A5057835525- Biomedical Text Mining and Ontologies
- Dementia and Cognitive Impairment Research
- Machine Learning in Healthcare
- Topic Modeling
- Dermatology and Skin Diseases
- Plant Reproductive Biology
- Transplantation: Methods and Outcomes
- Skin and Cellular Biology Research
- Retinal Development and Disorders
- Genomics and Chromatin Dynamics
- RNA Interference and Gene Delivery
- Autism Spectrum Disorder Research
- CRISPR and Genetic Engineering
- Plant tissue culture and regeneration
- Transgenic Plants and Applications
- Alzheimer's disease research and treatments
- Natural Language Processing Techniques
- Organ Transplantation Techniques and Outcomes
- RNA regulation and disease
- Genomics and Rare Diseases
- Neurofibromatosis and Schwannoma Cases
- Hip disorders and treatments
- Scoliosis diagnosis and treatment
- Memory Processes and Influences
- COVID-19 diagnosis using AI
Washington University in St. Louis
2014-2025
Emory University
2023
Children's Healthcare of Atlanta
2023
Alzheimer’s Disease Neuroimaging Initiative
2015
University College London
2015
Ixico (United Kingdom)
2015
Pfizer (United Kingdom)
2015
Brigham and Women's Hospital
2015
University of Michigan
2015
University of Pittsburgh
2015
Dozens of variants in the gene for homeodomain transcription factor (TF) cone-rod homeobox ( CRX ) are linked with human blinding diseases that vary their severity and age onset. How different this single TF alter its function ways lead to a range phenotypes is unclear. We characterized effects disease-causing on cis -regulatory by deploying massively parallel reporter assays (MPRAs) mouse retina explants carrying knock-ins two variants, one DNA-binding domain (p.R90W) other transcriptional...
The capacity of specialty memory clinics in the United States is very limited. If lower socioeconomic status or minoritized racial group associated with reduced use clinics, this could exacerbate health care disparities, especially if more effective treatments Alzheimer disease become available. We aimed to understand how a clinic neighborhood-level measures factors and intersectionality race.
Abstract Objectives There is much interest in utilizing clinical data for developing prediction models Alzheimer’s disease (AD) risk, progression, and outcomes. Existing studies have mostly utilized curated research registries, image analysis, structured electronic health record (EHR) data. However, critical information resides relatively inaccessible unstructured notes within the EHR. Materials Methods We developed a natural language processing (NLP)-based pipeline to extract AD-related...
Primary graft dysfunction (PGD) is a common complication after lung transplantation associated with poor outcomes. Although risk factors have been identified, the complex interactions between clinical variables affecting PGD are not well understood, which can complicate decisions about donor acceptance. Previously, we developed machine learning (ML) model to predict grade 3 using and recipient electronic health record (EHR) data, but it lacked granular information from CT scans, routinely...
Abstract Monogenic disorders account for a large proportion of population-attributable risk neurodevelopmental disabilities. However, the data necessary to infer causal relationship between given genetic variant and particular disorder is often lacking. Recognizing this scientific roadblock, 13 Intellectual Developmental Disabilities Research Centers (IDDRCs) formed consortium create Brain Gene Registry (BGR), repository pairing clinical with phenotypic from participants variants in putative...
Abstract Objective Accurately identifying clinical phenotypes from Electronic Health Records (EHRs) provides additional insights into patients’ health, especially when such information is unavailable in structured data. This study evaluates the application of OpenAI’s Generative Pre-trained Transformer (GPT)-4 model to identify EHR text non-small cell lung cancer (NSCLC) patients. The goal was disease stages, treatments and progression utilizing GPT-4, compare its performance against...
Abstract Dozens of variants in the photoreceptor-specific transcription factor (TF) CRX are linked with human blinding diseases that vary their severity and age onset. It is unclear how different this single TF alter its function ways lead to a range phenotypes. We examined effects disease-causing on cis -regulatory by deploying massively parallel reporter assays (MPRAs) live mouse retinas carrying knock-ins two variants, one DNA binding domain (p.R90W) other transcriptional effector...
PurposeClinically ascertained variants are under-utilized in neurodevelopmental disorder research. We established the Brain Gene Registry (BGR) to coregister clinically identified putative brain genes with participant phenotypes. Here, we report 179 genetic first BGR registrants and analyze proportion that were novel ClinVar at time of entry those absent other disease databases.MethodsFrom 10 academically affiliated institutions, individuals enrolled into BGR. Variants cross-referenced for...
Accurately identifying clinical phenotypes from Electronic Health Records (EHRs) provides additional insights into patients' health, especially when such information is unavailable in structured data. This study evaluates the application of OpenAI's Generative Pre-trained Transformer (GPT)-4 model to identify EHR text non-small cell lung cancer (NSCLC) patients. The goal was disease stages, treatments and progression utilizing GPT-4, compare its performance against GPT-3.5-turbo, Flan-T5-xl,...
Dementia is characterized by a decline in memory and thinking that significant enough to impair function activities of daily living. Patients seen dementia specialty clinics are highly heterogenous with variety different symptoms progress at rates. Recent research has focused on finding data-driven subtypes for revealing new insights into dementia’s underlying heterogeneity, rather than assuming the cohort homogenous. However, current studies subtyping have following limitations: (i)...
Abstract The risk of Alzheimer’s disease (AD) in women is about 2 times greater than men. estrogen hypothesis being accepted as the essential sex factor causing difference AD. Also, recent meta-analysis using large-scale medical records data indicated replacement therapy. However, underlying molecular targets and mechanisms explaining this AD development remain unclear. In study, we identified that treatment can strongly inhibition neuro-inflammation signaling targets, systems pharmacology...
Abstract The genetic modules that contribute to human evolution are poorly understood. Here we investigate positive selection in the Epidermal Differentiation Complex locus for skin barrier adaptation diverse HapMap populations (CEU, JPT/CHB, and YRI). Using Composite of Multiple Signals iSAFE, identify selective sweeps LCE1A - SMCP involucrin ( IVL ) haplotypes associated with migration out-of-Africa, reaching near fixation European populations. CEU- is increased expression a known...
The identification of regulatory elements for a given target gene poses significant technical challenge owing to the variability in positioning and effect sizes gene. Some progress has been made with bioinformatic prediction existence function proximal epigenetic modifications associated activated expression using conserved transcription factor binding sites. Chromatin conformation capture studies have revolutionized our ability discover physical chromatin contacts between sequences even...
Abstract Dementia is characterized by a decline in memory and thinking that significant enough to impair function activities of daily living. Patients seen dementia specialty clinics are highly heterogenous with variety different symptoms progress at rates. Recent research has focused on finding data-driven subtypes for revealing new insights into dementia’s underlying heterogeneity, compared analyzing the entire cohort as single homogeneous group. However, current studies subtyping have...
Generative pre-trained transformer (GPT) models have shown promise in clinical entity and relation extraction tasks because of their precise contextual understanding capability. In this work, we further leverage the Unified Medical Language System (UMLS) knowledge base to accurately identify medical concepts improve at document level. Our framework selects UMLS relevant text combines them with prompts guide language extracting entities. experiments demonstrate that initial concept mapping...
Dimensionality reduction techniques aim to enhance the performance of machine learning (ML) models by reducing noise and mitigating overfitting. We sought compare effect different dimensionality methods for comorbidity features extracted from electronic health records (EHRs) on ML predicting development various sub-phenotypes in children with Neurofibromatosis type 1 (NF1). EHR-derived data pediatric subjects a confirmed clinical diagnosis NF1 were used create 10 unique comorbidities...