Combined impact of traditional and non-traditional health behaviors on mortality: a national prospective cohort study in Spanish older adults

Abstract

Background: Data on the combined effect of lifestyles on mortality in older people have generally been collected from highly selected populations and have been limited to traditional health behaviors. In this study, we examined the combined impact of three traditional (smoking, physical activity and diet) and three non-traditional health behaviors (sleep duration, sedentary time and social interaction) on mortality among older adults.

Methods: A cohort of 3,465 individuals, representative of the Spanish population aged ≥60 years, was established in 2000/2001 and followed-up prospectively through 2011. At baseline, the following positive behaviors were self-reported: never smoking or quitting tobacco >15 years, being very or moderately physically active, having a healthy diet score ≥ median in the cohort, sleeping 7 to 8 h/d, spending <8 h/d in sitting time, and seeing friends daily. Analyses were performed with Cox regression and adjusted for the main confounders.

Results: During an average nine-year follow-up, 1,244 persons died. Hazard ratios (95% confidence interval) for all-cause mortality among participants with two, three, four, five and six compared to those with zero to one positive behaviors were, respectively, 0.63 (0.46 to 0.85), 0.41 (0.31 to 0.55), 0.32 (0.24 to 0.42), 0.26 (0.20 to 0.35) and 0.20 (0.15 to 0.28) (P for trend <0.001). The results were similar regardless of age, sex and health status at baseline. Those with six vs. zero to one positive health behaviors had an all-cause mortality risk equivalent to being 14 years younger. Adding the three non-traditional to the four traditional behaviors improved the model fit (likelihood ratio test, P <0.001) and the accuracy of mortality prediction (c-statistic: + 0.0031, P = 0.040).

Conclusions: Adherence to some traditional and non-traditional health behaviors may substantially reduce mortality risk in older adults.

Figure 1

Survival function according to number of traditional and non-traditional health behaviors in Spanish older adults. Survival function adjusted for age (years), sex (men, women), educational attainment (no education, primary, secondary or higher), body mass index (kg/m²), waist circumference (cm), systolic blood pressure (mm Hg), hypercholesterolemia status (yes, no), alcohol intake (g/d), former drinker (yes, no), extreme sleep durations (yes, no), occupational status (employed, unemployed, retired, househusband/housewife), and history of coronary heart disease (yes, no), stroke (yes, no), diabetes mellitus (yes, no), hip fracture (yes, no), and cancer (yes, no).