Using an interactive nutrition technology platform to predict malnutrition risk

Abstract

Background The Nutrition Dashboard is an interactive nutrition technology platform that displays food provision and intake data used to categorise the nutrition risk of hospitalised individuals. The present study aimed to investigate the Nutrition Dashboard's ability to identify malnutrition compared with a validated malnutrition screening tool (MST). Methods A retrospective observational study at a 99‐bed hospital was conducted using medical record and food intake data presented via the Nutrition Dashboard. Inter‐Rater Reliability of food intake estimation between hospital catering staff and a dietitian reported good agreement across 912 food items (κ = 0.69, 95% confidence interval = 0.65–0.72, p < 0.001). Default nutritional adequacy thresholds of 4500 kJ and 50 g protein were applied for Nutrition Dashboard categorisation of supply and intake. Generalised estimating equation regression models explored the association between the Nutrition Dashboard risk categories and the MST, with and without controlling for patient demographic characteristics. Results Analyses from 216 individuals (1783 hospital‐stay days) found that those in the highest risk Nutrition Dashboard category were 1.93 times more likely to have a MST score indicating risk compared to the lowest Nutrition Dashboard category (unadjusted odds ratio = 1.93, 95% confidence interval = 1.17–3.19, p < 0.01). When patient weight was added to the model, lower weight became the only significant predictor of MST ≥ 2 (p < 0.01) Conclusions The present study indicates a role for nutrition intake technology in malnutrition screening. Further adaptions that address the complexities of applying this technology could improve the use of the Nutrition Dashboard to support identification of malnutrition.