Lycopene is a very attractive antioxidant associated with cancer prevention in humans. Therefore, it is important to develop new analytical methods that allow for differentiation of food production streams that contain various antioxidant concentrations. The lycopene content in tomato juice, an intermediate between raw tomatoes and the final tomato paste product, was monitored on-line for 46 days at a production plant with a novel, patented double-channel Raman setup. The setup comprises a double-channel mini spectrometer placed in a fixed optical setup, and for each measurement there are two slightly shifted Raman spectra on the x-axis that opens up for additional data processing. The prototype was constructed specifically for 532 nm excitation with no moving parts, and it was designed to optimize each part for the rest of the system. That was the first step toward an integrated optical in-line process analytical solution for industry. As proof of concept, the developed prototype was able to perform a real-time differentiation of the normal and medium to high lycopene content in tomato juice. A correlation factor for double-channel measurements was compared with a correlation factor for background-corrected single-channel measurements by correlating with high performance liquid chromatography reference measurements (1-20 mg of lycopene per 100 g of wet sample). The latter gave a slightly better correlation for the specific application (R(2) = 0.76), acceptable for proof of concept. Real-time information is extremely valuable for the tomato processing plant, mainly because it can be used for improved differentiation of high lycopene content tomato paste to ensure a higher product price. In addition, the developed process analytical technology solution allows for differentiated payment of the tomato farmers based on the lycopene content in their crops.
Summary
Healthcare-associated infections (HAIs) are among the most common adverse events in hospitals. We used artificial intelligence (AI) algorithms for infection surveillance in a cohort study. The model correctly detected 67 out of 73 patients with HAIs. The final model used a multilayer perceptron neural network achieving an area under receiver operating curve (AUROC) of 90.27%; specificity of 78.86%; sensitivity of 88.57%. Respiratory infections had the best results (AUROC ≥93.47%). The AI algorithm could identify most HAIs. AI is a feasible method for HAI surveillance, has the potential to save time, promote accurate hospital-wide surveillance, and improve infection prevention performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.