Exploring Moderators of the Effect of High vs. Low-to-Moderate Intensity Exercise on Cardiorespiratory Fitness During Breast Cancer Treatment - Analyses of a Subsample From the Phys-Can RCT

Abstract

Introduction: The results from the physical training and cancer randomized controlled trial (Phys-Can RCT) indicate that high intensity (HI) strength and endurance training during (neo-)adjuvant cancer treatment is more beneficial for cardiorespiratory fitness (CRF, measured as peak oxygen uptake [VO₂peak]) than low-to-moderate intensity (LMI) exercise. Adherence to the exercise intervention and demographic or clinical characteristics of patients with breast cancer undergoing adjuvant treatment may moderate the exercise intervention effect on VO₂peak. In this study, the objective was to investigate whether baseline values of VO₂peak, body mass index (BMI), time spent in moderate- to vigorous-intensity physical activity (MVPA), physical fatigue, age, chemotherapy treatment, and the adherence to the endurance training moderated the effect of HI vs. LMI exercise on VO₂peak.

Materials and methods: We used data collected from a subsample from the Phys-Can RCT; women who were diagnosed with breast cancer and had a valid baseline and post-intervention VO₂peak test were included (n = 255). The exercise interventions from the RCT included strength and endurance training at either LMI, which was continuous endurance training at 40-50% of heart rate reserve (HRR), or at HI, which was interval training at 80-90% of HRR, with similar exercise volume in the two groups. Linear regression analyses were used to investigate moderating effects using a significance level of p < 0.10. Statistically significant interactions were examined further using the Johnson-Neyman (J-N) technique and regions of significance (for continuous variables) or box plots with adjusted means of post-intervention VO₂peak (for binary variables).

Results: Age, as a continuous variable, and adherence, dichotomized into < or > 58% based on median, moderated the effect of HI vs. LMI on CRF (B = -0.08, 95% CI [-0.16, 0.01], p _interaction = 0.06, and B = 1.63, 95% CI [-0.12, 3.38], p _interaction = 0.07, respectively). The J-N technique and regions of significance indicated that the intervention effect (HI vs. LMI) was positive and statistically significant in participants aged 61 years or older. Baseline measurement of CRF, MVPA, BMI, physical fatigue, and chemotherapy treatment did not significantly moderate the intervention effect on CRF.

Conclusion: Women with breast cancer who are older and who have higher adherence to the exercise regimen may have larger effects of HI exercise during (neo-)adjuvant cancer treatment on CRF.

Keywords: age; breast cancer; cardiorespiratory fitness (CRF); endurance and strength training; exercise adherence; intensity; moderators.

Figure 1

The hypothesized moderation model. Intervention effect (mean difference in change between low-to-moderate intensity (LMI) and high intensity (HI) training) on peakimal oxygen uptake (VO₂peak) post-intervention. The potential moderator variables investigated were baseline age, body mass index (BMI), cardiorespiratory fitness (CRF), hours in moderate-to-vigorous physical activity (MVPA), physical fatigue, chemotherapy treatment (yes/no), and adherence to the endurance training. Each of the potential moderator variables was included in the regression model one at a time, resulting in a total of seven models.

Figure 2

Johnson–Neyman plot showing the simple slope (with the 95% confidence intervals) of age on exercise intensity on post-intervention VO₂peak. Colored area represents the region of significance (p < 0.05).

Figure 3

VO₂peak post-intervention below and over the age cutoff (61 years), presented within the two intensity groups LMI (blue triangle) and HI (red squares). Means are adjusted for VO₂peak at baseline and study site is included as covariate.

Figure 4

VO₂peak post-intervention below and over median adherence to the endurance training (58%), presented within the two intensity groups LMI (blue triangle) and HI (red squares). Means are adjusted for VO₂peak at baseline and study site is included as covariate. * = p < 0.01.