A5006527008- Musculoskeletal pain and rehabilitation
- Chronic Disease Management Strategies
- Diabetes Management and Education
- Fibromyalgia and Chronic Fatigue Syndrome Research
- Spine and Intervertebral Disc Pathology
- Health Systems, Economic Evaluations, Quality of Life
- Medical Imaging and Analysis
- Health, Environment, Cognitive Aging
- Pain Management and Placebo Effect
- Mental Health Research Topics
- Health Policy Implementation Science
- Health disparities and outcomes
- Occupational Health and Performance
- Medical Coding and Health Information
- Hip and Femur Fractures
- Pelvic and Acetabular Injuries
- Dermatology and Skin Diseases
- Electronic Health Records Systems
- Scoliosis diagnosis and treatment
- Stroke Rehabilitation and Recovery
- Diabetes Management and Research
- Spinal Fractures and Fixation Techniques
- Machine Learning in Healthcare
- Olfactory and Sensory Function Studies
- Manufacturing Process and Optimization
University of California, San Francisco
2020-2025
Neurological Surgery
2025
University of California San Francisco Medical Center
2023
Federal Reserve
2022
There is a great and growing need to ascertain what exactly the state of patient, in terms disease progression, actual care practices, pathology, adverse events, much more, beyond paucity data available structured medical record data. Ascertaining these harder-to-reach elements now critical for accurate phenotyping complex traits, detection outcomes, efficacy off-label drug use, longitudinal patient surveillance. Clinical notes often contain most detailed relevant digital information about...
We applied natural language processing and inference methods to extract social determinants of health (SDoH) information from clinical notes patients with chronic low back pain (cLBP) enhance future analyses the associations between SDoH disparities cLBP outcomes.Clinical for were annotated 7 domains, as well depression, anxiety, scores, resulting in 626 at least one entity 364 patients. used a 2-tier taxonomy these 10 first-level classes (domains) 52 second-level classes. developed...
There are a number of risk factors- from biological, psychological, and social domains- for non-specific chronic low back pain (cLBP). Many cLBP treatments target factors on the assumption that targeted factor is not just associated with but also cause (i.e, causal factor). In most cases this strong assumption, primarily due to possibility confounding variables. False assumptions about relationships between likely contribute generally marginal results treatments. The objectives study were a)...
In epidemiological studies, finding the best subset of factors is challenging when number explanatory variables large.Our study had two aims. First, we aimed to identify essential depression-associated using extreme gradient boosting (XGBoost) machine learning algorithm from big survey data (the Korea National Health and Nutrition Examination Survey, 2012-2016). Second, achieve a comprehensive understanding multifactorial features in depression network analysis.An XGBoost model was trained...
Study Design. A retrospective study at a single academic institution. Objective. The purpose of this is to utilize machine learning predict hospital length stay (LOS) and discharge disposition following adult elective spine surgery, compare performance metrics models the American College Surgeon’s National Surgical Quality Improvement Program’s (ACS NSQIP) prediction calculator. Summary Background Data. total 3678 patients undergoing surgery between 2014 2019, acquired from electronic health...
Background Dry eye disease (DED) is a complex of the ocular surface, and its associated factors are important for understanding effectively treating DED. Objective This study aimed to provide an integrative personalized model DED by making explanatory using as many possible from Korea National Health Nutrition Examination Survey (KNHANES) data. Methods Using KNHANES data 2012 (4391 sample cases), point-based scoring system was created ranking with assessing patient-specific risk. First,...
OBJECTIVE Using the newly created University of California (UC) Health Data Warehouse, we present first study to analyze antihyperglycemic treatment utilization across five large UC academic health systems (Davis, Irvine, Los Angeles, San Diego, and Francisco). RESEARCH DESIGN AND METHODS This retrospective analysis used deidentified electronic records (EHRs; 2014–2019) including 97,231 patients with type 2 diabetes from 1,003 UC-affiliated clinical settings. Significant differences between...
