Machine Learning-Enabled COVID-19 Prognostic Tool Supports Clinical Decision-Making for Emergency Department Discharge
|
By HospiMedica International staff writers Posted on 26 Jan 2022 |
|
Researchers who evaluated the real-time performance of a machine learning (ML)-enabled, COVID-19 prognostic tool found that it supported clinical decision-making for emergency department discharge at hospitals.
A multidisciplinary team of intensivists, hospitalists, emergency doctors, and informaticians at the University of Minnesota Medical School (Minneapolis, MN, USA) evaluated the tool which delivered clinical decision support to emergency department providers to facilitate shared decision-making with patients regarding discharge.
The University research team successfully developed and implemented a COVID-19 prediction model that performed well across gender, race and ethnicity for three different outcomes. The logistic regression algorithm created to predict severe COVID-19 performed well in the persons under investigation, although developed on a COVID-19 positive population.
A logistic regression model ML-enabled can be developed, validated, and implemented as clinical decision support across multiple hospitals while maintaining high performance in real-time validation and remaining equitable. The researchers recommend that the effect on patient outcomes and resource use needs to be evaluated and further researched with the ML model.
“COVID-19 has burdened healthcare systems from multiple different facets, and finding ways to alleviate stress is crucial,” said Dr. Monica Lupei, an assistant professor at the U of M Medical School and medical director M Health Fairview University of Minnesota Medical Center - West Bank. “Clinical decision systems through ML-enabled predictive modeling may add to patient care, reduce undue decision-making variations and optimize resource utilization — especially during a pandemic.”
Related Links:
University of Minnesota Medical School
Latest COVID-19 News
- Low-Cost System Detects SARS-CoV-2 Virus in Hospital Air Using High-Tech Bubbles
- World's First Inhalable COVID-19 Vaccine Approved in China
- COVID-19 Vaccine Patch Fights SARS-CoV-2 Variants Better than Needles
- Blood Viscosity Testing Can Predict Risk of Death in Hospitalized COVID-19 Patients
- ‘Covid Computer’ Uses AI to Detect COVID-19 from Chest CT Scans
- MRI Lung-Imaging Technique Shows Cause of Long-COVID Symptoms
- Chest CT Scans of COVID-19 Patients Could Help Distinguish Between SARS-CoV-2 Variants
- Specialized MRI Detects Lung Abnormalities in Non-Hospitalized Long COVID Patients
- AI Algorithm Identifies Hospitalized Patients at Highest Risk of Dying From COVID-19
- Sweat Sensor Detects Key Biomarkers That Provide Early Warning of COVID-19 and Flu
- Study Assesses Impact of COVID-19 on Ventilation/Perfusion Scintigraphy
- CT Imaging Study Finds Vaccination Reduces Risk of COVID-19 Associated Pulmonary Embolism
- Third Day in Hospital a ‘Tipping Point’ in Severity of COVID-19 Pneumonia
- Longer Interval Between COVID-19 Vaccines Generates Up to Nine Times as Many Antibodies
- AI Model for Monitoring COVID-19 Predicts Mortality Within First 30 Days of Admission
- AI Predicts COVID Prognosis at Near-Expert Level Based Off CT Scans
Channels
Artificial Intelligence
view channel
AI Tool Uses Mammograms to Detect Common Cardiovascular Diseases
Cardiovascular disease, encompassing hypertension, ischemic heart disease, and stroke, is the leading cause of death in women. Many cases are detected late, as symptoms can be subtle and routine screening... Read more
AI Tool Predicts Post-Heart Attack Trajectories to Personalize Follow-Up
Acute myocardial infarction (heart attack) survivors often develop new comorbidities and complications that unfold over years. Predicting which patients will deteriorate and where problems will arise remains... Read more
Critical Care
view channel
Wearable Hormone Monitor Enables At-Home Detection of Primary Aldosteronism
Primary aldosteronism, a hormone disorder that affects up to one in five people with hypertension, increases risks of heart disease, stroke and diabetes. Many cases are missed because routine testing is... Read more
