A5028996387- Radiomics and Machine Learning in Medical Imaging
- Artificial Intelligence in Healthcare and Education
- COVID-19 diagnosis using AI
- Patient Satisfaction in Healthcare
- Healthcare Systems and Technology
- AI in cancer detection
- Power Systems and Renewable Energy
- Cardiac Imaging and Diagnostics
- RNA modifications and cancer
- Cancer Genomics and Diagnostics
- Cardiomyopathy and Myosin Studies
- Organ Transplantation Techniques and Outcomes
- Advanced Sensor and Control Systems
- Healthcare Policy and Management
- COVID-19 Clinical Research Studies
- Digital Radiography and Breast Imaging
- Global Cancer Incidence and Screening
- Magnetic and transport properties of perovskites and related materials
- Cardiovascular Function and Risk Factors
- Power Quality and Harmonics
- Infective Endocarditis Diagnosis and Management
- Prostate Cancer Treatment and Research
- Liver Disease Diagnosis and Treatment
- Cardiac Structural Anomalies and Repair
- Mechanical Circulatory Support Devices
National Cancer Institute
2023
Scripps Clinic Medical Group
2023
Scripps Clinic
2019
Duke University
2017-2018
Duke University Hospital
2017-2018
Duke Medical Center
2017-2018
Health systems are seeking innovative solutions to improve specialty care access. Electronic consultations (eConsults) allow specialists provide formal clinical recommendations primary providers (PCPs) based on patient chart review, without a face-to-face visit.We implemented nephrology eConsult pilot program within large, academic practice facilitate timely communication between nephrologists and PCPs. We used referral data compare wait times completion rates traditional referrals...
Chest X-rays (CXRs) play a pivotal role in cost-effective clinical assessment of various heart and lung related conditions. The urgency COVID-19 diagnosis prompted their use identifying conditions like opacity, pneumonia, acute respiratory distress syndrome pediatric patients. We propose an AI-driven solution for binary versus non-COVID-19 classification CXRs. present Federated Self-Supervised Learning (FSSL) framework to enhance Vision Transformer (ViT) performance detection ViT's prowess...
Cross-institution collaborations are constrained by data-sharing challenges. These challenges hamper innovation, particularly in artificial intelligence, where models require diverse data to ensure strong performance. Federated learning (FL) solves In typical collaborations, is sent a central repository trained. With FL, participating sites, trained locally, and model weights aggregated create master with improved At the 2021 Radiology Society of North America’s (RSNA) conference, panel was...
Prostate-specific antigen (PSA) screening for prostate cancer remains a controversial topic, particularly in the primary care community. Our multidisciplinary panel at Duke University Health System, USA created nuanced PSA algorithm, implemented it into Electronic Record of Primary Care, and conducted outreach meetings with practices to support its rollout. Through this project, we identified areas concern among clinicians regarding that structured two major categories: ideological...
Abstract Introduction: Reliability of machine and deep learning models on medical images can be compromised by the presence image artifacts variability in acquisition. This is further exacerbated when validating model performance across multiple institutions, where acquisition protocols scanner equipment may result significant numbers outlier scans. We developed a privacy-preserving identification algorithm via federated MR imaging quality evaluation distributed multi-institutional cohort...
Motivation: Site and scanner specific variations in prostate MRI impact performance of deep learning (DL) based models. Federated allows for privacy preserving training DL models without the need data sharing. Goal(s): In this study, we train cancer segmentation on using Rhino Health federated computing platform. Approach: We adopt 3D UNet architecture to 2 publicly available datasets. Results: trained a approach result more generalizable compared those single site data. Impact: Successful...
Abstract Human papilloma virus (HPV)-negative head and neck squamous cell carcinoma (HNSCC) patients have a poor prognosis most with metastatic disease are resistant to pembrolizumab. We recently showed that depletion of SET MYND domain protein 3 (SMYD3), methyltransferase, induces upregulation multiple type I IFN response genes in HPV-negative HNSCC human mouse cells vitro. Systemic treatment flank oral 1 (MOC1) tumors Smyd3 anti-sense oligonucleotides (ASOs) induced influx CD8+ T-cells,...
Introduction: Transjugular intrahepatic portosystemic shunts (TIPS) treat portal hypertension by connecting the vein to hepatic in liver. The resultant shunting of venous flow systemic circulation helps reduce gradient and is used complications hypertension. Right heart failure development pulmonary after TIPS are known complications; however, portopulmonary (POPH) rare. Description Case: A 61-year-old male presents clinic for six months exertional dyspnea, weight gain, lower extremity...