Digital Twins Modeling Blood Flow Could Predict Heart Problems
The HARVEY platform leverages supercomputing, physics-based simulations, and wearable device data to monitor real-time hemodynamics and spot heart failure early.
-
-
Association of Telomere Length with Ovarian Cancer Risk and Survival: A Systematic Review and Meta-analysis
Background: Telomeres are protective DNA sequences at chromosome ends that shorten with cell division and regulate cellular lifespan. Dysregulation of telomere maintenance through telomerase activation is implicated in carcinogenesis, including ovarian cancer. This study aimed to systematically review and meta-analyze the association between telomere length and ovarian cancer risk and survival outcomes. Methodology: A systematic…
-
Evaluation, Treatment, and Outcomes in Patients With Possible Severe Aortic Stenosis
Background Severe aortic stenosis (AS) is associated with significant morbidity and mortality. Prior reports suggest that severe AS is under-recognized and undertreated. Methods Retrospective analysis of the Duke Echocardiography Laboratory Database of individuals undergoing an echocardiogram between 2016 and 2024. Patients with possible severe AS (any of the following: aortic valve area (AVA) <1.0 cm2,…
-
Segmenting with confidence through uncertainty quantification for brain tumor imaging
A major barrier to clinical adoption of artificial intelligence (AI) for brain tumor monitoring is the lack of calibrated uncertainty in automated segmentation, limiting clinician trust. We developed a deep learning framework that generates uncertainty estimates for meningioma segmentation on brain MRI. Evidential deep learning ensembles were trained on 1655 post-contrast T1-weighted MRIs (788 patients)…
-
Patient-centered evaluation of anticoagulation in atrial fibrillation
BACKGROUND Prior analyses of trials comparing direct oral anticoagulants (DOACs) to warfarin in atrial fibrillation (AF) have not routinely incorporated patient preferences, despite substantial variation in how patients value the trade-off between outcomes such as stroke and bleeding. By applying patient-centered approaches, we aimed to provide intuitive metrics to inform shared decision-making, particularly for frail…
-
Predictors of ischemic stroke and major bleeding among patients with atrial fibrillation in clinical practice
Background Numerous risk scores exist to quantify the risk of ischemic stroke risk in patients with atrial fibrillation or flutter (AF/AFL). However, how these tools perform in cohorts or those already on oral anticoagulation (OAC) therapy is unclear. Methods Using 2 electronic health records datasets, individuals with AF/AFL were identified (Duke University Health System [DUHS]—2009-2018;…
-
Predictors of ischemic stroke and major bleeding among patients with atrial fibrillation in clinical practice
Background Numerous risk scores exist to quantify the risk of ischemic stroke risk in patients with atrial fibrillation or flutter (AF/AFL). However, how these tools perform in cohorts or those already on oral anticoagulation (OAC) therapy is unclear. Methods Using two electronic health records datasets, individuals with AF/AFL were identified [Duke University Health System (DUHS)…
-
-
Multi-Institutional Annotated Multiparametric MRI Dataset of Pediatric High-Grade Gliomas
The BraTS-PEDs dataset provides the largest, multi-institutional, publicly available collection of annotated multiparametric MRI scans of pediatric high-grade gliomas, enabling standardized benchmarking and development of AI tools in pediatric neuro-oncology. Key Points
-
Early attention deficit hyperactivity disorder prediction from longitudinal electronic health records
Attention deficit hyperactivity disorder (ADHD) is a common neurodevelopmental condition that can negatively impact long-term outcomes for individuals. Early diagnosis is critical, yet demographic and clinical disparities can delay detection. Using electronic health records (EHRs) from a cohort of over 720,000 patients, we pretrained an EHR foundation model. We then fine tuned it to predict…
