A5042424043- Dementia and Cognitive Impairment Research
- Bioinformatics and Genomic Networks
- Machine Learning in Healthcare
- Single-cell and spatial transcriptomics
- Preterm Birth and Chorioamnionitis
- Tryptophan and brain disorders
- Infant Development and Preterm Care
- Alzheimer's disease research and treatments
- Biomedical Text Mining and Ontologies
- Neonatal Respiratory Health Research
- Neuroinflammation and Neurodegeneration Mechanisms
- Gut microbiota and health
- Reproductive tract infections research
- Pregnancy and preeclampsia studies
- Biomedical and Engineering Education
- Reproductive System and Pregnancy
- Cell Image Analysis Techniques
- Pelvic floor disorders treatments
- Health, Environment, Cognitive Aging
- Medical Image Segmentation Techniques
- Health disparities and outcomes
- Diabetes and associated disorders
- Primary Care and Health Outcomes
- Maternal Mental Health During Pregnancy and Postpartum
- Diet and metabolism studies
University of California, San Francisco
2020-2025
University of California, Berkeley
2021-2025
Sunesis (United States)
2025
March of Dimes
2023-2024
University of Cincinnati
2023
Bioengineering Center
2023
Columbia University
2022
Garvan Institute of Medical Research
2014-2019
St Vincent's Hospital Sydney
2014-2019
St Vincent's Clinic
2019
<h3>Importance</h3> Antidepressant use may be associated with reduced levels of several proinflammatory cytokines suggested to involved the development severe COVID-19. An association between selective serotonin reuptake inhibitors (SSRIs)—specifically fluoxetine hydrochloride and fluvoxamine maleate—with decreased mortality among patients COVID-19 has been reported in recent studies; however, these studies had limited power due their small size. <h3>Objective</h3> To investigate SSRIs...
Abstract Motivation Knowledge graphs (KGs) are being adopted in industry, commerce and academia. Biomedical KG presents a challenge due to the complexity, size heterogeneity of underlying information. Results In this work, we present Scalable Precision Medicine Open Engine (SPOKE), biomedical connecting millions concepts via semantically meaningful relationships. SPOKE contains 27 million nodes 21 different types 53 edges 55 downloaded from 41 databases. The graph is built on framework 11...
Identification of Alzheimer's disease (AD) onset risk can facilitate interventions before irreversible progression. We demonstrate that electronic health records from the University California, San Francisco, followed by knowledge networks (for example, SPOKE) allow for (1) prediction AD and (2) prioritization biological hypotheses, (3) contextualization sex dimorphism. trained random forest models predicted on a cohort 749 individuals with 250,545 controls mean area under receiver operating...
Approximately 1.2 million people are living with HIV in the United States, 16,000 San Francisco. Many HIV-positive individuals have difficulty maintaining follow-up clinic visits under normal circumstances, and this is complicated by coronavirus disease 2019 (COVID-19) pandemic as many institutions transition to a telehealth-focused model of care maintain patient provider safety. However, it was unknown how telehealth would impact attendance perceptions about their care, particularly...
Although prematurity is the single largest cause of death in children under 5 years age, current definition prematurity, based on gestational lacks precision needed for guiding care decisions. Here, we propose a longitudinal risk assessment adverse neonatal outcomes newborns deep learning model that uses electronic health records (EHRs) to predict wide range over period starting shortly before conception and ending months after birth. By linking EHRs Lucile Packard Children’s Hospital...
Abstract Major depressive disorder and exposure to antidepressants during pregnancy have been previously associated with preterm birth (PTB). However, the reported results are inconsistent. In this study, we aimed estimate effects of maternal depression on risk PTB using data from electronic health records (EHRs). This is a population-based retrospective cohort utilizing primary care EHRs. The included 216,070 deliveries 176,866 patients UK between January 1996 February 2019. We analyzed...
Abstract Background Preterm birth (PTB) is the leading cause of infant mortality. Risk for PTB influenced by multiple biological pathways, many which are poorly understood. Some PTBs result from medically indicated labor following complications hypertension and/or diabetes, while others spontaneous with unknown causes. Previously, investigation potential risk factors has been limited a lack data on maternal medical history and difficulty classifying as or spontaneous. Here, we leverage...
Cytometry technologies are essential tools for immunology research, providing high-throughput measurements of the immune cells at single-cell level. Existing approaches in interpreting and using cytometry include manual or automated gating to identify cell subsets from data, highly intuitive results but may lead significant information loss, that additional details measured correlated signals might be missed. In this study, we propose test a deep convolutional neural network analyzing data...
