Rapid detection of pea, soybean and chickpea protein in beef patties using chemometrics: comparing hand-held NIR and NIR hyperspectral imaging

Advanced, accurate and rapid technologies able to verify whether the products comply with food label claims are still required to avoid public health issues. The aim of this study was to evaluate the feasibility of point-based near infrared spectroscopy (NIRS) and hyperspectral imaging (HSI) to dete...

Descripción completa

Detalles Bibliográficos
Autores: León Ecay, Sara, López Maestresalas, Ainara, Arazuri Garín, Silvia, Insausti Barrenetxea, Kizkitza
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2026
País:España
Institución:Universidad Pública de Navarra
Repositorio:Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
OAI Identifier:oai:academica-e.unavarra.es:2454/55478
Acceso en línea:https://hdl.handle.net/2454/55478
Access Level:acceso abierto
Palabra clave:Vegetable protein
Meat label claims
Food fraud
Hyperspectral imaging
Near-infrared spectroscopy
Machine learning
Descripción
Sumario:Advanced, accurate and rapid technologies able to verify whether the products comply with food label claims are still required to avoid public health issues. The aim of this study was to evaluate the feasibility of point-based near infrared spectroscopy (NIRS) and hyperspectral imaging (HSI) to determine if hand-made prepared burger samples contained vegetable protein in accordance with the legal threshold (3 %) established by Spanish Royal Decree No. 474/2014. A total of 240 patties were fabricated, of which 60 contained pea (PP), 60 contained soybean (SP), and 60 chickpea protein (CP) at levels from 1 up to 6 % (w/w). 60 hamburgers of Pure beef were included. Excellent results were achieved for identifying the type of protein added, using either partial least squares-discriminant analysis (PLS-DA) or linear discriminant analysis (LDA), with >90 % of the samples in Test correctly classified. Based on protein inclusion, LDA discriminated 100 % of the PP, SP and CP samples in Test with both NIR and HSI. Indeed, PLS-DA classified 100 % of the PP and CP burgers using the NIR instrument. To manage double classification tasks, a hierarchical model classifier (HMC) was proposed for both NIR and HSI spectra, achieving classification rates ranging from 83.34 % up to 100 % in Test by combining LDA and PLS-DA models at the nodes. The results obtained in the study demonstrated the suitability of NIR spectroscopy in detecting low levels (1 %) of vegetable protein flours added to beef burgers and; therefore, contributing to the disclosure of fraudulent practices in labelling at the food industry.