A5074764843- ECG Monitoring and Analysis
- Cardiac Arrest and Resuscitation
- Acute Myocardial Infarction Research
- EEG and Brain-Computer Interfaces
- Venous Thromboembolism Diagnosis and Management
- Non-Invasive Vital Sign Monitoring
- Cardiac electrophysiology and arrhythmias
- Attention Deficit Hyperactivity Disorder
- Artificial Intelligence in Healthcare
- Cell Image Analysis Techniques
- Advanced Chemical Sensor Technologies
- Behavioral and Psychological Studies
- Healthcare Technology and Patient Monitoring
- Mindfulness and Compassion Interventions
- Machine Learning in Materials Science
- Gas Sensing Nanomaterials and Sensors
- Anxiety, Depression, Psychometrics, Treatment, Cognitive Processes
- Music Therapy and Health
- AI in cancer detection
- Phonocardiography and Auscultation Techniques
- Analog and Mixed-Signal Circuit Design
- Analytical Chemistry and Sensors
- Cardiac pacing and defibrillation studies
- Machine Learning in Healthcare
- Cardiac Arrhythmias and Treatments
University of Pittsburgh
2021-2025
University of Pittsburgh Medical Center
2024
Patients with occlusion myocardial infarction (OMI) and no ST-elevation on presenting electrocardiogram (ECG) are increasing in numbers. These patients have a poor prognosis would benefit from immediate reperfusion therapy, but, currently, there accurate tools to identify them during initial triage. Here we report, our knowledge, the first observational cohort study develop machine learning models for ECG diagnosis of OMI. Using 7,313 consecutive multiple clinical sites, derived externally...
Abstract Background and Aims The importance of risk stratification in patients with chest pain extends beyond diagnosis immediate treatment. This study sought to evaluate the prognostic value electrocardiogram feature-based machine learning models risk-stratify all-cause mortality those pain. Methods was a prospective observational cohort consecutive, non-traumatic All-cause death ascertained from multiple sources, including CDC National Death Index registry. Six were trained for survival...
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Objective:</i> Pain assessment in children continues to challenge clinicians and researchers, as subjective experiences of pain require inference through observable behaviors, both involuntary deliberate. The presented approach supplements the self-report-based method by fusing electrodermal activity (EDA) recordings with video facial expressions develop an objective metric. Such is specifically...
In this paper we describe ECG-SMART-NET for identification of occlusion myocardial infarction (OMI). OMI is a severe form heart attack characterized by complete blockage one or more coronary arteries requiring immediate referral cardiac catheterization to restore blood flow the heart. Two thirds cases are difficult visually identify from 12-lead electrocardiogram (ECG) and can be potentially fatal if not identified in timely fashion. Previous works on topic scarce, current state-of-the-art...
Mindfulness has growing empirical support for improving emotion regulation in individuals with Autism Spectrum Disorder (ASD). is cultivated through meditation practices. Assessing the role of mindfulness challenging given reliance on self-report tools. Electroencephalography (EEG) successfully quantified neural responses to emotional arousal and other populations, making it ideal objectively measure before after (MF) practice among ASD. We performed an EEG-based analysis during a resting...
Abstract Patients with occlusion myocardial infarction (OMI) and no ST-elevation on presenting ECG are increasing in numbers. These patients have a poor prognosis would benefit from immediate reperfusion therapy, but we currently accurate tools to identify them during initial triage. Herein, report the first observational cohort study develop machine learning models for diagnosis of OMI. Using 7,313 consecutive multiple clinical sites, derived externally validated an intelligent model that...
Modern developments in gas sensor technology include a decrease size and an increase sensitivity selectivity. These improvements, paired with postprocessing tools, such as machine learning, are pushing detection toward viability for complex tasks, volatile organic compound (VOC) analysis human breath. In our research, we use array fabricated lab featuring hybrid combination of metals polymers [palladium (Pd), zinc oxide (ZnO), polypyrrole (PPy), polyaniline (PANI)] designed to detect range...
Abstract Funding Acknowledgements Type of funding sources: Public grant(s) – National budget only. Main source(s): Heart, Lung, and Blood Institute (NHLBI) Center for Advancing Translational Sciences (NCATS). Background The importance risk stratification in patients with suspected acute coronary syndrome (ACS) extends beyond diagnosis immediate treatment. It influences the precision care delivery allocation resources to those at highest adverse events. Purpose We sought evaluate prognostic...
Persistent hypothermia after cardiopulmonary bypass (CPB) in neonates with congenital heart defects (CHD) has been historically considered benign despite lack of evidence on its prognostic significance.
Deep learning (DL) models offer improved performance in electrocardiogram (ECG)-based classification over rule-based methods. However, for widespread adoption by clinicians, explainability methods, like saliency maps, are essential. On a subset of 100 ECGs from patients with chest pain, we generated maps using previously validated convolutional neural network occlusion myocardial infarction (OMI) classification. Three clinicians reviewed ECG-saliency map dyads, first assessing the likelihood...
Introduction: Neonatal hypothermia (< 36.5 o C) after CPB is considered benign despite lack of evidence on its prognostic significance. Question: Are group-based trajectory modeling (GBTM), k-means, and self-organizing map (SOM) clustering approaches clinically useful for evaluating their associations with important outcomes? Aims: Identify distinct postoperative temperature trajectories in neonates using novel machine learning (ML) methods, corroborate findings, evaluate value outcomes....