Abstract The complexity of affected brain regions and cell types is a challenge for Huntington’s disease (HD) treatment. Here we use single nucleus RNA sequencing to investigate molecular pathology in the cortex striatum from R6/2 mice human HD post-mortem tissue. We identify type-specific -agnostic signatures suggesting oligodendrocytes (OLs) oligodendrocyte precursors (OPCs) are arrested intermediate maturation states. OL-lineage regulators OLIG1 OLIG2 negatively correlated with CAG length...
Every year, 11% of infants are born preterm with significant health consequences, the vaginal microbiome a risk factor for birth. We crowdsource models to predict (1) birth (PTB; <37 weeks) or (2) early (ePTB; <32 from 9 studies representing 3,578 samples 1,268 pregnant individuals, aggregated public raw data via phylogenetic harmonization. The predictive validated on two independent unpublished datasets 331 148 individuals. top-performing (among and 121 submissions 318 teams) achieve area...
Alzheimer's disease (AD) is a pervasive neurodegenerative disorder that disproportionately affects women. Since neural anatomy and pathophysiology differ by sex, investigating sex-specific mechanisms in AD can inform new therapeutic approaches for both sexes. Previous bulk human brain RNA sequencing studies have revealed sex differences dysregulated molecular pathways related to energy production, neuronal function, immune response; however, the are yet be examined comprehensively on...
Abstract Alzheimer’s Disease (AD) is a neurodegenerative disorder that still not fully understood. Sex modifies AD vulnerability, but the reasons for this are largely unknown. We utilize two independent electronic medical record (EMR) systems across 44,288 patients to perform deep clinical phenotyping and network analysis gain insight into characteristics sex-specific associations in AD. Embeddings representation of patient diagnoses demonstrate greater comorbidity interactions comparison...
Abstract Persistent HPV16 infection is a major cause of the global cancer burden. The viral life cycle dependent on differentiation program stratified squamous epithelium, but landscape keratinocyte subpopulations which support distinct phases has yet to be elucidated. Here, single cell RNA sequencing infected compared uninfected organoids identifies twelve populations, with subset mapped reconstruct their respective 3D geography in epithelium. Instead conventional terminally differentiated...
Healthcare systems are struggling to meet the growing demand for neurological care, with challenges particularly acute in Alzheimer's disease and related dementias (ADRD). While artificial intelligence research has often focused on identifying patterns beyond human perception, implementing such predictive capabilities remains challenging as clinicians cannot readily verify insights they themselves detect. We propose that large language models (LLMs) offer more immediately practical...
A common issue in clinical drug development involves drug-drug interactions (DDI) that may lead to altered exposure and subsequent safety efficacy of an investigational or concomitant medications (conmeds) the target patient population. The pipeline therefore DDI risk assessment based on vitro studies, silico modeling, trials. Real-world data (RWD), particularly claims databases with reliable information pharmacy dispensing, provide opportunity understand conmeds usage indication a...
Background: Alzheimer's disease is a progressive neurodegenerative disorder with no curative treatment. Identifying distinct subphenotypes and understanding potential personalized modifications remain critical unmet needs. Methods: We applied unsupervised learning techniques to electronic medical records from UCSF identify based on comorbidity profiles. conducted enrichment analyses determine cluster-specific comorbidities. Based the observed sex-based differences, we subsequently...
Abstract Globally, every year about 11% of infants are born preterm, defined as a birth prior to 37 weeks gestation, with significant and lingering health consequences. Multiple studies have related the vaginal microbiome preterm birth. We present crowdsourcing approach predict: (a) or (b) early from 9 publicly available representing 3,578 samples 1,268 pregnant individuals, aggregated raw sequences via an open-source tool, MaLiAmPi. validated crowdsourced models on novel datasets 331 148...
For studies using microbiome data, the ability to robustly combine data from technically and biologically distinct is a crucial means of supporting more robust clinically relevant inferences. Formidable technical challenges arise when attempting diverse 16S rRNA gene variable region amplicon sequencing (16S) studies. Closed operational taxonomic units taxonomy are criticized as being heavily dependent upon reference sets with limited precision relative underlying biology. Phylogenetic...
Artificial Intelligence (AI) has the power to improve our lives through a wide variety of applications, many which fall into healthcare space; however, lack diversity is contributing limitations in how broadly AI can help people. The UCSF AI4ALL program was established 2019 address this issue by targeting high school students from underrepresented backgrounds AI, giving them chance learn about with focus on biomedicine, and promoting inclusion. In 2020, three-week held entirely online due...