A5016677781- Sepsis Diagnosis and Treatment
- Machine Learning in Healthcare
- Clinical Reasoning and Diagnostic Skills
- COVID-19 Clinical Research Studies
- SARS-CoV-2 and COVID-19 Research
- Emergency and Acute Care Studies
- Advanced X-ray and CT Imaging
- Phonocardiography and Auscultation Techniques
- Computational Drug Discovery Methods
- Healthcare cost, quality, practices
- Artificial Intelligence in Healthcare and Education
- Digital Imaging for Blood Diseases
- Radiation Dose and Imaging
- Artificial Intelligence in Healthcare
- Statistical and Computational Modeling
- Long-Term Effects of COVID-19
- Respiratory Support and Mechanisms
- Radiology practices and education
Cabell Huntington Hospital
2017-2021
Marshall University
2017-2021
Currently, physicians are limited in their ability to provide an accurate prognosis for COVID-19 positive patients. Existing scoring systems have been ineffective identifying patient decompensation. Machine learning (ML) may offer alternative strategy. A prospectively validated method predict the need ventilation patients is essential help triage patients, allocate resources, and prevent emergency intubations associated risks. In a multicenter clinical trial, we evaluated performance of...
Background Severe sepsis and septic shock are among the leading causes of death in USA. While early prediction severe can reduce adverse patient outcomes, remains one most expensive conditions to diagnose treat. Objective The purpose this study was evaluate effect a machine learning algorithm for on in-hospital mortality, hospital length stay 30-day readmission. Design Prospective clinical outcomes evaluation. Setting Evaluation performed multiyear, multicentre data set real-world containing...
Background: Machine learning methods have been developed to predict the likelihood of a given event or classify patients into two more diagnostic categories. Digital twin models, which forecast entire trajectories patient health data, potential applications in clinical trials and management. Methods: In this study, we apply digital model based on variational autoencoder population who went experience an ischemic stroke. The twin’s ability features was assessed with regard its measurement...
Background Racial disparities in health care are well documented the United States. As machine learning methods become more common settings, it is important to ensure that these do not contribute racial through biased predictions or differential accuracy across groups. Objective The goal of research was assess a algorithm intentionally developed minimize bias in-hospital mortality between white and nonwhite patient Methods Bias minimized preprocessing training data. We performed...
Abstract Background Severe sepsis and septic shock are among the leading causes of death in United States remains one most expensive conditions to diagnose treat. Accurate early diagnosis treatment can reduce risk adverse patient outcomes, but efficacy traditional rule-based screening methods is limited. The purpose this study was develop validate a machine learning algorithm (MLA) for severe prediction up 48 h before onset using diverse dataset. Methods Retrospective analysis performed on...
Abstract Introduction Sepsis is a major health crisis in US hospitals, and several clinical identification systems have been designed to help care providers with early diagnosis of sepsis. However, many these demonstrate low specificity or sensitivity, which limits their utility. We evaluate the effects machine learning algodiagnostic (MLA) sepsis prediction detection system using before-and-after study performed at Cabell Huntington Hospital (CHH) Huntington, West Virginia. Prior this...
Therapeutic agents for the novel coronavirus disease 2019 (COVID-19) have been proposed, but evidence supporting their use is limited. A machine learning algorithm was developed in order to identify a subpopulation of COVID-19 patients whom hydroxychloroquine associated with improved survival; this population might be relevant study clinical trial. pragmatic trial conducted at six United States hospitals. We enrolled that were admitted between 10 March and 4 June 2020. Treatment not...
Abstract Objective To validate performance of a machine learning algorithm for severe sepsis determination up to 48 hours before onset, and evaluate the effect on in-hospital mortality, hospital length stay, 30-day readmission. Setting This cohort study includes combined retrospective analysis clinical outcomes evaluation: dataset containing 510,497 patient encounters from 461 United States health centers analysis, multiyear, multicenter data set real-world 75,147 nine hospitals evaluation....
During a routine NRC inspection, review of historical occupational dosimetry monitoring data for interventional radiology physician AUs was questioned regarding unexpectedly low results. This interpreted to be an indicator noncompliance with the wearing dose devices and, therefore, required occupation reconstructions in order estimate actual dose. In effort comply requirements, AU radiologists diligently began their whole-body and ring dosimeters during all procedures including Y-90,...
<sec> <title>BACKGROUND</title> Racial disparities in health care are well documented the United States. As machine learning methods become more common settings, it is important to ensure that these do not contribute racial through biased predictions or differential accuracy across groups. </sec> <title>OBJECTIVE</title> The goal of research was assess a algorithm intentionally developed minimize bias in-hospital mortality between white and nonwhite patient <title>METHODS</title> Bias...