Beatriz García Santa Cruz

ORCID: 0000-0002-0939-4443
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Machine Learning in Healthcare
  • COVID-19 diagnosis using AI
  • Metabolomics and Mass Spectrometry Studies
  • Artificial Intelligence in Healthcare and Education
  • Cell Image Analysis Techniques
  • Machine Learning and Data Classification
  • Explainable Artificial Intelligence (XAI)
  • Radiomics and Machine Learning in Medical Imaging
  • Microbial Metabolic Engineering and Bioproduction
  • Biomedical Text Mining and Ontologies
  • Neurological disorders and treatments
  • Machine Learning and Algorithms
  • Artificial Intelligence in Healthcare
  • Diabetic Foot Ulcer Assessment and Management
  • BIM and Construction Integration
  • Marine Biology and Environmental Chemistry
  • Diet and metabolism studies
  • Marine Biology and Ecology Research
  • AI in cancer detection
  • Advanced Neural Network Applications
  • Architecture, Art, Education
  • Gait Recognition and Analysis
  • Voice and Speech Disorders
  • Lower Extremity Biomechanics and Pathologies
  • Marine and coastal plant biology

Centre Hospitalier de Luxembourg
2021-2023

University of Luxembourg
2018-2022

Instituto Venezolano de Investigaciones Científicas
2007

A multitude of factors contribute to complex diseases and can be measured with 'omics' methods. Databases facilitate data interpretation for underlying mechanisms. Here, we describe the Virtual Metabolic Human (VMH, www.vmh.life) database encapsulating current knowledge human metabolism within five interlinked resources 'Human metabolism', 'Gut microbiome', 'Disease', 'Nutrition', 'ReconMaps'. The VMH captures 5180 unique metabolites, 17 730 reactions, 3695 genes, 255 Mendelian diseases, 818...

10.1093/nar/gky992 article EN cc-by Nucleic Acids Research 2018-10-10

Abstract A multitude of factors contribute to complex diseases and can be measured with “omics” methods. Databases facilitate data interpretation for underlying mechanisms. Here, we describe the Virtual Metabolic Human (VMH, http://vmh.life) database encapsulating current knowledge human metabolism within five interlinked resources “Human metabolism”, “Gut microbiome”, “Disease”, “Nutrition”, “ReconMaps”. The VMH captures 5,180 unique metabolites, 17,730 reactions, 3,288 genes, 255 Mendelian...

10.1101/321331 preprint EN cc-by-nc bioRxiv (Cold Spring Harbor Laboratory) 2018-05-15

Machine learning based methods for diagnosis and progression prediction of COVID-19 from imaging data have gained significant attention in the last months, particular by use deep models. In this context hundreds models where proposed with majority them trained on public datasets. Data scarcity, mismatch between training target population, group imbalance, lack documentation are important sources bias, hindering applicability these to real-world clinical practice. Considering that datasets an...

10.48550/arxiv.2008.11572 preprint EN cc-by arXiv (Cornell University) 2020-01-01

Tivela mactroides y Crassostrea rhizophorae son dos especies de bivalvos abundantes a lo largo la costa venezolana alta demanda local como mariscos. La hierba marina Thalassia testudinum, interés en diferentes partes del mundo, es muy abundante zonas costeras Venezuela. Aquí informamos las concentraciones Cd, Cr, Cu, Ni, V Zn muestras blandas tejidos recolectadas venezolana. Estas metálicas fueron determinadas utilizando espectrometría emisión óptica con plasma inductivamente acoplado...

10.15517/rbt.v56i0.5588 article ES cc-by Revista de Biología Tropical 2007-08-13

The study of complex diseases relies on large amounts data to build models toward precision medicine. Such acquisition is feasible in the context high-throughput screening, which quality results accuracy image analysis. Although state-of-the-art solutions for segmentation employ deep learning approaches, high cost manually generating ground truth labels model training hampers day-to-day application experimental laboratories. Alternatively, traditional computer vision-based do not need...

10.1038/s41598-022-15623-7 article EN cc-by Scientific Reports 2022-07-06

The use of Convolutional Neural Networks (CNN) in medical imaging has often outperformed previous solutions and even specialists, becoming a promising technology for Computer-aidedDiagnosis (CAD) systems. However, recent works suggested that CNN may have poor generalisation on new data, instance, generated different hospitals. Uncontrolled confounders been proposed as common reason. In this paper, we experimentally demonstrate the impact confounding data unknown scenarios. We assessed effect...

10.7557/18.6302 article EN Proceedings of the Northern Lights Deep Learning Workshop 2022-04-18

Abstract Gait analysis is a systematic study of human movement. Combining wearable foot pressure sensors and machine learning (ML) solutions for high-fidelity body pose tracking from RGB video frames could reveal more insights into gait abnormalities. However, accurate detection heel strike (HS) toe-off (TO) events crucial to compute interpretable parameters. In this work, we present an experimental platform the timing using new sensor (ActiSense System, IEE S.A., Luxembourg), Google’s...

10.1515/cdbme-2022-1146 article EN cc-by-nc-nd Current Directions in Biomedical Engineering 2022-08-01

Abstract The study of complex diseases relies on large amounts data to build models toward precision medicine. Such acquisition is feasible in the context high-throughput screening, which quality results accuracy image analysis. Although state-of-the-art solutions for segmentation employ deep learning approaches, high cost manually generating ground truth labels model training hampers day-to-day application experimental laboratories. Alternatively, traditional computer vision-based do not...

10.21203/rs.3.rs-991404/v1 preprint EN cc-by Research Square (Research Square) 2021-10-29
Coming Soon ...