New article in Current Research in Food Science

A new publication from Tarini Naravane and Dr. Ilias Tagkopoulos about Machine learning models to predict micronutrient profile in food after processing.

Abstract: The information on nutritional profile of cooked foods is important to both food manufacturers and consumers, and a major challenge to obtaining precise information is the inherent variation in the composition of the raw ingredients. The ideal solution would address precision across the diversity of foods, but the current solutions are limited in their capabilities; analytical methods are too costly to scale, retention-factor based methods are scalable but approximate, and kinetic models are bespoke to a food and nutrient. We provide an alternate solution that predicts the micronutrient profile in cooked food from the raw food composition, and for multiple foods. The prediction model is trained on an existing food composition dataset and has a 31% lower error on average (across all foods, processes and nutrients) than predictions obtained using the baseline method of retention-factors. Significant to performance improvement, was the scaling of the data prior to model training, which mitigated the yield bias introduced by the representation of composition per 100g of food whether raw or cooked. This study shows the potential of machine learning methods over current solutions, and additionally provides guidance for the future generation of food composition data, specifically for sampling approach, data quality checks, and data representation standards.

Reference: Naravane, Tarini, and Ilias Tagkopoulos. “Machine learning models to predict micronutrient profile in food after processing.” Current Research in Food Science (2023): 100500. doi: 10.1016/j.crfs.2023.100500 (link)