A5069723888- Cardiomyopathy and Myosin Studies
- Machine Learning in Healthcare
- Sepsis Diagnosis and Treatment
- Insurance, Mortality, Demography, Risk Management
- Cardiac pacing and defibrillation studies
- Respiratory Support and Mechanisms
- Neurogenetic and Muscular Disorders Research
- Intensive Care Unit Cognitive Disorders
- Viral Infections and Immunology Research
- Non-Invasive Vital Sign Monitoring
- Heart Rate Variability and Autonomic Control
- Biomedical Text Mining and Ontologies
- Cardiovascular Function and Risk Factors
- Muscle Physiology and Disorders
- Electronic Health Records Systems
- Cardiac Arrest and Resuscitation
Amsterdam University Medical Centers
2022-2024
Vrije Universiteit Amsterdam
2022-2024
University of Amsterdam
2023
Erasmus MC
2019-2022
With the advent of artificial intelligence, secondary use routinely collected medical data from electronic healthcare records (EHR) has become increasingly popular. However, different EHR systems typically names for same concepts. This obviously hampers scalable model development and subsequent clinical implementation decision support. Therefore, converting original parameter to a so-called ontology, standardized set predefined concepts, is necessary but time-consuming labor-intensive. We...
For mechanically ventilated critically ill COVID-19 patients, prone positioning has quickly become an important treatment strategy, however, is labor intensive and comes with potential adverse effects. Therefore, identifying which intubated patients will benefit may help allocate resources. From the multi-center Dutch Data Warehouse of ICU from 25 hospitals, we selected all 3619 episodes in 1142 invasively patients. We excluded longer than 24 h. Berlin ARDS criteria were not formally...
Reinforcement Learning (RL) has recently found many applications in the healthcare domain thanks to its natural fit clinical decision-making and ability learn optimal decisions from observational data. A key challenge adopting RL-based solution practice, however, is inclusion of existing knowledge learning a suitable solution. Existing e.g. medical guidelines may improve safety solutions, produce better balance between short- long-term outcomes for patients increase trust adoption by...
Introduction: Benchmarking intensive care units for audit and feedback is frequently based on comparing actual mortality versus predicted mortality. Traditionally, prediction models rely a limited number of input variables significant manual data entry curation. Using automatically extracted electronic health record may be promising alternative. However, adequate comparative performance between these approaches currently lacking.Methods: The freely available highly granular AmsterdamUMCdb...
Background: Implantable cardioverter-defibrillators (ICDs) are frequently used for primary and secondary prevention in patients with cardiomyopathies due to different etiologies. However, the long-term outcome noncompaction cardiomyopathy (NCCM) is still lacking. This study summarises of implantable cardioverter-defibrillator (ICD) therapy compared those dilated (DCM) or hypertrophic (HCM).Methods: Prospective data from our single-centre ICD registry were analyze interventions survival NCCM...