Biserial targeted feature projection based radial kernel regressive deep belief neural learning for covid-19 prediction.

Coronavirus disease 2019 (COVID-19) is a highly infectious viral disease caused by the novel SARS-CoV-2 virus. Different prediction techniques have been developed to predict the coronavirus disease's existence in patients. However, the accurate prediction was not improved and time consumption was not minimized. In order to address these existing problems, a novel technique called Biserial Targeted Feature Projection-based Radial Kernel Regressive Deep Belief Neural Learning (BTFP-RKRDBNL) is introduced to perform accurate disease prediction with lesser time consumption. The BTFP-RKRDBNL techniques perform disease prediction with the help of different layers such as two visible layers namely input and layer and two hidden layers. Initially, the features and data are collected from the dataset and transmitted to the input layer. The Point Biserial Correlative Target feature projection is used to select relevant features and other irrelevant features are removed with minimizing the disease prediction time. Then the relevant features are sent to the hidden layer 2. Next, Radial Kernel Regression is applied to analyze the training features and testing disease features to identify the disease with higher accuracy and a lesser false positive rate. Experimental analysis is planned to measure the prediction accuracy, sensitivity, and specificity, and prediction time for different numbers of patients. The result illustrates that the method increases the prediction accuracy, sensitivity, and specificity by 10, 6, and 21% and reduces the prediction time by 10% as compared to state-of-the-art works.

2-deoxy-D-glucose as an adjunct to standard of care in the medical management of COVID-19: a proof-of-concept and dose-ranging randomised phase II clinical trial.

BACKGROUND: At present, no single efficacious therapeutic exists for acute COVID-19 management and a multimodal approach may be necessary. 2-deoxy-D-glucose (2-DG) is a metabolic inhibitor that has been shown to limit multiplication of SARS-CoV-2 in-vitro. We evaluated the efficacy and safety of 2-DG as adjunct to standard care in the treatment of moderate to severe COVID-19 patients. METHODS: We conducted a randomized, open-label, phase II, clinical study to evaluate the efficacy, safety, and tolerability of 2-DG administered as adjunct to standard of care (SOC). A total of 110 patients between the ages of 18 and 65 years with moderate to severe COVID-19 were included. Patients were randomized to receive 63, 90, or 126 mg/kg/day 2-DG in addition to SOC or SOC only. Times to maintaining SpO2 ≥ 94% on room air, discharge, clinical recovery, vital signs normalisation, improvement by 1 and 2 points on WHO clinical progression scale, negative conversion on RT-PCR, requirement for intensive care, and mortality were analyzed to assess the efficacy. RESULTS: Patients treated with 90 mg/kg/day 2-DG plus SOC showed better outcomes. Time to maintaining SpO2 ≥ 94% was significantly shorter in the 2-DG 90 mg compared to SOC (median 2.5 days vs. 5 days, Hazard ratio [95% confidence interval] = 2.3 [1.14, 4.64], p = 0.0201). Times to discharge from isolation ward, to clinical recovery, and to vital signs normalization were significantly shorter for the 2-DG 90 mg group. All three doses of 2-DG were well tolerated. Thirty-three (30.3%) patients reported 65 adverse events and were mostly (86%) mild. CONCLUSIONS: 2-DG 90 mg/kg/day as adjunct to SOC showed clinical benefit over SOC alone in the treatment of moderate to severe COVID-19. The promising trends observed in current phase II study is encouraging for confirmatory evaluation of the efficacy and safety of 2-DG in a larger phase III trial. TRIAL REGISTRATION: CTRI, CTRI/2020/06/025664. Registered 5th June 2020, http://ctri.nic.in/Clinicaltrials/pdf_generate.php?trialid=44369&EncHid=&modid=&compid=%27,%2744369det%27 .

Perception of individuality in bat vocal communication: discrimination between, or recognition of, interaction partners?

Different cognitive processes underlying voice identity perception in humans may have precursors in mammals. A perception of vocal signatures may govern individualised interactions in bats, which comprise species living in complex social structures and are nocturnal, fast-moving mammals. This paper investigates to what extent bats recognise, and discriminate between, individual voices and discusses acoustic features relevant for accomplishing these tasks. In spontaneous presentation and habituation-dishabituation experiments, we investigated how Megaderma lyra perceives and evaluates stimuli consisting of contact call series with individual-specific signatures from either social partners or unknown individuals. Spontaneous presentations of contact call stimuli from social partners or unknown individuals elicited strong, but comparable reactions. In the habituation-dishabituation experiments, bats dishabituated significantly to any new stimulus. However, reactions were less pronounced to a novel stimulus from the bat used for habituation than to stimuli from other bats, irrespective of familiarity, which provides evidence for identity discrimination. A model separately assessing the dissimilarity of stimuli in syllable frequencies, syllable durations and inter-call intervals relative to learned memory templates accounted for the behaviour of the bats. With respect to identity recognition, the spontaneous presentation experiments were not conclusive. However, the habituation-dishabituation experiments suggested that the bats recognised voices of social partners as the reaction to a re-habituation stimulus differed after a dishabituation stimulus from a social partner and an unknown bat.