A5046184914- SARS-CoV-2 and COVID-19 Research
- Machine Learning in Bioinformatics
- COVID-19 diagnosis using AI
- Gut microbiota and health
- SARS-CoV-2 detection and testing
- Numerical methods in inverse problems
- Asthma and respiratory diseases
- Gene expression and cancer classification
- MicroRNA in disease regulation
- Genomics and Phylogenetic Studies
- Cancer-related molecular mechanisms research
- Genetics, Bioinformatics, and Biomedical Research
- Muscle activation and electromyography studies
- Reproductive System and Pregnancy
- Infant Nutrition and Health
- COVID-19 Clinical Research Studies
- Statistical and numerical algorithms
- Systemic Lupus Erythematosus Research
- Bioinformatics and Genomic Networks
- IL-33, ST2, and ILC Pathways
- Parasitic infections in humans and animals
- Preterm Birth and Chorioamnionitis
- Fault Detection and Control Systems
- Motor Control and Adaptation
- Electrical and Bioimpedance Tomography
Utrecht University
2019-2024
University Medical Center Utrecht
2021-2024
Pharmo Institute
2020-2024
Oklahoma State University Center for Health Sciences
2021-2023
Centrum Wiskunde & Informatica
2018-2019
Université de Lille
2018
Centre de Recherche en Informatique
2018
AgroParisTech
2018
Université Paris-Saclay
2018
Sorbonne Université
2018
In a Mexican village in which Taenia solium infection was known to be endemic, we selected cluster sample of 368 households (21% the total) for demographic, environmental, and diagnostic surveys, medical histories taeniasis cysticercosis. Coproparasitologic studies 1,531 participants revealed by sp. four (0.3%) individuals; however, 5.8% respondents reported history having passed tapeworm proglottids feces. Of 1,552 human serum specimens, 10.8% tested positive cysticercosis immunoblot assay....
In this paper, deep learning is coupled with explainable artificial intelligence techniques for the discovery of representative genomic sequences in SARS-CoV-2. A convolutional neural network classifier first trained on 553 from National Genomics Data Center repository, separating genome different virus strains Coronavirus family 98.73% accuracy. The network's behavior then analyzed, to discover used by model identify SARS-CoV-2, ultimately uncovering exclusive it. discovered are validated...
Abstract Autism spectrum disorder (ASD) is a highly complex neurodevelopmental characterized by deficits in sociability and repetitive behaviour, however there great heterogeneity within other comorbidities that accompany ASD. Recently, gut microbiome has been pointed out as plausible contributing factor for ASD development individuals diagnosed with often suffer from intestinal problems show differentiated microbial composition. Nevertheless, studies rarely agree on the specific bacterial...
Abstract Background MicroRNAs (miRNAs) are noncoding RNA molecules heavily involved in human tumors, which few of them circulating the body. Finding a tumor-associated signature miRNA, that is, minimum miRNA entities to be measured for discriminating both different types cancer and normal tissues, is utmost importance. Feature selection techniques applied machine learning can help however they often provide naive or biased results. Results An ensemble feature strategy signatures proposed....
Circulating microRNAs (miRNA) are small noncoding RNA molecules that can be detected in bodily fluids without the need for major invasive procedures on patients. miRNAs have shown great promise as biomarkers tumors to both assess their presence and predict type subtype. Recently, thanks availability of datasets, machine learning techniques been successfully applied tumor classification. The results, however, difficult interpret by medical experts because algorithms exploit information from...
Abstract Background In recent years, human microbiome studies have received increasing attention as this field is considered a potential source for clinical applications. With the advancements in omics technologies and AI, research focused on discovery biomarkers using machine learning tools has produced positive outcomes. Despite promising results, several issues can still be found these such datasets with small number of samples, inconsistent lack uniform processing methodologies, other...
ABSTRACT In this paper, deep learning is coupled with explainable artificial intelligence techniques for the discovery of representative genomic sequences in SARS-CoV-2. A convolutional neural network classifier first trained on 553 from available repositories, separating genome different virus strains Coronavirus family considerable accuracy. The network’s behavior then analyzed, to discover used by model identify SARS-CoV-2, ultimately uncovering exclusive it. discovered are validated...
The detection of human emotions from facial expressions is crucial for social interaction. Therefore, several systems behavioral computing in robotics try to recognize emotion images and video, but most them are trained classify adults only. Using the standard 6 basic emotions: sadness, happiness, surprise, anger, disgust, fear, we using NAO robot children. In this study, make comparison between AFFDEX SDK, a Convolution Neural Network (CNN) with Viola-Jones AffectNet dataset, tuned...
