Monitoring population salt intake using casual urinary sodium: Tehran Lipid and Glucose Study

Abstract

Background: We aimed to estimate salt intake among an Iranian population using spot urine-based equations and a dietary-based method.

Methods: Adult men and women (n = 2069) were recruited from the Tehran Lipid and Glucose Study (2014-2017). Urinary sodium (Na), potassium (K), and creatinine (Cr) concentrations were measured in the morning spot urine samples. The 24-h urinary Na excretion and predicted salt intake was estimated using five equations, i.e., Kawasaki, Tanaka, Intersalt, Toft, and Whitton. A validated food frequency questionnaire (FFQ) was used to obtain dietary intake of salt. The agreement of each urinary- and FFQ-based salt estimation with the overall mean of the methods, considered as the gold standard, was assessed using the Bland-Altman method.

Results: Mean age of the participants was 45.6 ± 14.8 y, and 45.4% were men. Mean (SD) estimated salt intake, derived from the overall mean of the methods, was 9.0 ± 2.2 g/d (10.2 ± 2.1 and 7.9 ± 1.7 g/d in men and women, respectively). Mean bias of the estimations from the overall mean ranged from - 0.2.42 to 2.75 g/d, with the Tanaka equation having the least bias (mean bias = 0.13 ± 1.10, 95% CI - 2.37, 2.30 g/d). Tanaka estimated a mean salt intake of 8.9 g/d (range 2.1 to 18.7 g/d); accordingly, only 5.1% of participants adhered to the recommendation (< 5 g/d salt intake), whereas 26.8% and 2.4% exceeded the recommendation by 2- and threefold.

Conclusion: The Tanaka equation could provide a more accurate mean-population estimated salt intake from casual urinary Na concentration in our population. About 95% of the Iranian population exceeded the current recommendations of salt intake.

Keywords: Casual urinary sodium; Estimated population-salt intake; Tanaka equation.

Fig. 1

Mean bias, SD and 95% CI of each method compared to the gold-estimated salt intake (derived from the average of all methods), along with the slope and intercept for bias of each estimation vs. overall mean of 6 estimations