Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 5 de 5
Artificial Intelligence in Covid-19 ; : 239-256, 2022.
Article in English | Scopus | ID: covidwho-20245007


Artificial Intelligence (AI) is contributing to the campaign against the Coronavirus Disease 2019 (COVID-19). Since 2019, more and more AI frameworks and applications in COVID-19 have been proposed, and the recent research has shown that AI is a promising technology because AI can achieve a higher degree of scalability, a more comprehensive and identification of patterns in the vast amount of unstructured and noisy data, accelerated processing power, and strategies to outperform traditional methods in many specific tasks. In this chapter, we focus on the specific AI applications in the clinical immunology/immunoinformatics for COVID-19. More precisely, on one hand, we discuss the application of deep learning in designing SARS-CoV-2 vaccines, and, on the other hand, we discuss the development of a machine learning framework for investigating the SARS-CoV-2 mutations that can help us better respond to the future mutant viruses, including designing more robust vaccines based on such AI approaches. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

10th International Conference on Learning Representations, ICLR 2022 ; 2022.
Article in English | Scopus | ID: covidwho-2261616


Time-evolution of partial differential equations is fundamental for modeling several complex dynamical processes and events forecasting, but the operators associated with such problems are non-linear. We propose a Padé approximation based exponential neural operator scheme for efficiently learning the map between a given initial condition and the activities at a later time. The multiwavelets bases are used for space discretization. By explicitly embedding the exponential operators in the model, we reduce the training parameters and make it more data-efficient which is essential in dealing with scarce and noisy real-world datasets. The Padé exponential operator uses a recurrent structure with shared parameters to model the non-linearity compared to recent neural operators that rely on using multiple linear operator layers in succession. We show theoretically that the gradients associated with the recurrent Padé network are bounded across the recurrent horizon. We perform experiments on non-linear systems such as Korteweg-de Vries (KdV) and Kuramoto-Sivashinsky (KS) equations to show that the proposed approach achieves the best performance and at the same time is data-efficient. We also show that urgent real-world problems like epidemic forecasting (for example, COVID-19) can be formulated as a 2D time-varying operator problem. The proposed Padé exponential operators yield better prediction results (53% (52%) better MAE than best neural operator (non-neural operator deep learning model)) compared to state-of-the-art forecasting models. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

ACM Transactions on Computing for Healthcare ; 3(3) (no pagination), 2022.
Article in English | EMBASE | ID: covidwho-2252484
Pediatriya. Zhurnal im. G.N. Speranskogo ; 99(6):73-83, 2020.
Article in Russian | Russian Science Citation Index | ID: covidwho-1094690


The most severe manifestation of the new coronavirus infection COVID-19 in children is the multisystem inflammatory syndrome in children (MIS-C). A systematic review of foreign publications as of July 25, 2020 contains an analysis of the disease course in 662 children with this syndrome and is used for comparison with the data obtained. Objective of the research: to characterize clinical manifestation, results of laboratory and instrumental studies, therapy, outcomes and consequences of the COVID-19- associated MIS-C., based on the observation of patients hospitalized to Morozov Children's City Clinical Hospital and Children’s clinical hospital of infectious diseases № 6 from May 1 to September 15, 2020. Materials and methods: the pilot study included 32 children aged 9 months -15 years with COVID-19-associated MIS-C., verified based on WHO criteria (2020), including symptoms of Kawasaki disease (KD), arterial hypotension/shock, laboratory and instrumental signs of heart damage, signs of coagulopathy, gastrointestinal symptoms, increased inflammation markers, COVID-19 markers. Results: the median age of patients was 6 years, boys predominated among the patients (66%), all patients had antibodies to SARS-CoV-2 (31 children of the IgG class);MIS-C manifested itself as a combination of KD symptom complex (75% of patients) with arterial hypotension/shock (28%), neurological (50%), respiratory (41%), gastrointestinal (59%) symptoms;macrophage activation syndrome (MAS) was verified in 16% of patients. Therapy included intravenous immunoglobulin (75%), systemic glucocorticosteroids (88%), anticoagulants (91%), vasoactive/vasopressor support (31%). In 38% of cases treatment was performed in intensive care unit;one child died. According to echocardiography, 16% of patients had coronariitis, ectasia, and coronary arteries aneurysms. Conclusion: COVID-19-associated MIS-C is characterized by a severe course, cross-features with KD, shock syndrome with KD, MAS which requires intensive therapy and can cause acquired pathology of the cardiovascular system in children. Самым тяжелым проявлением новой коронавирусной инфекции COVID-19 у детей является ассоциированный с ней детский мультисистемный воспалительный синдром (ДМВС). Систематический обзор зарубежных публикаций по состоянию на 25 июля 2020 г. содержит анализ течения заболевания у 662 детей с данным синдромом и используется для сравнения с полученными данными. Цель исследования - характеристика клинической манифестации, результатов лабораторно-инструментальных исследований, терапии, исходов и последствий ДМВС, ассоциированного с COVID-19, основанная на наблюдении пациентов, госпитализированных в период с 1 мая по 15 сентября 2020 г. в Морозовскую ДГКБ и ДИКБ № 6 ДЗМ. Материалы и методы исследования: в пилотное исследование были включены 32 ребенка в возрасте 9 мес. - 15 лет с ДМВС, ассоциированным с COVID-19, верифицированным на основании критериев ВОЗ (2020), включающих симптомы болезни Кавасаки (БК), артериальную гипотензию/шок, лабораторно-инструментальные признаки поражения сердца, признаки коагулопатии, гастроинтестинальные симптомы, повышение маркеров воспаления, маркеры COVID-19. Результаты: медиана возраста больных составила 6 лет, среди больных преобладали мальчики (66%), у всех пациентов были обнаружены антитела к SARS-CoV-2 (у 31 ребенка класса IgG);ДМВС манифестировал в виде комбинации симптомокомплекса БК (75% больных) с артериальной гипотензией/шоком (28%), неврологическими (50%), респираторными (41%), гастроинтестинальными (59%) симптомами;у 16% пациентов был верифицирован синдром активации макрофагов (САМ). Терапия включала иммуноглобулин для внутривенного введения (75%), системные глюкокортикостероиды (88%), антикоагулянты (91%), вазоактивную/ вазопрессорную поддержку (31%). Лечение в 38% случаев проводилось в условиях отделения реанимации и интенсивной терапии;один ребенок погиб. У 16% по данным эхокардиографии были выявлены коронариит, эктазии, аневризмы коронарных артерий. Заключение: ДМВС, ассоциированный с COVID-19, характеризуется тяжелым течением, перекрестными чертами с БК, синдромом шока при БК, САМ, что требует проведения интенсивной терапии и может стать причиной приобретенной патологии сердечно-сосудистой системы у детей.