A5073970470- Respiratory Support and Mechanisms
- Sepsis Diagnosis and Treatment
- Machine Learning in Healthcare
- Inhalation and Respiratory Drug Delivery
- Artificial Intelligence in Healthcare
- Cardiac Arrest and Resuscitation
- Neonatal Respiratory Health Research
- Emergency and Acute Care Studies
- Bacterial Identification and Susceptibility Testing
- Archaeological and Historical Studies
- Mechanical Circulatory Support Devices
- COVID-19 diagnosis using AI
- Cardiac electrophysiology and arrhythmias
- Pharmacy and Medical Practices
- Cardiac Ischemia and Reperfusion
- Disaster Response and Management
- Infection Control in Healthcare
- Simulation Techniques and Applications
- Nosocomial Infections in ICU
- Model-Driven Software Engineering Techniques
- Heart Rate Variability and Autonomic Control
- Image Processing Techniques and Applications
- Neuroscience of respiration and sleep
- Cell Image Analysis Techniques
- Culinary Culture and Tourism
Aalborg University
2009-2012
Abstract Sepsis is a leading cause of mortality and early identification improves survival. With increasing digitalization health care data automated sepsis prediction models hold promise to aid in prompt recognition. Most previous studies have focused on the intensive unit (ICU) setting. Yet only small proportion develops ICU there an apparent clinical benefit identify patients earlier disease trajectory. In this cohort 82,852 hospital admissions 8038 episodes classified according Sepsis-3...
Importance Early warning scores (EWSs) are designed for in-hospital use but widely used in the prehospital field, especially select groups of patients potentially at high risk. To be useful paramedics daily clinical practice, evaluations needed predictive value EWSs based on first measured vital signs scene large cohorts covering unselected using ambulance services. Objective validate EWSs’ ability to predict mortality and intensive care unit (ICU) stay an cohort adult who ambulances....
Fast and correct classification of bacterial samples are important for accurate diagnostics treatment. Manual microscopic interpretation Gram stain is both time consuming operator dependent. The aim this study was to investigate the potential developing an automated algorithm images. We developed tested two algorithms (using image processing Casual Probabilistic Network (CPN) a Random Forest (RF) classification) A dataset 660 images including 33 microbial species (32 bacteria one fungus)...
This paper presents a novel mathematical model of alveoli, which simulates the effects tissue elasticity and surfactant on stability human alveoli. The incorporates spherical approximation to alveolar geometry, hysteretic behavior pulmonary elasticity. shows that alveolus without elastic properties lung are always at an unstable equilibrium, with capability both collapse irreversibly open infinite volume when has small opening radii. During normal tidal breathing, can becomes stable, if is...
Background: Adrenaline release and excess insulin during hypoglycemia stimulate the uptake of potassium from bloodstream, causing low plasma (hypokalemia). Hypokalemia has a profound effect on heart is associated with an increased risk malignant cardiac arrhythmias. It aim this study to develop physiological model changes better understand potassium. Method: Potassium counterregulation hypokalemia was modeled as linear function dependent absolute level. An insulin-induced using negative...
This paper presents a stratified physiological model of the respiratory mechanics during dynamic conditions. The combines existing models static lung compliance and airway resistance viscoelastic properties lungs. includes aspects pressures due to: resistance; chest wall; surface tension determined by surfactant activity; tissue elasticity; hydrostatic effects blood. is identified validated against experimentally measured flow, pressure volume profiles. simulates well amount hysteresis...
Ambulance requests by general practitioners for primary care patients (GP-requested) are often omitted in studies on increased demand within emergency but may comprise a substantial patient group. We aimed to assess acute severity, intensive unit (ICU) admission, and diagnostic pattern, including comorbidity, mortality among GP-requested ambulance patients, compared call patients. Our hypothesis was that had more severe health issues than
Background: Healthcare-associated infection (HAI) surveillance is essential for most prevention programs and continuous epidemiological data can be used to inform healthcare personal, allocate resources, evaluate interventions prevent HAIs. Many HAI systems today are based on time-consuming resource-intensive manual reviews of patient records. The objective HAI-proactive, a Swedish triple-helix innovation project, develop implement fully automated system electronic health record data....
Background: Pneumonia is the leading infectious cause of mortality globally. Artificial intelligence tools and techniques such as machine learning (ML) are increasingly seen a suitable manner to increase prediction capacity currently available in diseases. However, studies evaluating efficacy ML methods enhancing predictive existing scores for community-acquired pneumonia (CAP) limited. We aimed apply causal probabilistic network (CPN) model (SepsisFinder) predict 30-day patients with CAP....