摘要：Sensory evaluation, carried out by panel tests, is essential for quality classification of virgin olive oils (VOOs), but is time consuming and costly when many samples need to be assessed; sensory evaluation could be assisted by the application of screening methods. Rapid instrumental methods based on the analysis of volatile molecules might be considered interesting to assist the panel test through fast pre-classification of samples with a known level of probability, thus increasing the efficiency of quality control. With this objective, a headspace gas chromatography-ion mobility spectrometer (HS-GC-IMS) was used to analyze 198 commercial VOOs (extra virgin, virgin and lampante) by a semi-targeted approach. Different partial least squares-discriminant analysis (PLS-DA) chemometric models were then built by data matrices composed of 15 volatile compounds, which were previously selected as markers: a first approach was proposed to classify samples according to their quality grade and a second based on the presence of sensory defects. The performance (intra-day and inter-day repeatability, linearity) of the method was evaluated. The average percentages of correctly classified samples obtained from the two models were satisfactory, namely 77% (prediction of the quality grades) and 64% (prediction of the presence of three defects) in external validation, thus demonstrating that this easy-to-use screening instrumental approach is promising to support the work carried out by panel tests.
