A5029634063- Nursing Diagnosis and Documentation
- Urinary Tract Infections Management
- Electronic Health Records Systems
- Palliative Care and End-of-Life Issues
- AI in cancer detection
- Biomedical Text Mining and Ontologies
- Health and Wellbeing Research
- Machine Learning in Healthcare
- Global Cancer Incidence and Screening
- Data Quality and Management
- Sleep and related disorders
- Sepsis Diagnosis and Treatment
- Healthcare cost, quality, practices
- Clinical practice guidelines implementation
- Patient Satisfaction in Healthcare
- Pancreatitis Pathology and Treatment
- Big Data and Business Intelligence
- Colorectal Cancer Screening and Detection
- COVID-19 Clinical Research Studies
- Dementia and Cognitive Impairment Research
- Cancer survivorship and care
- Spreadsheets and End-User Computing
- Sleep and Work-Related Fatigue
- Statistical Methods in Epidemiology
- Family Caregiving in Mental Illness
University of California, Irvine
2019-2025
National Institutes of Health
2017-2023
Ulsan National Institute of Science and Technology
2023
Lee University
2023
National Institute on Minority Health and Health Disparities
2023
University of Minnesota
2014-2019
Stanford University
2018
Fairview Health Services
2017
Background: Sleep disturbances, such as difficulty in falling asleep and multiple awakenings at night, are prevalent among persons with Alzheimer’s disease related dementias (hereafter dementia), resulting advanced cognitive impairment increased behavioral problems. Additionally, family caregivers (eg, spouses or offspring) suffer from reduced sleep quality a result of disturbances the dementia (PWDs) they care for. Relatively little is known about interaction parameters dyads...
Background The rapid spread of coronavirus disease 2019 (COVID-19) revealed significant constraints in critical care capacity. In anticipation subsequent waves, reliable prediction severity is essential for capacity management and may enable earlier targeted interventions to improve patient outcomes. purpose this study develop externally validate a prognostic model/clinical tool predicting COVID-19 at presentation medical care. Methods This retrospective model the where was defined as ICU...
Massive generation of health-related data has been key in enabling the big science initiative to gain new insights healthcare. Nursing can benefit from this era science, as there is a growing need for discoveries large quantities nursing provide evidence-based care. However, are few studies using analytics. The purpose article explain knowledge discovery and mining approach that was employed discover about hospital-acquired catheter-associated urinary tract infections multiple sources,...
The purpose of this study was to create information models from flowsheet data using a data-driven consensus-based method. Electronic health records contain large volume about patient assessments and interventions captured in flowsheets that measure the same "thing," but names these observations often differ, according who performs documentation or location service (eg, pulse rate an intensive care, emergency department, surgical unit documented by nurse therapist automated monitoring)....
Survival machine learning (ML) has been suggested as a useful approach for forecasting future events, but growing concern exists that ML models have the potential to cause racial disparities through data used train them. This study aims develop race/ethnicity-specific survival Hispanic and black women diagnosed with breast cancer examine whether outperform general trained all races/ethnicity data.We from US National Cancer Institute's Surveillance, Epidemiology End Results programme...
Objective The study aimed to develop natural language processing (NLP) algorithms automate extracting patient-centred breast cancer treatment outcomes from clinical notes in electronic health records (EHRs), particularly for women under-represented populations. Methods used 2010 2021 a tertiary hospital the USA. were processed through various NLP techniques, including vectorisation methods (term frequency-inverse document frequency (TF-IDF), Word2Vec, Doc2Vec) and classification models...
Abstract Background Recent epidemiological evidence has demonstrated a higher rate of COVID-19 hospitalizations and deaths among minorities. This pattern race-ethnic disparities emerging throughout the United States raises question what social factors may influence spread highly transmissible novel coronavirus. The purpose this study is to describe socioeconomic associated with in patients our community Orange County, California understand role individual-level factors, neighborhood-level...
PURPOSE: The purpose of this study was to identify factors associated with healthcare-acquired catheter-associated urinary tract infections (HA-CAUTIs) using multiple data sources and mining techniques. SUBJECTS AND SETTING: Three sets were integrated for analysis: electronic health record from a university hospital in the Midwestern United States combined staffing environmental hospital's National Database Nursing Quality Indicators list patients HA-CAUTIs. METHODS: techniques used...
Abstract Purpose The aim of the study was to develop and validate machine learning models predict personalized risk for 30‐day readmission with venous thromboembolism (VTE). Design This a retrospective, observational study. Methods We extracted preprocessed structured electronic health records (EHRs) from single academic hospital. Then we developed evaluated three prediction using logistic regression, balanced random forest model, multilayer perceptron. Results sample included 158,804 total...
Objectives We examined the association of urinary incontinence (UI) with physical, mental, and social health among older Korean Americans living in subsidized senior housing.
Abstract Purpose The aim of the study was to develop a prediction model using deep learning approach identify breast cancer patients at high risk for chronic pain. Design This retrospective, observational study. Methods We used demographic, diagnosis, and social survey data from NIH ‘All Us’ program approach, specifically Transformer‐based time‐series classifier, evaluate our model. Results final dataset included 1131 patients. evaluated model, which achieved an accuracy 72.8% area under...
Objective: This study aims to develop and validate an evaluation framework ensure the safety reliability of mental health chatbots, which are increasingly popular due their accessibility, human-like interactions, context-aware support. Materials Methods: We created with 100 benchmark questions ideal responses, five guideline for chatbot responses. framework, validated by experts, was tested on a GPT-3.5-turbo-based chatbot. Automated methods explored included large language model (LLM)-based...
This study aimed to use wearable technology predict the sleep quality of family caregivers people with dementia among underrepresented groups. Caregivers often experience high levels stress and poor sleep, those from communities face additional burdens, such as language barriers cultural adaptation challenges. Participants, consisting 29 populations, wore smartwatches that tracked various physiological behavioral markers, including level, heart rate, steps taken, duration stages, overall...
Abstract Background The rapid spread of coronavirus disease 2019 (COVID-19) revealed significant constraints in critical care capacity. In anticipation subsequent waves, reliable prediction severity is essential for capacity management and may enable earlier targeted interventions to improve patient outcomes. purpose this study develop externally validate a prognostic model/clinical tool predicting COVID-19 at presentation medical care. Methods This retrospective model the where was defined...