Correlates of metabolic syndrome in people with chronic spinal cord injury

Abstract

Purpose: We aimed at identifying clinical risk factors or early markers of metabolic syndrome (MetS) in people with spinal cord injury (SCI) that would facilitate a timely diagnosis and implementation of preventive/therapeutic strategies.

Methods: One hundred sixty-eight individuals with chronic (> 1 year) SCI underwent clinical and biochemical evaluations. MetS was diagnosed according to modified criteria of the International Diabetes Federation validated in people with SCI. Wilcoxon rank-sum test and χ² test were used to compare variables between groups with and without MetS. Multiple logistic regression analysis was performed to reveal independent associations with MetS among variables selected by univariate linear regression analyses.

Results: MetS was diagnosed in 56 of 132 men (42.4%) and 17 of 36 women (47.2%). At univariate regression analyses, putative predictors of MetS were an older age, a higher number of comorbidities, a lower insulin-sensitivity, the presence and intensity of pain, a shorter injury duration, a poorer leisure time physical activity (LTPA) and an incomplete motor injury. At the multiple logistic regression analysis, a significant independent association with MetS only persisted for a poorer LTPA in hours/week (OR: 0.880, 95% CI 0.770, 0.990) and more severe pain symptoms as assessed by the numeral rating scale (OR: 1.353, 95% CI 1.085, 1.793).

Conclusion: In people with chronic SCI, intense pain symptoms and poor LTPA may indicate a high likelihood of MetS, regardless of age, SCI duration, motor disability degree, insulin-sensitivity and comorbidities.

Keywords: Cardiovascular risk; Insulin resistance; Obesity; Pain; Paraplegia; Physical activity.

Fig.1

Prevalence of metabolic syndrome (MetS) by A pain intensity quantified in tertiles of increasing numeral rating scale (NRS) score and B weekly leisure time physical activity (LTPA). Statistical significance for differences among groups of NRS scores, obtained by categorizing data into tertiles: χ² test for trend = 7.46, p = 0.02; Statistical significance for differences among groups of LTPA, obtained by categorizing data into tertiles: χ² test for trend = 9.53, p = 0.008)