Salt consumption is now much greater than needed for survival. High salt intake increases blood pressure in both animals and humans. Conversely, a reduction in salt intake causes a dose-dependent reduction in blood pressure in men and women of all ages and ethnic groups, and in patients already on medication. The risk of strokes and heart attacks rises with increasing blood pressure, and a reduction of blood pressure with drugs reduces the risk. However, most events occur in individuals with 'normal' blood pressure levels. Non-pharmacological prevention is therefore the only option to reduce such events in the population at large. Reduction in population salt intake reduces the number of vascular events. It is one of the most important public health measures to reduce the global cardiovascular burden. Salt reduction policies are feasible and effective (preventive imperative), cost-saving (economic imperative), powerful, rapid, equitable (political imperative) and life-saving (moral imperative). The World Health Organization recommends reducing salt consumption by 30% globally by 2025, aiming to reduce salt consumption to less than 5g per day, eventually.

The association between salt-related knowledge, attitude, behaviour (KAB) and actual salt consumption in Greek adults is uncertain. This study investigates the correlation between salt intake, gauged by 24-h urinary sodium excretion, with salt-related KAB. It further explores how socio-demographic factors influence these behaviors. Salt consumption was evaluated using a 24-h urinary sodium test, and compared to self-reported KAB data. Knowledge and behavior scores related to salt were computed. An overall cohort-adjusted model examined the relationship between daily salt consumption, knowledge and behavior scores, and certain covariates. Through the stratification by the cohort random effect, two models were established (Cohort I Adults; Cohort II Students) examining the same relationships of the overall cohort model. 463 Greek adults participated. The average salt intake was 9.54 g/day, nearly double the WHO recommendation. Significant differences in knowledge scores were noted based on sex, age, education, and BMI. A trend suggesting lower discretionary salt use with increased salt intake was observed (p = 0.06). However, comprehensive analysis revealed no direct correlation between salt intake and either knowledge (p = 0.562) or behavior scores (p = 0.210). The results emphasize the need for food product reforms by industry stakeholders and accelerated efforts towards reducing salt intake.

We introduce a new nonparametric framework for classification problems in the presence of missing data. The key aspect of our framework is that the regression function decomposes into an anova-type sum of orthogonal functions, of which some (or even many) may be zero. Working under a general missingness setting, which allows features to be missing not at random, our main goal is to derive the minimax rate for the excess risk in this problem. In addition to the decomposition property, the rate depends on parameters that control the tail behaviour of the marginal feature distributions, the smoothness of the regression function and a margin condition. The ambient data dimension does not appear in the minimax rate, which can therefore be faster than in the classical nonparametric setting. We further propose a new method, called the Hard-thresholding Anova Missing data (HAM) classifier, based on a careful combination of a k-nearest neighbour algorithm and a thresholding step. The HAM classifier attains the minimax rate up to polylogarithmic factors and numerical experiments further illustrate its utility.