Contactless AI Tool Detects Hypertension and Diabetes from Facial Video
Hypertension and diabetes are widespread yet often undiagnosed, driving preventable cardiovascular morbidity and mortality. Screening typically depends on clinic visits or wearable devices, which can limit... Read more
Surgical Techniques
view channel
Biodegradable Gastric Stent Could Eliminate Repeat Procedures After Bariatric Surgery
Gastric leaks are a serious complication after weight-loss surgery that can lead to infection, prolonged hospitalization, and repeated interventions. Conventional drainage stents were designed for the... Read more
Robot-Assisted Surgery Shows Advantages Over Laparoscopy in Gastric Cancer
Gastric cancer is most often treated with surgery, yet minimally invasive techniques can be technically challenging. Laparoscopic gastrectomy reduces recovery time compared with open surgery but relies... Read more
Patient Care
view channel
Multicenter Study Quantifies Delays in Care for Emergency Department Boarders
Emergency department (ED) boarding—the practice of keeping admitted patients in the ED while awaiting an inpatient bed—creates hazardous delays in definitive care. Prolonged transitions expose older and... Read more
Real-Time Radiation Monitor Supports Safer Fluoroscopy-Guided Procedures
Fluoroscopy-guided procedures expose clinicians to scatter radiation that accumulates over time, creating persistent occupational risks in cath labs and interventional suites. Traditional badges typically... Read more
Medical Imaging
view channel
Study Links Thymus Radiation Dose to Poorer Outcomes in Lung Cancer
Collateral radiation to the thymus during therapy for non-small cell lung cancer (NSCLC) may compromise antitumor immunity and disease control. The thymus is a small immune organ in the upper chest that... Read more
Automated AI Tool Enables Uncertainty-Aware Meningioma Volume Tracking on MRI
Magnetic resonance imaging (MRI) guides diagnosis and monitoring in brain tumors, yet routine measurements often rely on subjective reads or simplified two-dimensional calculations. These methods can miss... Read more
Health IT
view channel
Imaging Tool Quantifies Calcinosis Cutis Volume to Monitor Treatment
Calcinosis cutis involves calcium deposits in the skin or soft tissues that can develop anywhere in the body, causing pain, impaired mobility, and disability. Lesions along the spine or buttocks can make... Read more
Digital Symptom Monitoring Supports More Personalized Breast Cancer Care
Metastatic breast cancer, in which tumors spread to other organs, is incurable but increasingly managed with modern systemic therapies. As more treatments shift from hospital infusions to oral or at-home... Read more
Point of Care
view channel
Microneedle Patch Enables At-Home Monitoring of Acute Kidney Injury
Kidney disease is often silent in its early stages, making timely detection difficult outside clinical settings. Early biomarkers such as neutrophil gelatinase–associated lipocalin can require blood draws... Read more
Ultrathin Metasurface Could Bring Quantitative Phase Imaging to Portable Devices
Point-of-care imaging often depends on bulky optical systems that have difficulty visualizing nearly transparent cells and tissues without staining. These limitations can slow diagnosis and restrict use... Read more
Business
view channel
Philips and Imricor Collaboration Advances MRI-Guided Cardiac Procedures
Cardiac arrhythmias affect millions of people worldwide and are often treated with catheter ablation. These procedures typically rely on X-ray fluoroscopy, which provides only indirect visualization of... Read more
Abbott LAA Occluder Gains CE Mark for AFib Stroke Risk Reduction
Atrial fibrillation increases stroke risk because blood clots often form in the left atrial appendage. For patients who cannot tolerate long-term anticoagulation, minimally invasive closure can provide... Read more
FDA Seeks Feedback on Regulating Generative AI Medical Devices
Generative artificial intelligence (AI) is rapidly entering clinical workflows, offering tools that could enhance patient care while introducing risks that differ from those of traditional software.... Read more