Artificial Intelligence Sensing: Effective Flavor Blueprinting of Tea Infusions for a Quality Control Perspective.

Tea infusions are the most consumed beverages in the world after water; their pleasant yet peculiar flavor profile drives consumer choice and acceptance and becomes a fundamental benchmark for the industry. Any qualification method capable of objectifying the product's sensory features effectively supports industrial quality control laboratories in guaranteeing high sample throughputs even without human panel intervention. The current study presents an integrated analytical strategy acting as an Artificial Intelligence decision tool for black tea infusion aroma and taste blueprinting. Key markers validated by sensomics are accurately quantified in a wide dynamic range of concentrations. Thirteen key aromas are quantitatively assessed by standard addition with in-solution solid-phase microextraction sampling followed by GC-MS. On the other hand, nineteen key taste and quality markers are quantified by external standard calibration and LC-UV/DAD. The large dynamic range of concentration for sensory markers is reflected in the selection of seven high-quality teas from different geographical areas (Ceylon, Darjeeling Testa Valley and Castleton, Assam, Yunnan, Azores, and Kenya). The strategy as a sensomics-based expert system predicts teas' sensory features and acts as an AI smelling and taste machine suitable for quality controls.

Enhancing breast cancer screening with urinary biomarkers and Random Forest supervised classification: A comprehensive investigation.

OBJECTIVES: Urinary sex hormones are investigated as potential biomarkers for the early detection of breast cancer, aiming to evaluate their relevance and applicability, in combination with supervised machine-learning data analysis, toward the ultimate goal of extensive screening. METHODS: Sex hormones were determined on urine samples collected from 250 post-menopausal women (65 healthy - 185 with breast cancer, recruited among the clinical patients of Candiolo Cancer Institute FPO-IRCCS (Torino, Italy). Two analytical procedures based on UHPLC-MS/HRMS were developed and comprehensively validated to quantify 20 free and conjugated sex hormones from urine samples. The quantitative data were processed by seven machine learning algorithms. The efficiency of the resulting models was compared. RESULTS: Among the tested models aimed to relate urinary estrogen and androgen levels and the occurrence of breast cancer, Random Forest (RF) proved to underscore all the other supervised classification approaches, including Partial Least Squares - Discriminant Analysis (PLS-DA), in terms of effectiveness and robustness. The final optimized model built on only five biomarkers (testosterone-sulphate, alpha-estradiol, 4-methoxyestradiol, DHEA-sulphate, and epitestosterone-sulphate) achieved an approximate 98% diagnostic accuracy on replicated validation sets. To balance the less-represented population of healthy women, a Synthetic Minority Oversampling TEchnique (SMOTE) data oversampling approach was applied. CONCLUSIONS: By means of tunable hyperparameters optimization, the RF algorithm showed great potential for early breast cancer detection, as it provides clear biomarkers ranking and their relative efficiency, allowing to ground the final diagnostic model on a restricted selection five steroid biomarkers only, as desirable for noninvasive tests with wide screening purposes.