A5033019632- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare and Education
- Sepsis Diagnosis and Treatment
- Medical Coding and Health Information
- Clinical Reasoning and Diagnostic Skills
- Cardiac, Anesthesia and Surgical Outcomes
- Emergency and Acute Care Studies
- Bioinformatics and Genomic Networks
- Health Systems, Economic Evaluations, Quality of Life
- Chronic Disease Management Strategies
- Respiratory Support and Mechanisms
- Insurance, Mortality, Demography, Risk Management
- Oral and Maxillofacial Pathology
- Colorectal Cancer Screening and Detection
- Electronic Health Records Systems
- Esophageal Cancer Research and Treatment
- Head and Neck Surgical Oncology
- Acute Ischemic Stroke Management
- Congenital Heart Disease Studies
- Inflammatory Bowel Disease
- Ethics in Clinical Research
- Frailty in Older Adults
- Spine and Intervertebral Disc Pathology
- Neonatal Respiratory Health Research
- Artificial Intelligence in Healthcare
Icahn School of Medicine at Mount Sinai
2019-2025
Mount Sinai Hospital
2022-2025
Soochow University
2025
First Affiliated Hospital of Soochow University
2025
Feinstein Institute for Medical Research
2024
Northwell Health
2024
Duke Institute for Health Innovation
2019-2024
University of Pennsylvania
2024
Duke University Health System
2024
Duke University
2019-2023
Down syndrome (DS), or trisomy 21, is a common disorder associated with several complex clinical phenotypes. Although hypotheses have been put forward, it unclear as to whether particular gene loci on chromosome 21 (HSA21) are sufficient cause DS and its features. Here we present high-resolution genetic map of phenotypes based an analysis 30 subjects carrying rare segmental trisomies various regions HSA21. By using state-of-the-art genomics technologies mapped at exon-level resolution...
Machine learning technologies are increasingly developed for use in healthcare. While research communities have focused on creating state-of-the-art models, there has been less focus real world implementation and the associated challenges to fairness, transparency, accountability that come from actual, situated use. Serious questions remain underexamined regarding how ethically build interpret explain model output, recognize account biases, minimize disruptions professional expertise work...
The use of data-driven technologies such as Artificial Intelligence (AI) and Machine Learning (ML) is growing in healthcare. However, the proliferation healthcare AI tools has outpaced regulatory frameworks, accountability measures, governance standards to ensure safe, effective, equitable use. To address these gaps tackle a common challenge faced by delivery organizations, case-based workshop was organized, framework developed evaluate potential impact implementing an solution on health...
Successful integrations of machine learning into routine clinical care are exceedingly rare, and barriers to its adoption poorly characterized in the literature.This study aims report a quality improvement effort integrate deep sepsis detection management platform, Sepsis Watch, care.In 2016, multidisciplinary team consisting statisticians, data scientists, engineers, clinicians was assembled by leadership an academic health system radically improve treatment sepsis. This follows framework...
There is tremendous enthusiasm surrounding the potential for machine learning to improve medical prognosis and diagnosis. However, there are risks translating a model into clinical care end users often unaware of harm patients. This perspective presents "Model Facts" label, systematic effort ensure that front-line clinicians actually know how, when, how not, when not incorporate output decisions. The label was designed who make decisions supported by its purpose collate relevant, actionable...
<h3>Importance</h3> The ability to accurately predict in-hospital mortality for patients at the time of admission could improve clinical and operational decision-making outcomes. Few machine learning models that have been developed death are both broadly applicable all adult across a health system readily implementable. Similarly, few implemented, none evaluated prospectively externally validated. <h3>Objectives</h3> To validate model predicts hospital design using commonly available...
Despite enormous enthusiasm, machine learning models are rarely translated into clinical care and there is minimal evidence of or economic impact. New conference venues academic journals have emerged to promote the proliferating research; however, translational path remains unclear. This review undertakes first in-depth study identify how that ingest structured electronic health record data can be applied decision support tasks practice. The authors complement their own work with experience...