Abstract Long COVID, also known as post-acute sequelae of SARS-CoV-2 infection (PASC), encompasses a range symptoms persisting for weeks or months after the acute phase COVID-19. These symptoms, affecting multiple organ systems, significantly impact quality life. This study employs machine-learning approach to identify gene targets treating COVID. Using datasets GSE275334, GSE270045, and GSE157103, Recursive Ensemble Feature Selection (REFS) was applied key genes associated with The...
Many people suffer from a brain injury that requires rehabilitation. Rehabilitation might be exhausting and difficult. Therefore, it is necessary to develop mechanisms engage the patients, e.g. videogame. We propose design of an immersive videogame integrates motion capture, electromyography (EMG) sensing Virtual Reality (VR) in one unique system using Unity engine EMG sensors. The has as user inputs capture given by Microsoft Kinect or Yei 3-Space Sensors, measured effort muscle (biceps)....
Abstract Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a chronic disorder characterized by disabling fatigue. Several studies have sought to identify diagnostic biomarkers, with varying results. Here, we innovate this process combining both mRNA expression and DNA methylation data. We performed recursive ensemble feature selection (REFS) on publicly available data in peripheral blood mononuclear cells (PBMCs) of 93 ME/CFS patients 25 healthy controls, found signature 23...
ABSTRACT The SARS-CoV-2 variant B.1.1.7 lineage, also known as clade GR from Global Initiative on Sharing All Influenza Data (GISAID), Nextstrain 20B, or Variant Under Investigation in December 2020 (VUI – 202012/01), appears to have an increased transmissability comparison other variants. Thus, contain and study this of the virus, it is necessary develop a specific molecular test uniquely identify it. Using completely automated pipeline involving deep learning techniques, we designed primer...
Abstract Background Uncontrolled asthma can lead to severe exacerbations and reduced quality of life. Research has shown that the microbiome may be linked with characteristics; however, its association control not been explored. We aimed investigate whether gastrointestinal used discriminate between uncontrolled controlled in children. Methods 143 103 feces samples were obtained from children moderate‐to‐severe aged 6 17 years SysPharmPediA study. Patients classified as or asthmatics, their...
Acquiring information about the distribution of electrical sources in brain from electroencephalography (EEG) data remains a significant challenge. An accurate solution would provide an understanding inner mechanisms activity and damaged tissue. In this paper, we present methodology for reconstructing EEG by using bidomain formulation. The model considers continuous active neural tissue coupled with nonlinear cell model. Using technique, aim to find that give rise scalp potential recorded...
ABSTRACT As the COVID-19 pandemic continues, new SARS-CoV-2 variants with potentially dangerous features have been identified by scientific community. Variant B.1.1.7 lineage clade GR from Global Initiative on Sharing All Influenza Data (GISAID) was first detected in UK, and it appears to possess an increased transmissibility. At same time, South African authorities reported variant B.1.351, that shares several mutations B.1.1.7, might also present high Earlier this year, a labelled P.1 17...
Abstract Background Not being well controlled by therapy with inhaled corticosteroids and long‐acting β2 agonist bronchodilators is a major concern for severe‐asthma patients. The current treatment option these patients the use of biologicals such as anti‐IgE treatment, omalizumab, an add‐on therapy. Despite accepted do not always benefit from it. Therefore, there need to identify reliable biomarkers predictors omalizumab response. Methods Two novel computational algorithms, machine‐learning...
Background Pregnancy is a portentous stage in life, during which countless events are precisely orchestrated to ensure healthy offspring. Maternal microbial communities thought have profound impact on development. Although antibiotic drugs may interfere these processes, they constitute the most frequently prescribed medication pregnancy prohibit detrimental consequences of infections. Gestational intervention linked preeclampsia and negative effects neonatal immunity. Even though...
To compare the immunologic profiles of peripheral and menstrual blood (MB) women who experience recurrent pregnancy loss without complications.Explorative case-control study. Cross-sectional assessment flow cytometry-derived profiles.Academic medical center.Women experienced more than 2 consecutive miscarriages.None.Flow cytometry-based immune uterine systemic immunity (recurrent loss, n = 18; control, 14) assessed by machine learning classifiers in an ensemble strategy, followed recursive...
In Europe, allergic diseases are the most common chronic childhood illnesses and result of a complex interplay between genetics environmental factors. A new approach for analyzing this data is to employ machine learning (ML) algorithms. Therefore, aim pilot study was find predictors presence parental-reported allergy at 4–6 years age by using feature selection in ML. recursive ensemble (REFS) used, with 20% step reduction eight different classifiers ensemble, resampling given class...
The authors propose two equations based on the pixel geometry and connectivity properties, which can be used to compute, efficiently, Euler number of a binary digital image with either thick or thin boundaries. Although computing this feature, authors’ technique extracts underlying topological information provided by shape pixels given image. correctness using new is also established theoretically. performance proposed method compared against other available alternatives. Experimental...