Comprehensive Quality Analysis of an Organic Alternative Curing Process in Boneless Ham Using Consumer Sensory Evaluation and Artificial Intelligence

United States regulators and the meat industry have recently called for a shift from conventional natural curing ingredients to organic alternatives. However, the curing efficacy and consumer acceptance of these organic options remain unclear. Fully cooked, water-added boneless ham served as the model for assessing these ingredients in this study. The study evaluated the effects of commercial conventional and organic plant-sourced curing agents on ham quality using sensory evaluation, instrumental analysis, machine learning, and natural language processing (NLP). Five treatments were analyzed: pre-converted celery (CEL), organic celery (OCEL), Swiss chard (SW), organic Swiss chard (OSW), and sodium nitrite (SN). Consumer panels indicated no differences ( p  > 0.05) in overall liking or purchase intent across treatments. However, OSW exhibited a greater non-meat aftertaste compared to SW ( p  = 0.013) and SN ( p  = 0.033). Traditional statistical methods such as principal component analysis (PCA) and correlation studies revealed that non-meat aftertaste was positively correlated ( r  = 0.61) with terpenoids and negatively correlated ( r = -0.53) with esters, furans, and sulfur-containing compounds. Novel artificial intelligence tools such as machine learning classification of objective color measurements identified the 650/570 nm absorbance ratio as a key differentiating feature across treatments. Furthermore, NLP analysis of open-ended comments identified structured themes, where 'aftertaste/off note' language showed a significant association with lower overall liking. These findings demonstrate the value of integrating advanced data analytics with traditional meat science methodology.