A5005396204- Obstructive Sleep Apnea Research
- Non-Invasive Vital Sign Monitoring
- Neuroscience of respiration and sleep
- EEG and Brain-Computer Interfaces
- Heart Rate Variability and Autonomic Control
- Advanced Chemical Sensor Technologies
- Neuroscience and Neural Engineering
- Aerospace and Aviation Technology
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Respiratory Support and Mechanisms
- Sleep and Work-Related Fatigue
- Cardiovascular Health and Disease Prevention
- Cardiovascular and Diving-Related Complications
- Control Systems and Identification
- Neural dynamics and brain function
- Sleep and Wakefulness Research
- Pediatric Urology and Nephrology Studies
- Time Series Analysis and Forecasting
- Gaze Tracking and Assistive Technology
- Hemodynamic Monitoring and Therapy
- Human-Automation Interaction and Safety
- Autopsy Techniques and Outcomes
- Neural and Behavioral Psychology Studies
- Blind Source Separation Techniques
- Air Traffic Management and Optimization
Universidad de Valladolid
2015-2024
Stanford University
2019-2024
Lucile Packard Children's Hospital
2024
Albert Einstein College of Medicine
2024
Montefiore Medical Center
2024
University of Nevada, Las Vegas
2019-2024
Eurocontrol
2024
Hospital Universitario Río Hortega
2016-2023
Biomedical Research Networking Center in Bioengineering, Biomaterials and Nanomedicine
2020-2023
Instituto de Biomedicina y Genética Molecular de Valladolid
2022-2023
Lempel-Ziv complexity (LZ) and derived LZ algorithms have been extensively used to solve information theoretic problems such as coding lossless data compression. In recent years, has widely in biomedical applications estimate the of discrete-time signals. Despite its popularity a measure for biosignal analysis, question interpretability relationship other signal parameters metrics not previously addressed. We carried out an investigation aimed at gaining better understanding itself,...
Alzheimer's disease (AD) is the most common neurodegenerative disorder. Although a definite diagnosis only possible by necropsy, differential with other types of dementia and major depression should be attempted. The aim this study was to analyse electroencephalogram (EEG) background activity AD patients test hypothesis that regularity patients' EEG higher than age-matched controls. We recorded from 19 scalp electrodes in 11 Two different methods were used estimate activity: spectral entropy...
Abstract Pulse oximetry is routinely used to non-invasively monitor oxygen saturation levels. A low level in the blood means tissues, which can ultimately lead organ failure. Yet, contrary heart rate variability measures, a field has seen development of stable standards and advanced toolboxes software, no such open tools exist for continuous time series analysis. The primary objective this research was identify, implement validate key digital biomarkers (OBMs) purpose creating standard...
Rationale: The vast majority of children around the world undergoing adenotonsillectomy for obstructive sleep apnea–hypopnea syndrome (OSA) are not objectively diagnosed by nocturnal polysomnography because access availability and cost issues. Automated analysis oximetry (nSpO2), which is readily globally available, could potentially provide a reliable convenient diagnostic approach pediatric OSA.Methods: Deidentified nSpO2 recordings from total 4,191 originating 13 laboratories were...
This study aims at assessing the usefulness of deep learning to enhance diagnostic ability oximetry in context automated detection pediatric obstructive sleep apnea (OSA). A total 3196 blood oxygen saturation (SpO2) signals from children were used for this purpose. convolutional neural network (CNN) architecture was trained using 20-min SpO2 segments training set (859 subjects) estimate number apneic events. CNN hyperparameters tuned Bayesian optimization validation (1402 subjects). model...
Abstract Obstructive sleep apnea (OSA) is a serious medical condition with high prevalence, although diagnosis remains challenge. Existing home tests may provide acceptable performance but have shown several limitations. In this retrospective study, we used 12,923 polysomnography recordings from six independent databases to develop and evaluate deep learning model, called OxiNet, for the estimation of apnea-hypopnea index oximetry signal. We evaluated OxiNet across ethnicity, age, sex,...
Abstract Stillbirth rates have stalled or increased in some European countries during the last decade. We investigate to what extent time-trends and between-country differences stillbirth are explained by changing prevalence of advanced maternal age teenage pregnancies multiple births. analysed data on stillbirths live births multiplicity from 2010 2021 25 using Kitagawa decomposition separate rate into compositional components. Rates significantly decreased six countries, but two. Changes...
This study focuses on the analysis of blood oxygen saturation (SaO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ) from nocturnal pulse oximetry (NPO) to help in diagnosis obstructive sleep apnea (OSA) syndrome. A population 148 patients suspected suffering OSA syndrome was studied. wide set 16 features used characterize changes SaO profile during night. Our feature included common statistics time and frequency domains, conventional...
