A5084415954- Biomedical Text Mining and Ontologies
- Electronic Health Records Systems
- Privacy-Preserving Technologies in Data
- Ethics in Clinical Research
- Gene expression and cancer classification
- Machine Learning in Healthcare
- Cancer Genomics and Diagnostics
- Artificial Intelligence in Healthcare
- Bioinformatics and Genomic Networks
- Data Quality and Management
- AI in cancer detection
- Scientific Computing and Data Management
- Genetics, Bioinformatics, and Biomedical Research
- Mobile Health and mHealth Applications
- Epigenetics and DNA Methylation
- Statistical Methods and Inference
- Genomics and Rare Diseases
- Topic Modeling
- Cryptography and Data Security
- Inflammatory Bowel Disease
- Healthcare Technology and Patient Monitoring
- Health Systems, Economic Evaluations, Quality of Life
- Genomics and Phylogenetic Studies
- MicroRNA in disease regulation
- Statistical Methods in Clinical Trials
University of California, San Diego
2016-2025
Yale University
2023-2025
Data Management (Italy)
2024
UC San Diego Health System
2012-2023
Health Services Research & Development
2014-2023
VA San Diego Healthcare System
2014-2023
National Institutes of Health
2022
Health Affairs
2015-2018
Veterans Health Administration
2018
Biomedical Informatics Research Center Antwerp
2017
The US health care system is rapidly adopting electronic records, which will dramatically increase the quantity of clinical data that are available electronically. Simultaneously, rapid progress has been made in analytics—techniques for analyzing large quantities and gleaning new insights from analysis—which part what known as big . As a result, there unprecedented opportunities to use reduce costs United States. We present six cases—that is, key examples—where some clearest exist through...
The vertebrate retina is comprised of seven major cell types that are generated in overlapping but well-defined intervals. To identify genes might regulate retinal development, gene expression the developing was profiled at multiple time points using serial analysis (SAGE). patterns 1,051 showed developmentally dynamic by SAGE were investigated situ hybridization. A molecular atlas and mature thereby constructed, along with a taxonomic classification developmental patterns. Genes identified...
[corrected] The existence of several technologies for measuring gene expression makes the question cross-technology agreement measurements an important issue. Cross-platform utilization data from different has potential to reduce need duplicate experiments but requires corresponding be comparable.A comparison mRNA 2895 sequence-matched genes in 56 cell lines standard panel 60 cancer National Cancer Institute (NCI 60) was carried out by calculating correlation between matched and concordance...
Abstract To metastasize, carcinoma cells must attenuate cell–cell adhesion to disseminate into distant organs. A group of transcription factors, including Twist1, Snail1, Snail2, ZEB1, and ZEB2, have been shown induce epithelial mesenchymal transition (EMT), thus promoting tumor dissemination. However, it is unknown whether these factors function independently or coordinately activate the EMT program. Here we report that direct induction Snail2 essential for Twist1 EMT. knockdown completely...
The
Cross-institutional healthcare predictive modeling can accelerate research and facilitate quality improvement initiatives, thus is important for national delivery priorities. For example, a model that predicts risk of re-admission particular set patients will be more generalizable if developed with data from multiple institutions. While privacy-protecting methods to build models exist, most are based on centralized architecture, which presents security robustness vulnerabilities such as...
Background. Acute kidney injury (AKI) is common in critically ill patients and associated with high morbidity mortality. Early identification of high-risk provides an opportunity to develop strategies for prevention, early diagnosis treatment AKI. Methods. We undertook this multicenter prospective cohort study validate a risk score predicting AKI admitted intensive care unit (ICU). Patients were screened predictor variables within 48 h ICU admission. Baseline acute factors recorded at the...
Importance Health care algorithms are used for diagnosis, treatment, prognosis, risk stratification, and allocation of resources. Bias in the development use can lead to worse outcomes racial ethnic minoritized groups other historically marginalized populations such as individuals with lower income. Objective To provide a conceptual framework guiding principles mitigating preventing bias health promote equity. Evidence Review The Agency Healthcare Research Quality National Institute Minority...
Abstract Background and Aims Early diagnosis of aortic stenosis (AS) is critical to prevent morbidity mortality but requires skilled examination with Doppler imaging. This study reports the development validation a novel deep learning model that relies on two-dimensional (2D) parasternal long axis videos from transthoracic echocardiography without imaging identify severe AS, suitable for point-of-care ultrasonography. Methods results In training set 5257 studies (17 570 videos) 2016 2020...
Objective: To allow exchange of clinical practice guidelines among institutions and computer-based applications.
Objective: Predictive models that generate individualized estimates for medically relevant outcomes are playing increasing roles in clinical care and translational research. However, current methods calibrating these lose valuable information. Our goal is to develop a new calibration method conserve as much information possible, would compare favorably existing terms of important performance measures: discrimination calibration. Material methods: We propose an adaptive technique utilizes...
Objective The classification of complex or rare patterns in clinical and genomic data requires the availability a large, labeled patient set. While methods that operate on centralized sources have been extensively used, little attention has paid to understanding whether models such as binary logistic regression (LR) can be developed distributed manner, allowing researchers share without necessarily sharing data. Material Instead bringing central repository for computation, we bring...