A5048778597- Gestational Diabetes Research and Management
- Pregnancy and preeclampsia studies
- Patient Dignity and Privacy
- Artificial Intelligence in Healthcare and Education
- Caching and Content Delivery
- COVID-19 diagnosis using AI
- Ethics in Clinical Research
- Birth, Development, and Health
- Privacy, Security, and Data Protection
- Machine Learning in Healthcare
- Ophthalmology and Visual Impairment Studies
- Covalent Organic Framework Applications
- Ammonia Synthesis and Nitrogen Reduction
- Retinopathy of Prematurity Studies
- Healthcare Systems and Public Health
- Artificial Intelligence in Healthcare
- Ferroptosis and cancer prognosis
- Sepsis Diagnosis and Treatment
- Ophthalmology and Visual Health Research
- SARS-CoV-2 and COVID-19 Research
- Olfactory and Sensory Function Studies
- Bioinformatics and Genomic Networks
- Focus Groups and Qualitative Methods
- Gene expression and cancer classification
- Medical Coding and Health Information
Beijing Academy of Artificial Intelligence
2022-2025
Shanghai Artificial Intelligence Laboratory
2022-2025
General Hospital of Central Theater Command
2021
IMPORTANCE Identifying pediatric eye diseases at an early stage is a worldwide issue. Traditional screening procedures depend on hospitals and ophthalmologists, which are expensive time-consuming. Using artificial intelligence (AI) to assess children’s conditions from mobile photographs could facilitate convenient identification of disorders in home setting. OBJECTIVE To develop AI model identify myopia, strabismus, ptosis using photographs. DESIGN, SETTING, AND PARTICIPANTS This...
Accurate third-trimester birth weight prediction is vital for reducing adverse outcomes, and machine learning (ML) offers superior precision over traditional ultrasound methods. This study aims to develop an ML model on the basis of clinical big data accurate in third trimester pregnancy, which can help reduce maternal fetal outcomes. From January 1, 2018 December 31, 2019, a retrospective cohort involving 16,655 singleton live births without congenital anomalies (>28 weeks gestation) was...
Although new technologies have increased the efficiency and convenience of medical care, patients still struggle to identify specialized outpatient departments in Chinese tertiary hospitals due a lack knowledge.
The availability of high-throughput sequencing data creates opportunities to comprehensively understand human diseases as well challenges train machine learning models using such high dimensions data. Here, we propose a denoised multi-omics integration framework, which contains distribution-based feature denoising algorithm, Feature Selection with Distribution (FSD), for dimension reduction and Attention Multi-Omics Integration (AttentionMOI) predict cancer prognosis identify subtypes. We...
Clinical guidelines for the management of individuals with type 2 diabetes mellitus endorse systematic assessment atherosclerotic cardiovascular disease risk early interventions. In this study, we aimed to develop machine learning models predict 3-year in Chinese patients.Clinical records 4,722 admitted 94 hospitals were used. The features included demographic information, histories, laboratory tests and physical examinations. Logistic regression, support vector machine, gradient boosting...
Abstract Background Fetal macrosomia is associated with an increased risk of several maternal and newborn complications. Antenatal predication fetal remains challenging. We aimed to develop a nomogram model for the prediction using real-world clinical data improve sensitivity specificity prediction. Methods In present study, we performed retrospective, observational study based on 13,403 medical records pregnant women who delivered singleton infants at tertiary hospital in Shanghai from 1...
Background Myopia, strabismus, and ptosis are common pediatric eye diseases, which have a negative impact on children adolescents in terms of visual function, mental health, health-related quality life (HRQoL). Therefore, this study focused those diseases by analyzing their risk factors HRQoL for the comprehensive management myopia, ptosis. Methods A total 363 participants (2–18 years old) were included analysis We collected demographic characteristics, lifestyle habits care these analyzed...
Considering the high incidence of medical privacy disclosure, it is vital importance to study doctors' protection behavior and its influencing factors.We aim develop a scale for patients' in Chinese public institutions, following construction theoretical model framework through grounded theory, subsequently validate measure this behavior.Combined with paradigm motivation theory (PMT) semistructured interview data, research method, followed by Delphi expert group discussion methods, initial...
Background: Although new technologies have increased the efficiency and convenience of medical care, patients still struggle to identify specialized outpatient departments in Chinese tertiary hospitals due a lack knowledge. Thereby, we aimed develop precise subdividable triage system improve experiences patient care.Methods: We collected 395,790 EMRs 500 dialogue groups. 387,876 (98%) each dataset was used design train model, 3,957 (1%) for testing validation. The evaluated by recommendation...
<sec> <title>BACKGROUND</title> Although new technologies have increased the efficiency and convenience of medical care, patients still struggle to identify specialized outpatient departments in Chinese tertiary hospitals due a lack knowledge. </sec> <title>OBJECTIVE</title> The objective our study was develop precise subdividable triage system improve experiences patient care. <title>METHODS</title> We collected 395,790 electronic records (EMRs) 500 dialogue groups. EMRs were divided into 3...
Objective: To develop a nomogram model for prediction of macrosomia with routine clinical data in pregnant women Chinese polulation.Methods: The present study retrospectively analyzed the medical records who delivered singleton infants tertiary hospital Shanghai from January 1st,2018 to December 31st, 2019. were randomly divided into two groups 4:1 ratio generate and validate model. independent risk factors by multivariate logistic regression, predict was established verified R software....
<sec> <title>BACKGROUND</title> Considering the high incidence of medical privacy disclosure, it is vital importance to study doctors’ protection behavior and its influencing factors. </sec> <title>OBJECTIVE</title> We aimed explore internal mechanism doctors' patients' in Chinese public institutions using grounded theory, order construct a theoretical model framework, develop, subsequently validate scale measure this behavior. <title>METHODS</title> Combined with PMT interview data, theory...
Background: Fetal weight can be evaluated fetal growth trends and screen for abnormal growth. Predicting the birth in late gestation effectively guide clinical decisions reduce adverse pregnancy outcomes. Antenatal predication of remains challenging. On basis big data, we aim to develop a machine learning (ML) model accurate prediction prenatal weight.Methods: From 1 January 2018 31 December 2019, retrospective cohort study involving 16655 singleton live births (> 28 weeks gestation) was...
Abstract Aim: To develop a nomogram model for the prediction of macrosomia using real-world clinical data. Methods: In present study, we retrospectively analyzed medical records pregnant women who delivered singleton infants at tertiary hospital in Shanghai from 1 January 2018 through 31 December 2019. We extracted data total 13,403 this with original dataset split into training set (n = 9,382) and validation 4,021) 7:3 ratio to generate validate our model. The independent risk factors were...