Development and validation of criteria for determining undernutrition in community-dwelling older men and women: The Short Nutritional Assessment Questionnaire 65+

Abstract

Background & aims: There is no valid, fast and easy-to-apply set of criteria to determine (risk of) undernutrition in community-dwelling older persons. The aim of this study was to develop and validate such criteria.

Methods: Selection of potential anthropometric and undernutrition-related items was based on consensus literature. The criteria were developed using 15-year mortality in community-dwelling older persons ≥ 65 years (Longitudinal Aging Study Amsterdam, n = 1687) and validated in an independent sample (InCHIANTI, n = 1142).

Results: Groups distinguished were: (1) undernutrition (mid-upper arm circumference <25 cm or involuntary weight loss ≥4 kg/6 months); (2) risk of undernutrition (poor appetite and difficulties climbing staircase); and (3) no undernutrition (others). Respective hazard ratio's for 15-year mortality were: (1) 2.22 (95% CI 1.83-2.69); and (2) 1.57 (1.22-2.01) ((3) = reference). The area under the curve (AUC) was 0.55. Comparable results were found stratified by sex, excluding cancer/obstructive lung disease/(past) smoking, using 6-year mortality, and applying results to the InCHIANTI study (hazard ratio's 2.12 and 2.46, AUC 0.59).

Conclusions: The developed set of criteria (SNAQ⁶⁵⁺) for determining (risk of) undernutrition in community-dwelling older persons shows good face validity and moderate predictive validity based on the consistent association with mortality in a second independent study sample.

Fig. 1.

Classification tree for predicting 15-year mortality risk in community-dwelling older persons by undernutrition-related-items, developed in LASA. The end nodes are indicated by squares including roman numerals to indicate the emerging groups (I–V) and the intermediate nodes by circles. Both contain the group size (top number), the number of deaths (middle number), and the proportion of deaths at the end of the 15- year follow-up (bottom number). The split variable is shown on the resulting branches.

Fig. 2.

Kaplan—Meier curves for predicting 15-year mortality in community-dwelling older persons in the LASA study by 5 groups based on the 5 end nodes of the developed classification tree depicted in Fig. 1. Groups I, II, and III had a statistically significantly poorer survival (p < 0.01) compared to group V.

Fig. 3.

Kaplan—Meier curves for predicting 6-year mortality in community-dwelling older persons in the LASA and InCHIANTI study by 5 groups based on the 5 end nodes of the developed classification tree depicted in Fig. 1. Groups I, II, and III had a statistically significantly poorer survival (p < 0.05) compared to group V.