Coleção de Artigos Acadêmicos
URI permanente para esta coleçãohttps://repositorio.insper.edu.br/handle/11224/3227
Navegar
2 resultados
Resultados da Pesquisa
Artigo Científico Cause-specific mortality prediction in older residents of São Paulo, Brazil: a machine learning approach(2021) Nascimento, Carla Ferreira do; Hellen Geremias dos Santos; ANDRE FILIPE DE MORAES BATISTA; Lay, Alejandra Andrea Roman; Duarte, Yeda Aparecida OliveiraBackground: 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.Artigo Científico Loss of life expectancy from PM2.5 in Brazil: A national study from 2010 to 2018(2022) Yu, Pei; Xu, Rongbin; Li, Shanshan; Coelho, Micheline S. Z. S.; Saldiva, Paulo H. N.; Sim, Malcolm R.; Abramson, Michael J.; Guo, YumingBackground Long-term exposure to PM2.5 is proved to be linked with mortality. However, limited studies have estimated the PM2.5 related loss of life expectancy (LLE) and its changing trends. How much life expectancy would be improved if PM2.5 pollution is reduced to the new WHO air quality guideline (AQG) level is unclear. Methods Data on deaths from all-causes, cancer, cardiovascular and respiratory diseases were collected from 5,565 Brazilian municipalities during 2010–2018. A difference-in-differences approach with quasi-Poisson regression was applied to examine the PM2.5-years of life lost (YLL) associations and PM2.5 associated LLE. Results The annual PM2.5 concentration in each municipality from 2010 to 2018 was 7.7 µg/m3 in Brazil. Nationally, with each 10 μg/m3 increase in five-year-average (current and previous four years) concentrations of PM2.5, the relative risks (RRs) were 1.18 (95% CI: 1.15–1.21) for YLL from all-causes, 1.22 (1.16–1.28) from cancer, 1.12 (1.08–1.17) from cardiovascular and 1.17 (1.10–1.25) from respiratory diseases. Life expectancy could be improved by 1.09 (95% CI: 0.92–1.25) years by limiting PM2.5 concentration to the national lowest level (2.9 µg/m3), specifically, 0.20 (0.15–0.24) years for cancer, 0.16 (0.11–0.22) years for cardiovascular and 0.09 (0.05–0.13) years for respiratory diseases, with significant disparities across regions and municipalities. Life expectancy would be improved by 0.78 (0.66–0.90) years by setting the new WHO AQG PM2.5 concentration level of 5 μg/m3 as an acceptable threshold. Conclusions Using nationwide death records in Brazil, we found that long-term exposure to PM2.5 was associated with reduced life expectancy from all-causes, cancer, cardiovascular and respiratory diseases with regional inequalities and different trends. PM2.5 pollution abatement to below the WHO AQG level would improve this loss of life expectancy in Brazil.