Accuracy of an artificial intelligence-based model for estimating leftover liquid food in hospitals: validation study (Preprint)

BACKGROUND The accurate evaluation of the nutritional status of malnourished hospitalized patients at a higher risk of complications, such as frailty or disability, is crucial. Visual methods of estimating food intake are popular for evaluating the nutritional status in clinical environments. However, from the perspective of accurate measurement, such methods are unreliable. OBJECTIVE The accuracy of estimating leftover liquid food in hospitals using an artificial intelligence (AI)-based model was compared to that of visual estimation. METHODS The accuracy of obtained using the AI-based model (AI estimation) was compared to that of the visual estimation method for thin rice gruel as staple food, and fermented milk and peach juice as side dishes. A total of 576 images of liquid food (432 images of thin rice gruel, 72 of fermented milk, and 72 of peach juice) were used. Welch's t-test and the confusion matrix were used to examine the difference of mean absolute error between AI and visual estimation. RESULTS The mean absolute errors obtained through the AI estimation approach for side dishes were as follows: fermented milk: 0.63 and peach juice: 0.25. These were significantly smaller than those obtained using the visual estimation approach: fermented milk: 1.40 and peach juice: 0.90. Contrastingly, the mean absolute error for staple food obtained using the AI estimation method (0.99) did not differ significantly from that obtained using visual estimation (0.99). The confusion matrix for staple foods showed variation in the distribution of errors, indicating that the errors in the AI estimation were biased toward the case of many leftovers. CONCLUSIONS AI estimation measures liquid food intake in hospitals more precisely than visual estimation, but its accuracy in estimating staple food leftovers requires improvement.

Determination of Trace and Heavy Metals in Fruit Juices in the Romanian Market

The presence of trace, heavy metals in foodstuffs is of intense public interest. The aim of this study was to determine the metal contents in most known commercial fruit juices present on the Romanian market. The multielement analysis was made using the ICP-MS technique, after appropriate dilution, using the external standard calibration method. Multifruit, mango, and kiwi juice have recoded the highest concentration of Cu, while apple and pear juice has recoded the lowest concentration, and in the case of Zn, peach juice has recoded the highest concentration. Concerning Pb, Cd, and As concentration, apple, peach, and multifruit juices recorded the highest levels of concentration. The concentration of Zn, Cu, Co, and As generally, was higher in the juice samples packed in boxes, while Ni, Cr, Pb, and Cd recorded the highest values in the juice packed in plastic bottles.

Application of FTIR-ATR to discriminate peach nectars with higher and lower sugar contents

Fruit juice does not have the same nutritional value as fresh fruit with regards to the vitamin, mineral and dietary fibre contents and the antioxidant properties. However, it can be part of a healthy diet if it is produced with the minimal addition of sugar. This study aimed to evaluate the performance of the FTIR-ATR technique to discriminate the authenticity (concerning the addition of other pulps) and amount of sugar in peach nectars. This technique is usually used in food analysis because it does not require sample preparation, is quick and allows for the determination of several parameters with a single sample aliquot. The nutritional information provided on the labels of 69 samples of 23 different brands of commercial peach juice, was analysed. The differences in the nutritional composition and in the ingredients were determined according to an analysis of the labels. The largest differences observed between the samples were the sugar contents, the percentages of pulp and the addition of other pulps. All samples were analysed by FTIR-ATR equipped with a controlled temperature flow-through cell. The spectral multivariate analysis suggested it was possible to identify differences in the amount of sugar present and identify the presence of fruit pulps other than peach.