A5101475016- Retinal Imaging and Analysis
- Pregnancy and preeclampsia studies
- Artificial Intelligence in Healthcare
- Retinal Diseases and Treatments
- Birth, Development, and Health
- Artificial Intelligence in Healthcare and Education
- Gestational Diabetes Research and Management
- Machine Learning in Healthcare
- Advanced Decision-Making Techniques
- Synthesis and Catalytic Reactions
- Chemical Synthesis and Reactions
- Pregnancy and Medication Impact
- Chronic Kidney Disease and Diabetes
- Drug Transport and Resistance Mechanisms
- Cardiac Valve Diseases and Treatments
- Acute Ischemic Stroke Management
- Hip disorders and treatments
- Glaucoma and retinal disorders
- Sulfur-Based Synthesis Techniques
- Simulation and Modeling Applications
- Orthopaedic implants and arthroplasty
- Evaluation and Optimization Models
Shanghai Sixth People's Hospital
2023-2025
Shanghai Jiao Tong University
2023-2025
Beijing Academy of Artificial Intelligence
2025
Hunan University of Science and Engineering
2024
Women's Hospital, School of Medicine, Zhejiang University
2023
Abstract Diabetic retinopathy (DR) is the leading cause of preventable blindness worldwide. The risk DR progression highly variable among different individuals, making it difficult to predict and personalize screening intervals. We developed validated a deep learning system (DeepDR Plus) time within 5 years solely from fundus images. First, we used 717,308 images 179,327 participants with diabetes pretrain system. Subsequently, trained multiethnic dataset comprising 118,868 29,868 diabetes....
Abstract Primary diabetes care and diabetic retinopathy (DR) screening persist as major public health challenges due to a shortage of trained primary physicians (PCPs), particularly in low-resource settings. Here, bridge the gaps, we developed an integrated image–language system (DeepDR-LLM), combining large language model (LLM module) image-based deep learning (DeepDR-Transformer), provide individualized management recommendations PCPs. In retrospective evaluation, LLM module demonstrated...
Improving the accessibility of screening diabetic kidney disease (DKD) and differentiating isolated nephropathy from non-diabetic (NDKD) are two major challenges in field diabetes care. We aimed to develop validate an artificial intelligence (AI) deep learning system detect DKD retinal fundus images. In this population-based study, we developed a image-based AI-deep system, DeepDKD, pretrained using 734 084 First, for detection, used 486 312 images 121 578 participants Shanghai Integrated...
Intrahepatic cholestasis of pregnancy (ICP) is an idiopathic disease that occurs during mid-to-late and associated with various adverse outcomes, including intrauterine fetal demise. However, since the underlying cause ICP remains unclear, there ongoing debate on phenotyping criteria used in diagnostic process. Here, we identified single- multi-symptomatic (ICP-S ICP-M) 104,221 Chinese females from ZEBRA maternity cohort, objective exploring risk implications two phenotypes outcomes...
A convenient and practical method for the synthesis of various
<title>Abstract</title> Medical foundation models (FM), pre-trained on large-scale unlabelled data, have demonstrated robust performance and high efficiency when fine-tuned to various clinically relevant applications. However, the impact of pre-training data medical FM such as generalisability fairness, which form in models, remains unexplored. To address this, we sampled two large cohorts from sites, Moorfields Eye Hospital (UK) Shanghai Diabetes Prevention Program (China), each containing...
Background Preeclampsia (PE) is one of the most common hypertensive diseases, affecting 2%-8% all pregnancies. The high maternal and fetal mortality rates PE are due to a lack early identification affected pregnant women that would have led closer monitoring care. Recent data suggest misfolded proteins might be promising biomarker for prediction, which can detected in urine samples according their congophilia (aggregated) characteristic. Objective main purpose this trial evaluate value...
<sec> <title>BACKGROUND</title> Preeclampsia (PE) is one of the most common hypertensive diseases, affecting 2%-8% all pregnancies. The high maternal and fetal mortality rates PE are due to a lack early identification affected pregnant women that would have led closer monitoring care. Recent data suggest misfolded proteins might be promising biomarker for prediction, which can detected in urine samples according their congophilia (aggregated) characteristic. </sec> <title>OBJECTIVE</title>...