A5078056045- Acute Myocardial Infarction Research
- ECG Monitoring and Analysis
- Emergency and Acute Care Studies
- Machine Learning in Healthcare
- Cardiac Arrest and Resuscitation
- Heart Failure Treatment and Management
- Cardiac Imaging and Diagnostics
- Renal function and acid-base balance
- Pain Management and Treatment
- Phonocardiography and Auscultation Techniques
- Artificial Intelligence in Healthcare
- Myasthenia Gravis and Thymoma
- Heart Rate Variability and Autonomic Control
- Cardiac Health and Mental Health
- Hyperglycemia and glycemic control in critically ill and hospitalized patients
- Patient Safety and Medication Errors
- Cardiac electrophysiology and arrhythmias
- Chronic Obstructive Pulmonary Disease (COPD) Research
Skåne University Hospital
2021-2024
Lund University
2021-2024
Abstract Aims In the present study, we aimed to evaluate performance of machine learning (ML) models for identification acute myocardial infarction (AMI) or death within 30 days among emergency department (ED) chest pain patients. Methods and results Using data from 9519 consecutive ED patients, created ML based on logistic regression artificial neural networks. Model inputs included sex, age, ECG first blood tests at patient presentation: High sensitivity TnT (hs-cTnT), glucose, creatinine,...
Objective Computerized decision-support tools may improve diagnosis of acute myocardial infarction (AMI) among patients presenting with chest pain at the emergency department (ED). The primary aim was to assess predictive accuracy machine learning algorithms based on paired high-sensitivity cardiac troponin T (hs-cTnT) concentrations varying sampling times, age, and sex in order rule or out AMI. Methods In this register-based, cross-sectional diagnostic study conducted retrospectively 5695 2...
Background. Glucose is emerging as a biomarker for early and safe rule-out of acute myocardial infarction in emergency department (ED) chest pain patients. We evaluated the diagnostic accuracy dual testing with high sensitivity TnT (hs-cTnT) glucose prediction major adverse cardiac events (MACE) within 30 days. Methods. This was secondary analysis single-center prospective observational study 1167 ED chest-pain patients hs-cTnT at presentation (0 h), 1 h later. tested addition <5.6 mmol/L to...
At the emergency department (ED), it is important to quickly and accurately determine which patients are likely have a major adverse cardiac event (MACE). Machine learning (ML) models can be used aid physicians in detecting MACE, improving performance of such an active area research. In this study, we sought if ML improved by including prior electrocardiogram (ECG) from each patient. To that end, trained several predict MACE within 30 days, both with without ECGs, using data collected 19,499...
<b><i>Introduction:</i></b> With the implementation of early reperfusion therapy, number complications in patients with acute coronary syndrome (ACS) has diminished significantly. However, ACS are still routinely admitted to units high-level monitoring such as or intensive care unit (CCU/ICU). The cost these admissions is high and there often a shortage beds. aim this study was analyze contemporary emergency department (ED) map patient management....
Abstract Background In the European Union alone, more than 100 million people present to emergency department (ED) each year, and this has increased steadily year-on-year by 2–3%. Better patient management decisions have potential reduce ED crowding, number of diagnostic tests, use inpatient beds, healthcare costs. Methods We established Skåne Emergency Medicine (SEM) cohort for developing clinical decision support systems (CDSS) based on artificial intelligence or machine learning as well...
Simulation-based studies indicate that crisis checklist use improves management of patients with critical conditions in the emergency department (ED). An interview-based study suggests an manual (EM)-a collection checklists-improves clinical perioperative crises. There is a need for in-depth prospective EM during practice, evaluating when and how EMs are used impact on patient management. This 6-month long prospectively evaluates digital priority 1 Skåne University Hospital at Lund's ED....
At the emergency department (ED), it is important to quickly and accurately determine which patients are likely have a major adverse cardiac event (MACE). Machine learning (ML) models can be used aid physicians in detecting MACE, improving performance of such an active area research. In this study, we sought if ML improved by including prior electrocardiogram (ECG) from each patient. To that end, trained several predict MACE both with without ECGs, using data collected 19499 consecutive...
Abstract Background Machine learning approaches are increasingly being explored for use in healthcare systems, but there is a trade-off between increased accuracy and decreased explainability with more complex models. We aimed to evaluate the diagnostic performance acute myocardial infarction (AMI) or death within 30 days of index visit. models were trained using demographic factors, ECG blood markers, compare them single high sensitivity TnT (hs-cTnT) value. Methods Using records from 9519...