Hyperspectral imaging as a non-destructive technique for estimating the nutritional value of food

• Published in: Current research in food science 2024-01, Vol.9, p.100799, Article 100799
• Main Authors: Marín-Méndez, Juan-Jesús, Luri Esplandiú, Paula, Alonso-Santamaría, Miriam, Remirez-Moreno, Berta, Urtasun Del Castillo, Leyre, Echavarri Dublán, Jaione, Almiron-Roig, Eva, Sáiz-Abajo, María-José
• Format: Article
• Language: English
• Subjects: Chemometrics; Hyperspectral imaging; Machine learning; Nutritional value; Review; Ridge regression
• ISSN: 2665-9271; 2665-9271
• DOI: 10.1016/j.crfs.2024.100799

Knowledge of the energy and macronutrient content of complex foods is essential for the food industry and to implement population-based dietary guidelines. However, conventional methodologies are time-consuming, require the use of chemical products and the sample cannot be recovered. We hypothesize that the nutritional value of heterogeneous food products can be readily measured instead by using hyperspectral imaging systems (NIR and VIS-NIR) combined with mathematical models previously fitted with spectral profiles.118 samples from different food products were collected for building the predictive models using their hyperspectral imaging data as predictors and their nutritional values as dependent variables. Ten different models were screened (Multivariate Linear regression, Lasso regression, Rigde regression, Elastic Net regression, K-Neighbors regression, Decision trees regression, Partial Least Square, Support Vector Machines, Gradient Boosting regression and Random Forest regression). The best results were obtained with Ridge regression for all parameters. The best performance was for estimating the protein content with a RMSE of 1.02 and a R2 equal to 0.88 in a test set, following by moisture (RMSE of 2.21 and R2 equal to 0.85), energy value (RMSE of 21.84 and R2 equal to 0.76) and total fat (RMSE of 2.17 and R2 equal to 0.72). The performance with carbohydrates (RMSE of 2.12 and R2 equal to 0.61) and ashes (RMSE of 0.25 and R2 equal to 0.38) was worse. This study shows that it is possible to predict the energy and nutrient values of processed complex foods, using hyperspectral imaging systems combined with supervised machine learning methods. [Display omitted] •HSI with ML, is an accurate and rapid technique for estimations of food composition.•This is the first study using HSI for complex food products composition assessment.•HSI allows complex food products to be scanned directly without homogenization.•NIR with ML have great performance predicting energetic values and protein content.•NIR has a better performance predicting nutritional values than VIS-NIR.