期刊名称：Proceedings of the National Academy of Sciences
印刷版ISSN：0027-8424
电子版ISSN：1091-6490
出版年度：2020
卷号：117
期号：28
页码：16273-16282
DOI：10.1073/pnas.1918455117
出版社：The National Academy of Sciences of the United States of America
摘要：Behavioral and social scientists have identified many nonbiological predictors of mortality. An important limitation of much of this research, however, is that risk factors are not studied in comparison with one another or from across different fields of research. It therefore remains unclear which factors should be prioritized for interventions and policy to reduce mortality risk. In the current investigation, we compare 57 factors within a multidisciplinary framework. These include ( i ) adverse socioeconomic and psychosocial experiences during childhood and ( ii ) socioeconomic conditions, ( iii ) health behaviors, ( iv ) social connections, ( v ) psychological characteristics, and ( vi ) adverse experiences during adulthood. The current prospective cohort investigation with 13,611 adults from 52 to 104 y of age (mean age 69.3 y) from the nationally representative Health and Retirement Study used weighted traditional (i.e., multivariate Cox regressions) and machine-learning (i.e., lasso, random forest analysis) statistical approaches to identify the leading predictors of mortality over 6 y of follow-up time. We demonstrate that, in addition to the well-established behavioral risk factors of smoking, alcohol abuse, and lack of physical activity, economic (e.g., recent financial difficulties, unemployment history), social (e.g., childhood adversity, divorce history), and psychological (e.g., negative affectivity) factors were also among the strongest predictors of mortality among older American adults. The strength of these predictors should be used to guide future transdisciplinary investigations and intervention studies across the fields of epidemiology, psychology, sociology, economics, and medicine to understand how changes in these factors alter individual mortality risk.
关键词：mortality ; transdisciplinary ; social ; behavioral ; data-driven
