A5002272507- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare
- Chronic Disease Management Strategies
- Sepsis Diagnosis and Treatment
- Dialysis and Renal Disease Management
- Hearing Loss and Rehabilitation
- Trauma and Emergency Care Studies
- Emergency and Acute Care Studies
- Blood Pressure and Hypertension Studies
- Hearing, Cochlea, Tinnitus, Genetics
- Vestibular and auditory disorders
- Heart Failure Treatment and Management
- Multimodal Machine Learning Applications
- AI-based Problem Solving and Planning
- Electronic Health Records Systems
- Healthcare Systems and Public Health
- Bayesian Modeling and Causal Inference
- Advanced Image and Video Retrieval Techniques
- Healthcare Systems and Reforms
- Health disparities and outcomes
- Time Series Analysis and Forecasting
- Semantic Web and Ontologies
- Thyroid Cancer Diagnosis and Treatment
- Cardiovascular Health and Risk Factors
- Image Retrieval and Classification Techniques
Peking University
2015-2024
Beijing Academy of Artificial Intelligence
2024
Zhejiang Institute of Science and Technology Information
2023
Beijing Institute of Big Data Research
2023
University of Manchester
2008-2011
Abstract Background Early and accurate identification of sepsis patients with high risk in-hospital death can help physicians in intensive care units (ICUs) make optimal clinical decisions. This study aimed to develop machine learning-based tools predict the hospital ICUs. Methods The source database used for model development validation is medical information mart (MIMIC) III. We identified adult using new definition Sepsis-3. A total 86 predictor variables consisting demographics,...
BackgroundWith the outbreak of coronavirus disease 2019 (COVID-19), nurses have won well-deserved recognition for their indispensable roles in providing humane and professional healthcare patients. However, by nature role working at forefront patient care, are prone to experiencing mental health consequences. Therefore, we pay attention measuring magnitude psychological symptoms identifying associated factors among China.MethodsWe launched a nationwide, cross-sectional survey who worked...
Particulate of diameter ≤ 1 µm (PM
We propose to employ evidential reasoning (ER) rule construct a clinical decision support system (CDSS) aid physicians predict the probability of intensive care unit (ICU) admission and in-hospital death for trauma patients once they arrive at hospital. A generalized Bayesian is used mine evidence from historical data. Evidence profiled using format belief distribution, where degrees different outcomes are assigned with derived probabilities linked corresponding outcomes. Inputs CDSS data...
Background: Frailty is an epidemic age-related syndrome addressing heavy burden to the healthcare system. Subject rarity, age-, and gender-specific prevalence of frailty its prognosis among longevous population remains under-investigated. Methods: Based on Chinese Longitudinal Healthy Longevity Study (CLHLS, 2008–2018), individuals aged ≥ 65 years having complete data were recruited. Modified Fried criteria (exhaustion, shrink, weakness, low mobility, inactivity) adopted define pre-frailty...
Background Accumulated researches revealed that both fine particulate matter (PM 2.5 ) and sunlight exposure may be a risk factor for obesity, while regarding the potential effect modification by on relationship between PM obesity are limited. We aim to investigate whether of is affected among general population in China. Methods A sample 47,204 adults China was included. Obesity abdominal were assessed based body mass index, waist circumference waist-to-hip ratio, respectively. The...
Objective Trauma is China's fifth leading cause of death and ranked first among youths. databases have been well-established in many countries to announce the current state trauma rescue, treatment care. Nevertheless, China hasn't yet established a comparable database. This paper included two national-level describe situation epidemiological characteristics incidence, which sought provide data support for decision-making, resource allocation, prevention, management, other aspects. Methods...
Abstract Background Seasonal associations of cardiovascular mortality have been noted in most populations European origin years ago, but are not well evaluated Asian recently. Methods Utilizing the electronic Hospitalization Summary Reports (HSRs) from 32 top-ranked hospitals Beijing, China, we association between winter season and risk death among hospitalized individuals. General additive models logistic regression were adjusted for confounding factors. Results Older patients who admitted...
This study aimed to construct machine learning (ML) models for predicting prolonged length of stay (pLOS) in intensive care units (ICU) among general ICU patients. A multicenter database called eICU (Collaborative Research Database) was used model derivation and internal validation, the Medical Information Mart Intensive Care (MIMIC) III external validation. We four different ML methods (random forest, support vector machine, deep learning, gradient boosting decision tree (GBDT)) develop...
<sec> <title>BACKGROUND</title> Hearing loss and depression are important health issues among the middle-aged older population. </sec> <title>OBJECTIVE</title> This study aimed to investigate associations between hearing depressive symptom trajectories in Chinese <title>METHODS</title> The survey data of 2011, 2013, 2015, 2018 waves collected China Health And Retirement Longitudinal Study (CHARLS) was used for analysis. Latent Growth Mixture Modeling (LGMM) approach employed examine...
Abstract: A critical issue in the clinical decision support system (CDSS) research area is how to represent and reason with both uncertain medical domain knowledge symptoms arrive at accurate conclusions. Although a number of methods tools have been developed past two decades for modelling guidelines, few those capabilities handling uncertainties that exist almost every stage decision‐making process. This paper describes apply recently generic rule‐base inference methodology using evidential...
Background With market-oriented economic and health-care reform, public hospitals in China have received unprecedented pressures from governmental regulations, opinions, financial demands. To adapt the changing environment keep pace of modernizing healthcare delivery system, are expanding clinical services improving efficiency, while controlling costs. Recent experiences valuable lessons for guiding future reform. Here we carefully study three teaching hospitals, to exemplify their during...
Abstract Background The relationship between kidney function and hearing loss has long been recognized, but evidence of this association mostly comes from small observational studies or other populations. aim study is to explore the reduced in a large population-based among middle-aged elderly Chinese. Methods Data collected Chinese Health Retirement Longitudinal Study (CHARLS) 2015 were used for analysis. A cross-sectional was conducted 12,508 participants aged 45 years older. Hearing loss,...
Chronic kidney disease (CKD) is an important public health problem worldwide. However, there are few active surveillance systems for it. The China Kidney Disease Network (CK-NET) was established as a comprehensive system CKD using various data sources. As part of this, the proposed CK-NET-Yinzhou study aims to build regional in developed coastal area obtain detailed dynamic information about and improve ability manage effectively.
Abstract Background Patients receiving maintenance hemodialysis (HD) and peritoneal dialysis (PD) are frequently hospitalized. Reducing unplanned 30-day hospital readmissions is a key priority for improving the quality of health care. The purpose this study was to assess association between Charlson Comorbidity Index (CCI), which has been used evaluate multi-comorbidities status, readmission in patients on HD PD therapy. Methods Hospital Quality Monitoring System (HQMS), national...