- Bacterial Identification and Susceptibility Testing
- EEG and Brain-Computer Interfaces
- Clostridium difficile and Clostridium perfringens research
- Machine Fault Diagnosis Techniques
- Genomics and Phylogenetic Studies
- Antibiotic Resistance in Bacteria
- Metabolomics and Mass Spectrometry Studies
- Nosocomial Infections in ICU
- Voice and Speech Disorders
- Railway Engineering and Dynamics
- Gut microbiota and health
- Medical Imaging and Analysis
- Sinusitis and nasal conditions
- ECG Monitoring and Analysis
- Phonetics and Phonology Research
- History of Medicine Studies
- Industrial Technology and Control Systems
- E-Learning and Knowledge Management
- Gaze Tracking and Assistive Technology
- Neurology and Historical Studies
- Nasal Surgery and Airway Studies
- Neuroscience and Neural Engineering
- Knowledge Societies in the 21st Century
- Neurological Complications and Syndromes
- Latin American socio-political dynamics
Universidad Politécnica de Madrid
2023-2025
University of Sucre
2025
Universidad Carlos III de Madrid
2021-2024
Universidad de Antioquia
2023
Hospital General Universitario Gregorio Marañón
2021-2023
Pilot University of Colombia
2015
Universidad del Rosario
2015
University of Pamplona
2013
NewYork–Presbyterian Brooklyn Methodist Hospital
2008
New York Proton Center
2008
The Enterobacter cloacae complex (ECC) encompasses heterogeneous clusters of species that have been associated with nosocomial outbreaks. These may different acquired antimicrobial resistance and virulence mechanisms, their identification is challenging. This study aims to develop predictive models based on matrix-assisted laser desorption ionization-time flight mass spectrometry (MALDI-TOF MS) profiles machine learning for species-level identification. A total 219 ECC 118 Klebsiella...
Maintaining railway axles is critical to preventing severe accidents and financial losses. The industry increasingly interested in advanced condition monitoring techniques enhance safety efficiency, moving beyond traditional periodic inspections toward Maintenance 4.0. This study introduces a robust Deep Autoregressive solution that integrates seamlessly with existing systems avert mechanical failures. Our approach simulates predicts vibration signals under various conditions fault...
While semantic segmentation allows precise localization of potential lesions, a based on object detection using bounding boxes is considered more effective for indicating the location target without replacing clinical expertise, reducing attentional and automation biases. In this context, work lays foundation better explainable lesions in lungs due to pneumonia by applying combined approach first Bayesian uncertainty measure evaluate likelihood specific slice being positive particular...
Clostridioides difficile is a leading cause of hospital-acquired diarrhea, presenting significant clinical challenges due to its high morbidity and mortality rates role in nosocomial outbreaks. Rapid accurate detection toxigenic ribotypes crucial for effective outbreak control. We developed diagnostic methodology utilizing MALDI-TOF MS Machine Learning algorithms differentiate C. ribotypes. Analysis spectra from 379 isolates 10 Spanish hospitals identified seven biomarker peaks...
Parkinson’s disease significantly impacts speech, particularly affecting phonemic groups like stop-plosives, fricatives, and affricates. However, its objective impact on the different has been briefly addressed in past. This study introduces a new model, called MARTA, built upon Gaussian Mixture Variational AutoEncoder with metric learning to measure disease’s grouping automatically objectively. MARTA was trained normophonic speech before adapting it parkinsonian speech. The model...
Abstract Many research articles have explored the impact of surgical interventions on voice and speech evaluations, but advances are limited by lack publicly accessible datasets. To address this, a comprehensive corpus 107 Spanish Castilian speakers was recorded, including control patients who underwent upper airway surgeries such as Tonsillectomy, Functional Endoscopic Sinus Surgery, Septoplasty. The dataset contains 3,800 audio files, averaging 35.51 ± 5.91 recordings per patient. This...
The screening of Parkinson's Disease (PD) through speech is hindered by a notable lack publicly available datasets in different languages. This fact limits the reproducibility and further exploration existing research. To address this gap, manuscript presents NeuroVoz corpus consisting 112 native Castilian-Spanish speakers, including 58 healthy controls 54 individuals with PD, all recorded ON state. showcases diverse array tasks: sustained vowels; diadochokinetic tests; 16 Listen-and-Repeat...
Maintaining railway axles is crucial to prevent catastrophic failures and enormous human economic costs. In recent years, there has been a growing interest in the industry adopt condition monitoring techniques enhance safety efficiency of rail transport system, which maintenance currently based on periodic inspections. this context, work presents technique for real-time crack diagnosis axles, advanced 2D-Convolutional Neural Network (CNN) architectures applied time–frequency representations...
The advancement of Parkinson's Disease (PD) diagnosis through speech analysis is hindered by a notable lack publicly available, diverse language datasets, limiting the reproducibility and further exploration existing research. In response to this gap, we introduce comprehensive corpus from 108 native Castilian Spanish speakers, comprising 55 healthy controls 53 individuals diagnosed with PD, all whom were under pharmacological treatment recorded in their medication-optimized state. This...
Abstract Endoscopic sinus and skull base surgeries require the use of precise neuronavigation techniques, which may take advantage accurate delimitation surrounding structures. This is critical for robotic-assisted surgery procedures to limit volumes no resection. In this respect, segmentation Osseous Structures Paranasal Sinuses (OSPS) a relevant issue protect anatomic structures during these surgeries. Currently, manual labour-intensive task requires expertise, often leading...
Abstract The implementation of Matrix-assisted laser desorption ionization–time flight (MALDI-TOF) mass spectrometry has had a profound impact on clinical microbiology, facilitating rapid bacterial identification through protein profile analysis. However, the application this technique is limited by challenges related to reproducibility and variability spectra, particularly in distinguishing closely strains, as exemplified typification Clostridioides difficile ribotypes. This thesis...
Healthcare-associated infections (HAIs) are a significant concern within hospital environments, with the World Health Organization (WHO) identifying them as major source of bacteriological infections. HAIs affect millions patients annually, leading to substantial morbidity and mortality. However, proportion preventable through early detection appropriate intervention isolation. Traditional methods for bacterial species strains, such antigen tests, often time-consuming hamper realtime...
This paper presents a novel approach for the classification of \ac{af} using \ac{ppg} signals treated as images. The proposed method builds upon previous research that has demonstrated promising results by converting into image representations and \ac{ecg} heatmaps matrices.The main contribution this lies in two aspects. Firstly, it introduces methodology treats images, allowing improved accuracy. Classification between \ac{nsr} is performed over MIMIC PERform Dataset achieving 100\%...