Investigating sex differences in the accuracy of dietary assessment methods to measure energy intake in adults: a systematic review and meta-analysis

Background: To inform the interpretation of dietary data in the context of sex differences in diet-disease relations, it is important to understand whether there are any sex differences in accuracy of dietary reporting. Objective: To quantify sex differences in self-reported total energy intake (TEI) compared with a reference measure of total energy expenditure (TEE). Methods: Six electronic databases were systematically searched for published original research articles between 1980 and April 2020. Studies were included if they were conducted in adult populations with measures for both females and males of self-reported TEI and TEE from doubly labeled water (DLW). Studies were screened and quality assessed independently by 2 authors. Random-effects meta-analyses were conducted to pool the mean differences between TEI and TEE for, and between, females and males, by method of dietary assessment. Results: From 1313 identified studies, 31 met the inclusion criteria. The studies collectively included information on 4518 individuals (54% females). Dietary assessment methods included 24-h recalls (n = 12, 2 with supplemental photos of food items consumed), estimated food records (EFRs; n = 11), FFQs (n = 10), weighed food records (WFRs, n = 5), and diet histories (n = 2). Meta-analyses identified underestimation of TEI by females and males, ranging from -1318 LW (95% CI: -1967, -669) for FFQ to -2650 kJ/d (95% CI: -3492. -1807) for 24-h recalls for females, and from -1764 kJ/d (95% CI: -2285, -1242) for FFQ to -3438 kJ/d (95% CI: -5382. -1494) for WFR for males. There was no difference in the level of underestimation by sex, except when using EFR, for which males underestimated energy intake more than females (by 590 kJ/d, 95% CI: 35, 1.146). Conclusion: Substantial underestimation of TEI across a range of dietary assessment methods was identified, similar by sex. These underestimations should be considered when assessing TEI and interpreting diet-disease relations.