unseen data. Results The outcome with highest predictive performance was death by DRS (AUC−ROC = 0.89), followed by the other specific causes (AUC−ROC = 0.87), DCS (AUC−ROC = 0.67) and neoplasms (AUC−ROC = 0.52). Among only the 25% of individuals with the highest predicted risk of mortality from DRS were included 100% of the actual cases. The machine learning algorithms with the highest predictive performance were light gradient boosted machine and extreme gradient boosting. Conclusion The algorithms had a high predictive performance for DRS, but lower for DCS and neoplasms. Mortality prediction with machine learning can improve clinical decisions especially regarding targeted preventive measures for older individuals. [ABSTRACT FROM AUTHOR]

Objective: To assess the use of male condoms and dual protection by Brazilian adolescent men, as well as their associated aspects., Methods: A database from the Study of Cardiovascular Risks in Adolescents (ERICA) was used for this national cross-sectiotabelnal school-based research. The sample included adolescents of both sexes, aged between 12 and 17 years old, selected through cluster sampling in 2014 (n = 75,060). This study analyzed information from adolescent men who reported having had sexual intercourse (n = 12,215). The dependent variables were the use of male condoms and the use of dual protection (simultaneous use of male condoms and oral hormonal contraceptives) in the last sexual intercourse. Data were analyzed using univariate and multiple logistic regression., Results: Most adolescents used a male condom in the last sexual intercourse, while the use of double protection was quite low. The use of male condoms, reported by 71% (95%CI 68.7-73.1), was positively associated with age, living with both parents, and having used alcohol in the previous 30 days. The use of double protection, reported by 3.6% (95%CI 2.8-4.5) was positively associated with age and studying in a private school, as well as negatively associated with tobacco use in the previous 30 days., Conclusions: The wide difference shown in the proportion of condom or dual protection use in the last sexual intercourse draws attention to the different logics that govern juvenile sexual relations. The low proportion of dual protection use may be a reflection of men's lack of knowledge about a function that has historically been attributed to women, which is contraception. Thus, one must deconstruct such dichotomy that the sphere of sexuality is of the domain/interest of men, while that of reproduction concerns only women.