A5062398553- Obstructive Sleep Apnea Research
- Sleep and Wakefulness Research
- Neuroscience of respiration and sleep
- Cardiovascular and Diving-Related Complications
- Cardiac Valve Diseases and Treatments
- Cardiovascular Function and Risk Factors
- ECG Monitoring and Analysis
- Cardiac Imaging and Diagnostics
- Sleep and related disorders
- IoT-based Smart Home Systems
- Restless Legs Syndrome Research
- Tracheal and airway disorders
- Non-Invasive Vital Sign Monitoring
- Vestibular and auditory disorders
- Advanced Sensor and Energy Harvesting Materials
- Pericarditis and Cardiac Tamponade
- Phonocardiography and Auscultation Techniques
- Ultrasound in Clinical Applications
- Congenital Heart Disease Studies
- Circadian rhythm and melatonin
- Context-Aware Activity Recognition Systems
- Pulmonary Hypertension Research and Treatments
- Machine Learning and Data Classification
- Anomaly Detection Techniques and Applications
- EEG and Brain-Computer Interfaces
ETH Zurich
2021-2025
Kantonsspital St. Gallen
2023-2024
University of Basel
2023
Institute of Robotics
2023
Institute of Cardiology
2023
Pleural effusion (PE) is a common chest radiography (CXR) finding in patients with advanced cardiac disease. The pathophysiology and clinical value of PE this setting are incompletely defined. We aimed to assess the haemodynamic correlates prognostic impact severe aortic stenosis (AS).
Summary Mitochondrial diseases are rare genetic disorders often accompanied by severe sleep disorders. We present the case of a 12‐year‐old boy diagnosed with primary mitochondrial disease, exhibiting ataxia, spasticity, progressive external ophthalmoplegia, cardiomyopathy and severely disrupted sleep, but no cognitive impairment. Interestingly, his parents reported improved during night train rides. Based on this observation, we installed rocking bed in patient's bedroom performed different...
Abstract Objective . Learning to classify cardiac abnormalities requires large and high-quality labeled datasets, which is a challenge in medical applications. Small datasets from various sources are often aggregated meet this requirement, resulting final dataset prone label noise due inter- intra-observer variability different expertise. It well known that can affect the performance generalizability of trained models. In work, we explore impact self-learning correction on classification...
Abstract Vestibular Stimulation (VS) has been shown to positively affect various autonomic body functions, including sleep. In the past, VS was often investigated using large and complex rocking beds that would only allow for short intervention periods in constrained lab settings. this work, we present an overview of mechanics, kinematics, dynamics, tuning our latest bed, Somnomat Casa. Its compact dimensions, comparable a standard single its connectivity, easy usability, prolonged studies...
Abstract Background In aortic stenosis (AS), left ventricular hypertrophy (LVH) is the response to pressure overload and represents substrate for a maladaptive cascade, so‐called AS‐related cardiac damage. We hypothesized that in AS patients electrocardiogram (ECG) LVH not only predicts echocardiography but also other noninvasive invasive markers of damage prognosis after valve replacement (AVR). Methods 279 with severe undergoing ECG, echocardiography, catheterization before AVR,...
Robust body position classification during sleep is crucial for closed-loop robotic interventions in position-dependent disorders. This work investigates a compact, custom-made textile pressure sensor to automatically classify recumbent positions. We implemented range of traditional methods, including Naïve Bayes, Decision Trees, and Support Vector Machines. Furthermore, we trained different machine learning models on recordings from 19 participants, with varying amount personalized training...
Sleep is essential to boost the rehabilitation outcome as it facilitates motor learning, enhances cognitive performance, and improves mood well-being. Rocking beds that provide vestibular stimulation may be a promising non-invasive alternative conventional pharmaceutical treatments for individuals with sleep problems, offering regenerative without unwanted side effects. Previous research has shown effectiveness of interventions related chosen rocking acceleration. Moreover, movement bed must...
In this work, we present a machine learning approach that is able to classify 30 cardiac abnormalities from an arbitrary number of electrocardiogram (ECG) leads. Features extracted by deep convolutional neural network are combined with hand-crafted features (demographic, morphological, and heart rate variability metrics) fed into multilayer perceptron. We employ Asymmetric Loss (ASL) function, which enables the model focus on hard but under-represented samples. To mitigate issue ground-truth...
Reliable detection of sleep positions is essential for the development technical aids patients with position-dependent sleep-related breathing disorders. We compare personalized and generalizable sleeping position classifiers using unobtrusive eight-channel pressure-sensing mats. Data six male confirmed apnea was recorded during three subsequent nights. Personalized trained leave-one-night-out cross-validation on average reached an F1-score 61.3% supine/non-supine 46.2%...
In aortic stenosis (AS), estimated glomerular filtration rate (eGFR) is an important prognostic marker but its haemodynamic determinants are unknown. We investigated the correlation between eGFR and invasive haemodynamics long-term mortality in AS patients undergoing valve replacement (AVR).We studied 503 [median (interquartile range) age 76 (69-81) years] with [indexed area .42 (.33-.49) cm2 /m2 ] cardiac catheterization prior to surgical (72%) or transcatheter (28%) AVR. Serum creatinine...
Unobtrusive sleep position classification is essential for monitoring and closed-loop intervention systems that initiate changes. In this paper, we present a novel unobtrusive under-mattress optical tactile sensor classification. The uses camera to track particles embedded in soft silicone layer, inferring the deformation of therefore providing information about pressure shear distributions applied its surface.We characterized sensitivity after placing it under conventional mattress applying...
<b>Introduction:</b> Positional interventions might be beneficial for patients with positional sleep apnoea (POSA). The aim was to assess the effect of intelligent apnoea beds (ISABel) on OSA severity and fragmentation in POSA. <b>Method:</b> Adults POSA (apnoea-hypopnoea-index (AHI) ≥10/h) were eligible. Following a baseline polysomnography, randomly allocated intervention nights ISABel1 ISABel2. In case of an or hypopnoea, elevated upper body by 50° ISABel2 induced one-side...
Robust body position classification during sleep is crucial for closed-loop robotic interventions in position-dependent disorders. This work investigates a compact, custom-made textile pressure sensor to automatically classify recumbent positions. We trained different convolutional neural networks on recordings from 21 participants, with varying amount of personalized training data (i.e. generalized inter-person classifier towards fully classifiers). The performances were compared using...
The relationship between chest radiograph (CXR) findings of pulmonary congestion and invasive hemodynamics clinical outcomes in patients with cardiac diseases is unclear. We assessed the correlation a CXR-based score (RxCS) mean artery wedge pressure (mPAWP) prognostic impact RxCS mPAWP severe aortic stenosis (AS).
Sleep is crucial in rehabilitation processes, promoting neural plasticity and immune functions. Nocturnal body postures can indicate sleep quality frequent repositioning required to prevent bedsores for bedridden patients after a stroke or spinal cord injury. Polysomnography (PSG) considered the gold standard assessment. Unobtrusive methods classifying have been presented with similar accuracy PSG, but most evaluations done research lab environments. To investigate challenges usability of...