Determine if deep learning detects sepsis earlier and more accurately than other models. To evaluate model performance using implementation-oriented metrics that simulate clinical practice.We trained internally temporally validated a (multi-output Gaussian process recurrent neural network [MGP-RNN]) to detect encounters from adult hospitalized patients at large tertiary academic center. Sepsis was defined as the presence of 2 or systemic inflammatory response syndrome (SIRS) criteria, blood...
Abstract Objectives Real‐world data on ustekinumab for the treatment of pediatric Crohn's disease (CD) are limited. This study sought to evaluate effectiveness, long‐term durability, and safety in children with CD. Methods A retrospective longitudinal cohort CD treated from two large centers between 2015 2020 was performed. The primary outcome frequency steroid‐free clinical remission at 1 year. Secondary outcomes included time remission, biochemical drug escalation discontinuation, serum...
Examples of fully integrated machine learning models that drive clinical care are rare. Despite major advances in the development methodologies outperform experts and growing prominence mainstream medical literature, challenges remain. At Duke Health, we our fourth year developing, piloting, implementing technologies care. To advance translation into care, health system leaders must address barriers to progress make strategic investments necessary bring a new digital age. Machine can improve...
Abstract Objective The complexity and rapid pace of development algorithmic technologies pose challenges for their regulation oversight in healthcare settings. We sought to improve our institution’s approach evaluation governance used clinical care operations by creating an Implementation Guide that standardizes criteria so local is performed objective fashion. Materials Methods Building on a framework applies key ethical quality principles (clinical value safety, fairness equity, usability...
Developments in machine learning recent years have precipitated a surge research on the applications of artificial intelligence within medicine. Machine algorithms are beginning to impact medicine broadly, and field spine surgery is no exception. Electronic medical records key source data that can be leveraged for creation clinically valuable algorithms. This review examines current state using electronic as it applies surgery. Studies across record domains imaging, text, structured...
Abstract Background Human immunodeficiency virus (HIV) pre-exposure prophylaxis (PrEP) is underutilized in the southern United States. Rapid identification of individuals vulnerable to diagnosis HIV using electronic health record (EHR)-based tools may augment PrEP uptake region. Methods Using machine learning, we developed EHR-based models predict incident as a surrogate for candidacy. We included patients from medical system with encounters between October 2014 and August 2016, training...
Objective: This study retrospectively analyzed the clinical characteristics of patients newly diagnosed with acute myeloid leukemia (AML) who were admitted to hematology intensive care unit (HCU) critical illness. It also examined factors associated illness and early mortality in these patients. Methods: Clinical data collected from 91 AML HCU Department Hematology, First Affiliated Hospital Soochow University, October 2020 2024. Reasons for admission, major therapeutic interventions, risk...
Abstract When integrating AI tools in healthcare settings, complex interactions between technologies and primary users are not always fully understood or visible. This deficient ambiguous understanding hampers attempts by organizations to adopt AI/ML, it also creates new challenges for researchers identify opportunities simplifying adoption developing best practices the use of AI-based solutions. Our study fills this gap documenting process designing, building, maintaining an solution called...
Renal cell carcinoma (RCC) is one of the most malignant tumors in human. Here, we found that odd-skipped related transcription factor 1 (OSR1) was downregulated 769-P and 786-O cells due to promoter CpG methylation. OSR1 expression could be restored by pharmacological demethylation treatment silenced lines. Knockdown two normal expressed lines- A498 ACHN promoted invasion cellular proliferation. RNA-Sequencing analysis showed profile genes involved multiple cancer-related pathways changed...
Machine learning technologies are increasingly developed for use in healthcare. While research communities have focused on creating state-of-the-art models, there has been less focus real world implementation and the associated challenges to accuracy, fairness, accountability, transparency that come from actual, situated use. Serious questions remain under examined regarding how ethically build interpret explain model output, recognize account biases, minimize disruptions professional...
High rates of screen failure for the minimum Simple Endoscopic Score Crohn's Disease (SES-CD) plague disease (CD) clinical trials. We aimed to determine accuracy segmental intestinal ultrasound (IUS) parameters and scores detect SES-CD activity.