An Artificial Neural Network for Nasogastric Tube Position Decision Support.

Purpose: To develop and validate a deep learning model for detection of nasogastric tube (NGT) malposition on chest radiographs and assess model impact as a clinical decision support tool for junior physicians to help determine whether feeding can be safely performed in patients (feed/do not feed). Materials and Methods: A neural network ensemble was pretrained on 1 132 142 retrospectively collected (June 2007-August 2019) frontal chest radiographs and further fine-tuned on 7081 chest radiographs labeled by three radiologists. Clinical relevance was assessed on an independent set of 335 images. Five junior emergency medicine physicians assessed chest radiographs and made feed/do not feed decisions without and with artificial intelligence (AI)-generated NGT malposition probabilities placed above chest radiographs. Decisions from the radiologists served as ground truths. Model performance was evaluated using receiver operating characteristic analysis. Agreement between junior physician and radiologist decision was determined using the Cohen κ coefficient. Results: In the testing set, the ensemble achieved area under the receiver operating characteristic curve values of 0.82 (95% CI: 0.78, 0.86), 0.77 (95% CI: 0.71, 0.83), and 0.98 (95% CI: 0.96, 1.00) for satisfactory, malpositioned, and bronchial positions, respectively. In the clinical evaluation set, mean interreader agreement for feed/do not feed decisions among junior physicians was 0.65 ± 0.03 (SD) and 0.77 ± 0.13 without and with AI support, respectively. Mean agreement between junior physicians and radiologists was 0.53 ± 0.05 (unaided) and 0.65 ± 0.09 (AI-aided). Conclusion: A simple classifier for NGT malposition may help junior physicians determine the safety of feeding in patients with NGTs.Keywords: Neural Networks, Feature Detection, Supervised Learning, Machine Learning Supplemental material is available for this article. Published under a CC BY 4.0 license.

Green Route to Produce Silver Nanoparticles Using the Bioactive Flavonoid Quercetin as a Reducing Agent and Food Anti-Caking Agents as Stabilizers.

In previous work, the isolated polyphenolic compound (PPC) quercetin was used as a reducing agent in the formation of silver nanoparticles (AgNPs), testing two types of quercetin. This PPC is a bioactive molecule that provides the electrons for the reduction of silver ions to zerovalent silver. The results demonstrated that quercetin in dietary supplement presentation was better than reagent grade quercetin for the synthesis of AgNPs, and the difference between them was that the dietary supplement had microcrystalline cellulose (CM) in its formulation. Therefore, this dietary anti-caking agent was added to the reagent-grade quercetin to validate this previously found improvement. AgNPs were obtained at neutral pH by a green route using quercetin as a reducing agent and microcrystalline cellulose and maltodextrin as stabilizing agents. In addition, different ratios were evaluated to find the optimum ratio. Ultraviolet-Visible spectroscopy (UV-VIS), Atomic Force Microscope (AFM), Z-potential, Dynamic Light Scattering (DLS) and X-ray Powder Diffraction (XRD) were used for characterization. The antibacterial activity of the S. aureus and E. coli agent was tested by the disk diffusion and microdilution method. According to the results, this green synthesis needs the use of food stabilizer when working at pH 7 to maintain AgNPs in the long term. The ideal ratio of reducing the agent:stabilizing agent was 1:2, since with this system stable AgNPs are obtained for 2 months and with improved antimicrobial activity, validating this method was ecologically and economically viable.

Comparison between the Visual Analog Scale and the Numerical Rating Scale in the perception of esthetics and pain.

BACKGROUND: Pain is an unpleasant, emotional, and sensorial experience. Esthetics and pain express perceptions or sensations that are subjective and personal, but non-consensual, between professionals and patients. The Visual Analog Scale (VAS) and the Numerical Rating Scale (NRS) are simple methods to evaluate such subjective phenomena. OBJECTIVE: To verify whether a concordance exists between VAS and NS in the perception of esthetics and pain. MATERIAL AND METHODS: Regarding esthetics, an on-line questionnaire was prepared with extra- and intra-oral images (adapted). The order of the scales was alternated between interwoven and sequential. Regarding perception of pain, respondents personally classified its intensity at the present moment, or over the past 30 days. RESULTS: A statistically significant concordance (P<0.001) - positive and moderate - was found between the scales, for the evaluation of both the extra- and intra-oral images, r=0.678 and 0.638, respectively. Regarding pain perception, taking formal education into account, no concordance was found between the two scales for participants who had "no formal education" (P>0.05). The concordance between the scales increased proportionally with the level of education. CONCLUSION: There was a concordance between the scales with regard to esthetical perception and the evaluation of pain. When assessing esthetics, the order in which the two scales are applied does not affect the concordance between them. However, the strength of the concordance is influenced. Esthetic perception is not influenced by the differences between the panels of evaluators. The concordance between the two scales, for the evaluation of pain, increases proportionally with the level of formal education.

Novel non-calcemic secosteroids that are produced by human epidermal keratinocytes protect against solar radiation.

CYP11A1 hydroxylates the side chain of vitamin D3 (D3) in a sequential fashion [D3→20S(OH)D3→20,23(OH)2D3→17,20,23(OH)3D3], in an alternative to the classical pathway of activation [D3→25(OH)D3→1,25(OH)2D3]. The products/intermediates of the pathway can be further modified by the action of CYP27B1. The CYP11A1-derived products are biologically active with functions determined by the lineage of the target cells. This pathway can operate in epidermal keratinocytes. To further define the role of these novel secosteroids we tested them for protective effects against UVB-induced damage in human epidermal keratinocytes, melanocytes and HaCaT keratinocytes, cultured in vitro. The secosteroids attenuated ROS, H2O2 and NO production by UVB-irradiated keratinocytes and melanocytes, with an efficacy similar to 1,25(OH)2D3, while 25(OH)D3 had lower efficacy. These attenuations were also seen to some extent for the 20(OH)D3 precursor, 20S-hydroxy-7-dehydrocholesterol. These effects were accompanied by upregulation of genes encoding enzymes responsible for defense against oxidative stress. Using immunofluorescent staining we observed that the secosteroids reduced the generation cyclobutane pyrimidine dimers in response to UVB and enhanced expression of p53 phosphorylated at Ser-15, but not at Ser-46. Additional evidence for protection against DNA damage in cells exposed to UVB and treated with secosteroids was provided by the Comet assay where DNA fragmentation was markedly reduced by 20(OH)D3 and 20,23(OH)2D3. In conclusion, novel secosteroids that can be produced by the action of CYP11A1 in epidermal keratinocytes have protective effects against UVB radiation. This article is part of a special issue entitled '17th Vitamin D Workshop'.