Abstract Purpose To identify independent risk factors, including the Risk Assessment and Prediction Tool (RAPT) score, associated with extended length of stay (eLOS) non-home discharge following elective multi-level instrumented spine fusion operations for diagnosis adult spinal deformity (ASD) lumbar degenerative pathology. Methods Adults who underwent ( $$\ge 3$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mo>≥</mml:mo> <mml:mn>3</mml:mn> </mml:mrow>...
Abstract Background Adverse social determinants of health (SDoH), or risk factors, such as food insecurity and housing instability, are known to contribute poor outcomes inequities. Our ability study these linkages is limited because SDoH information more frequently documented in free-text clinical notes than structured data fields. To overcome this challenge, there a growing push develop techniques for automated extraction SDoH. In study, we explored natural language processing (NLP)...
Chronic low back pain (LBP) is a leading cause of disability and opioid prescriptions worldwide, representing significant medical socioeconomic problem. Clinical heterogeneity LBP limits accurate diagnosis precise treatment planning, culminating in poor patient outcomes. A current priority research the development objective, multidimensional assessment tools that subgroup patients based on neurobiological mechanisms, to facilitate matching with optimal therapies. Using unsupervised machine...
<sec> <title>BACKGROUND</title> Adverse social determinants of health (SDoH), or risk factors, such as food insecurity and housing instability, are known to contribute poor outcomes inequities. Our ability study these linkages is limited because SDoH information more frequently documented in free-text clinical notes than structured data fields. To overcome this challenge, there a growing push develop techniques for automated extraction SDoH. </sec> <title>OBJECTIVE</title> In study, we...
Tools, such as the STarTBack Screening Tool (SBT), have been developed to identify risks of progressing chronic disability in low back pain (LBP) patients primary care population. However, less is known about predictors change function after treatment specialty
Abstract Background Context There are a number of risk factors- from biological, psychological, and social domains- for non-specific chronic low back pain (cLBP). Many cLBP treatments target factors on the assumption that targeted factor is not just associated with but also cause (i.e, causal factor). In most cases this strong assumption, primarily due to possibility confounding variables. False assumptions about relationships between likely contribute generally marginal results treatments....
Abstract Introduction: Care and outcomes for patients with chronic low back pain (cLBP) are influenced by the social risk factors that they experience. Social such as food insecurity housing instability have detrimental effects on patient health wellness, healthcare outcomes, disparities. Objectives: This retrospective cross-sectional study examined how identified in unstructured structured electronic record (EHR) data 1,295 cLBP were associated care utilization. We also studied impact of...
Decision-making in spine surgery is complex due to patients' heterogeneity and complexity of spinal pathologies the various surgical options applied a given pathology. Artificial intelligence/machine learning algorithms provide an opportunity improve patient selection, planning, outcomes. The purpose this article present experience applications at 2 large academic health care systems.
Abstract Background Chronic low back pain (cLBP) is the leading cause of disability worldwide. Current treatments have minor or moderate effects, partly because idiopathic nature most cLBP cases, complexity its presentation, and heterogeneity in population. Explaining this by identifying subgroups patients critical for personalized health. Clinical decisions tailoring treatment to patients’ subgroup characteristics specific responses can improve health outcomes. patient stratification tools...
Background: In Spring 2019, the University of California (UC) health system launched a UC Wide Diabetes Initiative. response to growing population people with diabetes, as well significant heterogeneity in diabetes care across five campuses, Health Initiative aims increase alignment methods delivery, and improve clinical outcomes. Methods: The joins financially operationally independent academic medical campuses - Davis, San Francisco, Los Angeles, Irvine, Diego. Endocrinologists, primary...
<sec> <title>BACKGROUND</title> In epidemiological studies, finding the best subset of factors is challenging when number explanatory variables large. </sec> <title>OBJECTIVE</title> Our study had two aims. First, we aimed to identify essential depression-associated using extreme gradient boosting (XGBoost) machine learning algorithm from big survey data (the Korea National Health and Nutrition Examination Survey, 2012-2016). Second, achieve a comprehensive understanding multifactorial...