A5015249430- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare and Education
- Biomedical Text Mining and Ontologies
- Nosocomial Infections in ICU
- Electronic Health Records Systems
- Emergency and Acute Care Studies
- Parkinson's Disease Mechanisms and Treatments
- Infrared Thermography in Medicine
- Medical Imaging and Analysis
- Neurological disorders and treatments
- Blood disorders and treatments
- Cellular transport and secretion
- Hyperglycemia and glycemic control in critically ill and hospitalized patients
- AI in Service Interactions
- Natural Language Processing Techniques
- Atrial Fibrillation Management and Outcomes
- Sepsis Diagnosis and Treatment
- Topic Modeling
- COVID-19 diagnosis using AI
- Rheumatoid Arthritis Research and Therapies
- Text Readability and Simplification
Maersk (Denmark)
2019-2023
University of Southern Denmark
2019-2023
Aarhus University
2023
The development of standardised methods for ultrasound (US) scanning and evaluation synovitis activity by the OMERACT-EULAR Synovitis Scoring (OESS) system is a major step forward in use US diagnosis monitoring patients with inflammatory arthritis. variation interpretation disease on images can affect diagnosis, treatment outcomes clinical trials. We, therefore, set out to investigate if we could utilise neural network architecture Doppler images, using OESS scoring system.Two...
In natural language processing, benchmarks are used to track progress and identify useful models. Currently, no benchmark for Danish clinical word embeddings exists. This paper describes the development of a embeddings. The consists ten datasets: eight intrinsic two extrinsic. Moreover, we evaluate trained on text from domain, general practitioner domain established benchmark. All tasks publicly available.
Abstract Objectives This study evaluated if medical doctors could identify more hemorrhage events during chart review in a clinical setting when assisted by an artificial intelligence (AI) model and doctors' perception of using the AI model. Methods To develop model, sentences from 900 electronic health records were labeled as positive or negative for categorized into one 12 anatomical locations. The was on test cohort consisting 566 admissions. Using eye-tracking technology, we investigated...
Clinical machine learning algorithms have shown promising results and could potentially be implemented in clinical practice to provide diagnosis support improve patient treatment. Barriers for realisation of the algorithms’ full potential include bias which is systematic unfair discrimination against certain individuals favor others.The objective this work measure anatomical text algorithms. We define as algorithmic outcomes patients with medical conditions specific locations. degree across...
Objectives: Health systems worldwide experience limited resources, highlighting the need for automation in health-care. Diagnostic robots could aid health professionals areas which currently require human skills. In this study, we investigate factors facilitating acceptance of diagnostic work-up healthcare Denmark. Methods: The study was a cross-sectional survey on cohort representative adult population It comprised an electronic questionnaire sent to adults (≥18 years) living Results: Among...
Bleeding can be a life-threatening condition which occurs for 3.2% of medical patients. Information about previous bleeding and site is used to predict the risk future guide anticoagulant treatment. However, obtaining this information time-consuming task as it contained in free text electronic health records. Previous research has mainly been focused on extracting events but does not classify important assessing severity bleeding. This study creates first dataset developing evaluating...
Abstract Purpose This study addresses the lack of information about bleeding incidences, location and risk factors in admitted children. The primary objective this was to determine incidence children hospital. Methods In an observational cohort study, first admittance 13,842 (< 18years) Odense University Hospital from 2015–2020 analyzed. Bleeding episodes anatomical were identified electronic health record (EHR) text using a combination artificial intelligence manual validation....
This study addresses the lack of information about bleeding incidences, location and risk factors in children admitted to hospital. The primary objective this was determine incidence Methods : In a retrospective observational cohort study, first admittance 13,842 (<18 years old) Odense University Hospital from 2015-2020 analyzed. Bleeding episodes anatomical were identified electronic health record (EHR) text using combination artificial intelligence manual validation. determined...
<title>Abstract</title> Aggregation of α-synuclein (α-syn) is critical to the development synucleinopathies such as Parkinson’s Disease (PD), yet we do not have any effective therapy against these diseases. α-syn accumulates insoluble amyloid in intracellular Lewy Bodies (LBs) but also forms soluble αSOs (αSOs) which are thought be even more cytotoxic than fibrils. We lack tools detect and block unwanted activities αSOs. To address this, raised monoclonal antibodies (mAbs) different αSOs,...
<h3>Background</h3> The development of standardized methods for ultrasound (US) scanning and evaluation synovitis activity by the OMERACT-EULAR Synovitis Scoring (OESS) system, is a major step forward in use US diagnosis monitoring patients with inflammatory arthritis. variation interpretation disease on images can affect diagnosis, treatment outcomes clinical trials. <h3>Objectives</h3> To investigate if we could utilize neural network architecture Doppler images, using OESS scoring system....