A5069913933- Mechanical Circulatory Support Devices
- Heart Failure Treatment and Management
- Cardiovascular Function and Risk Factors
- Cardiac Structural Anomalies and Repair
- Congenital Heart Disease Studies
- Artificial Intelligence in Healthcare and Education
- Transplantation: Methods and Outcomes
- Machine Learning in Healthcare
- Cardiac Imaging and Diagnostics
- Amyloidosis: Diagnosis, Treatment, Outcomes
- Chronic Disease Management Strategies
- Radiomics and Machine Learning in Medical Imaging
- COVID-19 diagnosis using AI
- Cardiac Arrest and Resuscitation
- Topic Modeling
- Cardiovascular Disease and Adiposity
- Health Systems, Economic Evaluations, Quality of Life
- Parathyroid Disorders and Treatments
- Natural Language Processing Techniques
- Advanced X-ray and CT Imaging
- Electrolyte and hormonal disorders
- Colorectal Cancer Screening and Detection
- Blood Pressure and Hypertension Studies
- Primary Care and Health Outcomes
- Methodology and Impact of Social Science Research
Medical University of South Carolina
2023-2025
Northwestern Medicine
2019-2024
St George's Hospital
2024
Northwestern University
2016-2023
Northwestern Memorial Hospital
2016-2023
Cardiovascular Institute of the South
2020
Anoka-Ramsey Community College
2013
University of North Carolina at Chapel Hill
2010-2013
Duke University
2009
Saint George Hospital
2007
Background There are characteristic findings of coronavirus disease 2019 (COVID-19) on chest images. An artificial intelligence (AI) algorithm to detect COVID-19 radiographs might be useful for triage or infection control within a hospital setting, but prior reports have been limited by small data sets, poor quality, both. Purpose To present DeepCOVID-XR, deep learning AI radiographs, that was trained and tested large clinical set. Materials Methods DeepCOVID-XR is an ensemble convolutional...
Clinical knowledge-enriched transformer models (eg, ClinicalBERT) have state-of-the-art results on clinical natural language processing (NLP) tasks. One of the core limitations these is substantial memory consumption due to their full self-attention mechanism, which leads performance degradation in long texts. To overcome this, we propose leverage long-sequence Longformer and BigBird), extend maximum input sequence length from 512 4096, enhance ability model long-term dependencies...
Transthyretin amyloid cardiomyopathy (ATTR-CM) is a form of heart failure (HF) with preserved ejection fraction (HFpEF). Technetium Tc 99m pyrophosphate scintigraphy (PYP) enables ATTR-CM diagnosis. It unclear which patients HFpEF have sufficient risk to warrant PYP.To derive and validate simple score predict increased in HFpEF.Retrospective cohort study 666 HF (ejection ≥ 40%) suspected referred for PYP at Mayo Clinic, Rochester, Minnesota, from May 10, 2013, through August 31, 2020. These...
Transformers-based models, such as BERT, have dramatically improved the performance for various natural language processing tasks. The clinical knowledge enriched model, namely ClinicalBERT, also achieved state-of-the-art results when performed on named entity recognition and inference One of core limitations these transformers is substantial memory consumption due to their full self-attention mechanism. To overcome this, long sequence transformer e.g. Longformer BigBird, were proposed with...
Increase in early onset colorectal cancer makes adherence to screening a significant public health concern, with various social determinants playing crucial role its incidence, diagnosis, treatment, and outcomes. Stressful life events, such as divorce, marriage, or sudden loss of job, have unique position among the health. We applied large language model (LLM) history sections clinical notes records database Medical University South Carolina extract recent stressful events assess their...
Prior authorization (PA) may be a necessary evil within the healthcare system, contributing to physician burnout and delaying care, but also allowing payers prevent wasting resources on redundant, expensive, and/or ineffective care. PA has become an "informatics issue" with rise of automated methods for review, championed in Health Level 7 International's (HL7's) DaVinci Project. proposes using rule-based automate PA, time-tested strategy known limitations. This article alternative that more...
Abstract We report here on our findings from adolescent and young adult females (ages 14–25) with a family history of fragile X syndrome regarding their perceptions the optimal ages for (1) learning is inherited, (2) one could be carrier X, (3) offering testing X. Three groups were enrolled: those who knew they carriers or noncarriers only at‐risk to carrier. Only 2 53 participants felt that should delayed until age 18 years. Participants provided older than actual status. did not express...
The COVID-19 pandemic has posed unprecedented challenges to global healthcare systems, highlighting the need for accurate and timely risk prediction models that can prioritize patient care allocate resources effectively. This study presents DeepCOVID-Fuse, a deep learning fusion model predicts levels in patients with confirmed by combining chest radiographs (CXRs) clinical variables. collected initial CXRs, variables, outcomes (i.e., mortality, intubation, hospital length of stay, Intensive...
Yonathan Freund, MD, PhD; Marine Cachanado, MSc; Quentin Delannoy, MD; Said Laribi, Youri Yordanov, Judith Gorlicki, Tahar Chouihed, Anne-Laure Féral-Pierssens, Jennifer Truchot, Thibaut Desmettre, Celine Occelli, Xavier Bobbia, Mehdi Khellaf, Olivier Ganansia, Jérôme Bokobza, Frédéric Balen, Sebastien Beaune, Ben Bloom, Tabassome Simon, Alexandre Mebazaa, PhD
<sec> <title>BACKGROUND</title> Increase in early onset colorectal cancer makes adherence to screening a significant public health concern with various social determinants playing crucial role its incidence, diagnosis, treatment, and outcomes. Stressful life events, such as divorce, marriage, or sudden loss of job, have unique position among the health. </sec> <title>OBJECTIVE</title> We applied large language model (LLM) history sections clinical notes records database Medical University...
Introduction: Left ventricular assist device (LVAD) offers a lifeline for advanced heart failure patients, but ~30% experience post-operative right (RHF) with significant morbidity and mortality. Current methods predicting RHF risk have limited accuracy. This study is the first of its kind to explore feasibility using convolutional neural network (CNN) deep learning model pulmonary artery pressure (PAP) tracings acquired during pre-operative hemodynamic assessment identify patients at early...
Introduction: Right heart failure (RHF) is a significant contributor to morbidity and mortality after left ventricular assist device (LVAD) implantation. Lack of respiratory variation in the right atrial pressure (RAP) waveform, perhaps marker RV reserve capacity, has been associated with RHF worse outcomes patients precapillary pulmonary hypertension. It unknown if RAP may predict early post-LVAD Hypothesis: We hypothesized that lack pre-implant would be predictive RHF. Methods: In this...