Semiparametric modeling for the cardiometabolic risk index and individual risk factors in the older adult population: A novel proposal

Abstract

The accurate monitoring of metabolic syndrome in older adults is relevant in terms of its early detection, and its management. This study aimed at proposing a novel semiparametric modeling for a cardiometabolic risk index (CMRI) and individual risk factors in older adults.

Methods: Multivariate semiparametric regression models were used to study the associa- tion between the CMRI with the individual risk factors, which was achieved using secondary

analysis the data from the SABE study (Survey on Health, Well-Being, and Aging in Colom- bia, 2015). Results: The risk factors were selected through a stepwise procedure. The

covariates included showed evidence of non-linear relationships with the CMRI, revealing non-linear interactions between: BMI and age (p< 0.00); arm and calf circumferences

(p<0.00); age and females (p<0.00); walking speed and joint pain (p<0.02); and arm circum- ference and joint pain (p<0.00). Conclusions: Semiparametric modeling explained 24.5% of

the observed deviance, which was higher than the 18.2% explained by the linear model.