A Machine Learning-Based Web Tool for the Severity Prediction of COVID-19.

Predictive tools provide a unique opportunity to explain the observed differences in outcome between patients of the COVID-19 pandemic. The aim of this study was to associate individual demographic and clinical characteristics with disease severity in COVID-19 patients and to highlight the importance of machine learning (ML) in disease prognosis. The study enrolled 344 unvaccinated patients with confirmed SARS-CoV-2 infection. Data collected by integrating questionnaires and medical records were imported into various classification machine learning algorithms, and the algorithm and the hyperparameters with the greatest predictive ability were selected for use in a disease outcome prediction web tool. Of 111 independent features, age, sex, hypertension, obesity, and cancer comorbidity were found to be associated with severe COVID-19. Our prognostic tool can contribute to a successful therapeutic approach via personalized treatment. Although at the present time vaccination is not considered mandatory, this algorithm could encourage vulnerable groups to be vaccinated.

A New Definition of the Term "High-Phenolic Olive Oil" Based on Large Scale Statistical Data of Greek Olive Oils Analyzed by qNMR.

In the last few years, a new term, "High-phenolic olive oil", has appeared in scientific literature and in the market. However, there is no available definition of that term regarding the concentration limits of the phenolic ingredients of olive oil. For this purpose, we performed a large-scale screening and statistical evaluation of 5764 olive oil samples from Greece coming from >30 varieties for an eleven-year period with precisely measured phenolic content by qNMR. Although there is a large variation among the different cultivars, the mean concentration of total phenolic content was 483 mg/kg. The maximum concentration recorded in Greece reached 4003 mg/kg. We also observed a statistically significant correlation of the phenolic content with the harvest period and we also identified varieties affording olive oils with higher phenolic content. In addition, we performed a study of phenolic content loss during usual storage and we found an average loss of 46% in 12 months. We propose that the term high-phenolic should be used for olive oils with phenolic content > 500 mg/kg that will be able to retain the health claim limit (250 mg/kg) for at least 12 months after bottling. The term exceptionally high phenolic olive oil should be used for olive oil with phenolic content > 1200 mg/kg (top 5%).

Oleocanthalic Acid, a Chemical Marker of Olive Oil Aging and Exposure to a High Storage Temperature with Potential Neuroprotective Activity.

The investigation of olive oils stored for a period of 24 months under appropriate conditions (25 °C, dark place, and airtight container) led to the identification of a new major phenolic ingredient, which was named oleocanthalic acid. The structure of the new compound was elucidated using one- and two-dimensional nuclear magnetic resonance in combination with tandem mass spectrometry. The new compound is an oxidation product of oleocanthal and is found in fresh oils in very low concentrations. The concentration of oleocanthalic acid increased with storage time, while the oleocanthal concentration decreased. A similar increase of the oleocanthalic acid/oleocanthal ratio was achieved after exposure of olive oil to 60 °C for 14 days. Although the presence of an oxidized derivative of decarboxymethylated ligstroside aglycon had been reported, it is the first time that its structure is characterized. The isolated compound could induce the expression of amyloid-ß major transport proteins as well as tight junctions expressed at the blood-brain barrier, suggesting that oleocanthalic acid could be beneficial against Alzheimer's disease.