Validity of self-reported and objectively measured sedentary behavior in pregnancy

Abstract

Background: Sedentary behavior (SED) is a potential risk factor for poor pregnancy outcomes. We evaluated the validity of several common and one new method to assess SED across three trimesters of pregnancy.

Methods: This cohort study of pregnant women measured objective and self-reported SED each trimester via thigh-worn activPAL3 micro (criterion), waist-worn Actigraph GT3X, and self-report from the Pregnancy Physical Activity Questionnaire (PPAQ) and the de novo Sedentary Behavior Two Domain Questionnaire (SB2D). SED (hours per day) and percent time in SED (SED%) from activPAL were compared to GT3X, SB2D, and PPAQ using Pearson's r, ICC, Bland-Altman analysis, and comparison of criterion SED and SED% across tertiles of alternative methods.

Results: Fifty-eight women (mean age 31.5 ± 4.8 years; pre-pregnancy BMI 25.1 ± 5.6 kg/m²; 76% white) provided three trimesters of valid activPAL data. Compared to activPAL, GT3X had agreement ranging from r = 0.54-0.66 and ICC = 0.52-0.65. Bland-Altman plots revealed small mean differences and unpatterned errors, but wide limits of agreement (greater than ±2 h and ± 15%). The SB2D and PPAQ had r < 0.5 and ICC < 0.3 vs. activPAL SED, with lower agreement during the 2nd and 3rd trimesters, and performed poorly in Bland-Altman analyses. SED% from the modified SB2D performed best of the self-reported instruments with modest mean differences, r ranging from 0.55 to 0.60, and ICCs from 0.31-0.33; though, limits of agreement were greater than ±35%. Significant trends in activPAL SED were observed across increasing tertiles of SB2D SED in the 1st and 3rd trimesters (both p ≤ 0.001), but not the 2nd trimester (p = 0.425); and for PPAQ SED in the 1st and 2nd trimesters (both p < 0.05), but not the 3rd trimester (p = 0.158). AcitvPAL SED and SED% increased significantly across tertiles of GT3X SED and SED% as well as SB2D SED% (all p-for-trend ≤ 0.001).

Conclusions: Compared to activPAL, waist-worn GT3X produced moderate agreement, though similar mean estimates of SED across pregnancy. Self-report questionnaires had large absolute error and wide limits of agreement for SED hr./day; SB2D measurement of SED% was the best self-report method. These data suggest activPAL be used to measure SED when possible, followed by GT3X, and - when necessary - SB2D assessing SED% in pregnancy.

Trial registration: www.clinicaltrials.gov NCT03084302 on 3/20/2017.

Keywords: Accelerometer; Sedentary time; Self-report questionnaire; Trimester; activPAL.

Fig. 1

Bland-Altman Plots comparing Sedentary Behavior assessed by Waist-worn monitor (Actigraph GT3X) versus Thigh-worn monitor (activPAL3 micro) across Pregnancy Trimesters

Fig. 2

Bland-Altman Plots comparing Sedentary Behavior assessed by the Sedentary Behavior Two Domain Questionnaire (SB2D) versus Thigh-worn monitor (activPAL3 micro) across Pregnancy Trimesters

Fig. 3

Bland-Altman Plots comparing Sedentary Behavior assessed by the Pregnancy Physical Activity Questionnaire versus Thigh-worn monitor (activPAL3 micro) across Pregnancy Trimesters