Determinants of lifestyle behavior change to prevent type 2 diabetes in high-risk individuals

Abstract

Background: Although there are many effective lifestyle interventions for type 2 diabetes (T2DM) prevention, insight into effective intervention pathways, especially of long-term interventions, is often lacking. This study aims to provide insight into the effective intervention pathways of the SLIMMER diabetes prevention intervention using mediation analyses.

Methods: In total, 240 participants at increased risk of T2DM were included in the analyses over 18 months. The intervention was a combined lifestyle intervention with a dietary and a physical activity (PA) component. The primary and secondary outcomes were change in fasting insulin (pmol/L) and change in body weight (kg) after 18 months, respectively. Firstly, in a multiple mediator model, we investigated whether significant changes in these outcomes were mediated by changes in dietary and PA behavior. Secondly, in multiple single mediator models, we investigated whether changes in dietary and PA behavior were mediated by changes in behavioral determinants and the participants' psychological profile. The mediation analyses used linear regression models, where significance of indirect effects was calculated with bootstrapping.

Results: The effect of the intervention on decreased fasting insulin was 40% mediated by change in dietary and PA behavior, where dietary behavior was an independent mediator of the association (34%). The effect of the intervention on decreased body weight was 20% mediated by change in dietary and PA behavior, where PA behavior was an independent mediator (17%). The intervention significantly changed intake of fruit, fat from bread spread, and fiber from bread. Change in fruit intake was mediated by change in action control (combination of consciousness, self-control, and effort), motivation, self-efficacy, intention, and skills. Change in fat intake was mediated by change in action control and psychological profile. No mediators could be identified for change in fiber intake. The change in PA behavior was mediated by change in action control, motivation, and psychological profile.

Conclusion: The effect of the SLIMMER intervention on fasting insulin and body weight was mediated by changes in dietary and PA behavior, in distinct ways. These results indicate that changing dietary as well as PA behavior is important in T2DM prevention.

Trial registration: ClinicalTrials.gov NCT02094911.

Keywords: Behavioral determinants; Lifestyle intervention; Mediation; Prevention; Primary healthcare; Type 2 Diabetes Mellitus.

Fig. 1

Flow chart

Fig. 2

Causal model of SLIMMER intervention

Fig. 3

Multiple mediator model for intervention effect via dietary and physical activity behavior. The a₁ path represents the association between intervention and NBS index. B₁ represents the association between NBS index and outcome (y), corrected for intervention. A₂ and b₂ are interpreted similarly. The c path represents the crude association between intervention and outcome. C′ represents the association between intervention and outcome corrected for NBS and PA

Fig. 4

Single mediator models for intervention effect on health behavior (y) via behavioral determinants (m). Path a represents the association between intervention (x) and individual behavioral determinants (m). Path b represents the relation between individual behavior determinants (m) and dietary/PA behaviors (y). C path represents the crude association of the intervention (x) on each of the health behaviors (y). C′ path represents the association between intervention (x) and a health behavior (y) corrected for behavioral determinant (m)