Approximate entropy (ApEn) is a family of statistics introduced as quantification regularity in time series without any priori knowledge about the system generating them. The aim this preliminary study was to assess whether analysis arterial oxygen saturation (SaO2) signals from overnight pulse oximetry by means ApEn could yield essential information on diagnosis obstructive sleep apnea (OSA) syndrome. We analyzed SaO2 187 subjects: 111 with positive OSA and 76 negative OSA. divided our data...
Complexity, costs, and waiting list issues demand a simplified alternative for sleep apnea-hypopnea syndrome (SAHS) diagnosis. The blood oxygen saturation signal (SpO2) carries useful information about SAHS can be easily acquired from overnight oximetry. In this study, SpO2 single-channel recordings 320 subjects were obtained at patients' homes used to automatically obtain statistical, spectral, nonlinear, clinical SAHS-related information. Relevant, nonredundant data these analyses...
Practical motor imagery-based brain computer interface (MI-BCI) applications are limited by the difficult to decode signals in a reliable way. In this paper, we propose processing framework address non-stationarity, as well handle spectral, temporal, and spatial characteristics associated with execution of tasks. Stacked generalization is used exploit power classifier ensembles for combining information coming from multiple sources reducing existing uncertainty EEG signals. The outputs...
This paper presents an electroencephalographic (EEG) P300-based brain-computer interface (BCI) Internet browser. The system uses the "odd-ball" row-col paradigm for generating P300 evoked potentials on scalp of user, which are immediately processed and translated into web browser commands. There were previous approaches controlling a BCI However, to best our knowledge, none them was focused assistive context, failing test their applications with suitable number end users. In addition, all...
Abstract The most appropriate physiological signals to develop simplified as well accurate screening tests for obstructive sleep apnoea (OSA) remain unknown. This study aimed at assessing whether joint analysis of at-home oximetry and airflow recordings by means machine-learning algorithms leads a significant diagnostic performance increase compared single-channel approaches. Consecutive patients showing moderate-to-high clinical suspicion OSA were involved. apnoea-hypopnoea index (AHI) from...
Automatic deep-learning models used for sleep scoring in children with obstructive apnea (OSA) are perceived as black boxes, limiting their implementation clinical settings. Accordingly, we aimed to develop an accurate and interpretable model staging using single-channel electroencephalogram (EEG) recordings. We EEG signals from the Childhood Adenotonsillectomy Trial (CHAT) dataset (n = 1637) a database 980). Three distinct architectures were explored automatically classify stages data....
Abstract Background RNA sequencing combined with machine learning techniques has provided a modern approach to the molecular classification of cancer. Class predictors, reflecting disease class, can be constructed for known tissue types using gene expression measurements extracted from cancer patients. One challenge current predictors is that they often have suboptimal performance estimates when integrating datasets generated different labs. Often, quality data variable, procured...
Nocturnal oximetry is an attractive option for the diagnosis of obstructive sleep apnoea (OSA) syndrome because its simplicity and low cost compared to polysomnography (PSG).The present study assesses non-linear analysis blood oxygen saturation (SaO 2 ) from nocturnal as a diagnostic test discriminate between OSA positive negative patients.A sample 187 referred outpatients, clinically suspected having OSA, were studied using performed simultaneously with complete PSG.A was found 111 cases,...
The purpose of this study is to evaluate the usefulness boosting algorithm AdaBoost (AB) in context sleep apnea-hypopnea syndrome (SAHS) diagnosis.We characterize SAHS single-channel airflow (AF) signals from 317 subjects by extraction spectral and nonlinear features. Relevancy redundancy analyses are conducted through fast correlation-based filter derive optimum set features among them. These used feed classifiers based on linear discriminant analysis (LDA) classification regression trees...
Nocturnal polysomnography (PSG) is the gold-standard for sleep apnea-hypopnea syndrome (SAHS) diagnosis. It provides value of index (AHI), which used to evaluate SAHS severity. However, PSG costly, complex, and time-consuming. We present a novel approach automatic estimation AHI from nocturnal oxygen saturation (SaO <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">$_2$</tex></formula> ) recordings...
This study is aimed at assessing the usefulness of different feature selection and classification methodologies in context sleep apnea hypopnea syndrome (SAHS) detection. Feature extraction, stages were applied to analyze blood oxygen saturation (SaO 2 ) recordings order simplify polysomnography (PSG), gold standard diagnostic methodology for SAHS. Statistical, spectral nonlinear measures computed compose initial set. Principal component analysis (PCA), forward stepwise (FSFS) genetic...
Nocturnal oximetry has become known as a simple, readily available, and potentially useful diagnostic tool of childhood obstructive sleep apnea (OSA). However, at-home respiratory polygraphy (HRP) remains the preferred alternative to polysomnography (PSG) in unattended settings. The aim this study was twofold: (1) design assess novel methodology for pediatric OSA screening based on automated analysis oxyhemoglobin saturation (SpO2), (2) compare its performance with HRP.SpO2 recordings were...