NIH

Study Funding Source: NIH

PEDSnet-Based Graph Embedding Pilot for Patient Similarity Modeling: FL-GNN Concept Validation Using Harmonized Pediatric Data

PEDSnet provides a harmonized, multi-institutional pediatric clinical dataset that enables cross-site research within a unified governance framework. However, traditional EHR analyses rely on diagnosis-based cohort definitions or tabular feature representations that do not fully capture the relational structure of longitudinal pediatric health data. We propose to leverage the Data Distillery Knowledge Graph (DDKG) to model […]

Identifying Pediatric Pancreatitis and Predicting Pancreatic Diabetes (T3cD)

Type 3c diabetes (T3cD) is a distinct form of diabetes related to diseases of the exocrine pancreas. In the setting of pancreatitis, T3cD affects 4-9% of children and is associated with long-term morbidity and increased mortality. T3cD is understudied especially in pediatrics, and we cannot yet predict which children will develop T3cD. My overall goal […]

AR2 (Autism Replication & Reproducibility) Center – NIH Autism Data Science Initiative Task 4 Application

PEDSnet and the AR2 Center will collaborate to enable model validation and replication activities using pediatric data. The focus is on leveraging existing data within PEDSnet’s Common Data Model (CDM) to support independent validation of models and methods developed under Tasks I-III of the NIH Autism Data Science Initiative (ADSI) This study aims to refine […]

Ischemic Stroke Incidence and Risk Factors in Adults with Congenital Heart Disease

It is well known that adults with CHD have higher rates of stroke and stroke at younger ages, compared to the general population. We aim to better characterize this risk in a large US patient population, and to better understand the role of CHD-related and typical stroke risk factors to ultimately guide management strategies to […]

Evaluating EHR-based Prediction of Obesity using WHO Weight Velocity Standards and Peak BMI

Obesity is a common, pervasive, chronic disease often beginning in early childhood, and infant growth characteristics are key signals of lifelong chronic disease risk. Frequent primary care visits in the first two years of life provide many opportunities for growth surveillance and early intervention, but there are no current clinical practice guidelines for identifying infant […]

Advancing Patient Centered Assessment to Reduce Disparities in Pediatric Primary Chronic Pain across the Continuum of Care

One in four children experience chronic pain worldwide. Primary chronic pain is the most common type of chronic pain in childhood and is associated with negative impact on physical, psychological, and social functioning. Many children have mental health symptoms (e.g., anxiety, depression, insomnia) which impact on their pain experience and are associated with poor prognosis. […]

Determining Barriers Leading to Inferior Survival for Black and Hispanic Patients with Hodgkin Lymphoma: A Patient-Centered Study

Five-year relative survival rates for Hodgkin lymphoma (HL) are excellent at ~90%, yet Black and Hispanic patients have worse survival outcomes than White patients across all age groups (children, young adults, and older adults). HL’s age distribution and generally high cure rates offer a paradigm to study cancer inequities across the lifespan, since each age […]

Alkali therapy and Linear Growth in Children with CKD

Children with chronic kidney disease (CKD) have higher rates of hospitalizations, metabolic abnormalities, cardiovascular disease, and growth restriction, compared to their healthy counterparts. 1-4 Growth failure is common in pediatric CKD; affecting up to 35% of these children. 5 Children with kidney failure and short stature have increased mortality risk compared to those children with […]

Investigating timing of diagnosis and equitable care in children with Turner syndrome

PEDSNet data will be used to identify temporal changes in timing of diagnosis following updated Turner syndrome guidelines in 2017, in addition to association of race, ethnicity and insurance status to timing of diagnosis. Existing dataset of children with Turner syndrome diagnosis between 2010 and 2023 will be analyzed. A computable phenotype for Turner syndrome […]

Scroll to Top