A5106481242- Artificial Intelligence in Healthcare and Education
- Heart Failure Treatment and Management
- Radiomics and Machine Learning in Medical Imaging
- Coronary Interventions and Diagnostics
- Tracheal and airway disorders
- Topic Modeling
- Cardiac Structural Anomalies and Repair
- Biomedical Text Mining and Ontologies
- Text Readability and Simplification
- Nuclear reactor physics and engineering
- Pneumocystis jirovecii pneumonia detection and treatment
- Intracerebral and Subarachnoid Hemorrhage Research
- Nutrition and Health in Aging
- Genomics and Rare Diseases
- Brain Metastases and Treatment
- Bone and Joint Diseases
- Stroke Rehabilitation and Recovery
- Coronary Artery Anomalies
- Lipid metabolism and disorders
- Machine Learning in Healthcare
- Chronic Disease Management Strategies
- Vascular Malformations Diagnosis and Treatment
- Nuclear Engineering Thermal-Hydraulics
- Cancer-related cognitive impairment studies
- Medicinal plant effects and applications
Second Military Medical University
2025
Sichuan University
2023-2025
West China Hospital of Sichuan University
2023-2024
Hebei University of Engineering
2023
Capital Medical University
2010-2019
Beijing Tongren Hospital
2006-2019
Xi'an Jiaotong University
2018
Beijing Anzhen Hospital
2010-2017
Yale University
2014
University of Colorado Denver
2009
Abstract The use of large language models (LLMs) in clinical medicine is currently thriving. Effectively transferring LLMs’ pertinent theoretical knowledge from computer science to their application crucial. Prompt engineering has shown potential as an effective method this regard. To explore the prompt LLMs and examine reliability LLMs, different styles prompts were designed used ask about agreement with American Academy Orthopedic Surgeons (AAOS) osteoarthritis (OA) evidence-based...
The efficacy of large language models (LLMs) in domain-specific medicine, particularly for managing complex diseases such as osteoarthritis (OA), remains largely unexplored.
Background We investigated whether 1-year trajectories of cancer-related cognitive decline (CRCD) would be different in patients with chemotherapy combined immune checkpoint inhibitors (chemoICI group) as compared alone (chemo group). Methods Participants scheduled or without ICI were prospectively recruited from three academic hospitals and followed up for 1 year four sessions. Subjective objective CRCD measured by Perceived Cognitive Impairment (PCI) Montreal Assessment (MoCA),...
Large Language Models (LLMs) show promise in healthcare tasks but face challenges complex medical scenarios. We developed a Multi-Agent Conversation (MAC) framework for disease diagnosis, inspired by clinical Multi-Disciplinary Team discussions. Using 302 rare cases, we evaluated GPT-3.5, GPT-4, and MAC on knowledge reasoning. outperformed single models both primary follow-up consultations, achieving higher accuracy diagnoses suggested tests. Optimal performance was achieved with four doctor...
The eukaryotic translation initiation factor eIF4E recognizes the mRNA cap, a key step in initiation. Here we have characterized from human parasite Schistosoma mansoni. Schistosome mRNAs either typical monomethylguanosine (m(7)G) or trimethylguanosine (m(2,2,7)G) cap derived spliced leader trans-splicing. Quantitative fluorescence titration analyses demonstrated that schistosome has similar binding specificity for both caps. We present first crystal structure of an with m(7)G and m(2,2,7)G...
Abstract Background GPT-4 is a newly developed large language model that has been preliminarily applied in the medical field. However, GPT-4’s relevant theoretical knowledge of computer science not effectively transferred to Objective To explore application prompt engineering and examine reliability GPT-4. Methods Different styles prompts were designed used ask questions about agreement with American Academy Orthopaedic Surgeons (AAOS) osteoarthritis (OA) evidenced-based guidelines. Each...
What is known and objective Although the long-term infusion of ANP has proved effective to treat heart failure, no published randomized controlled study been reported confirm efficacy short-term in congestive failure (CHF) patients. This was designed assess safety recombinant human atrial natriuretic peptide (rhANP) CHF Methods A total 48 patients with were enrolled into four groups, treated standard therapy or rhANP (0·05, 0·1 0·2 μg/kg/min) for 1-hour addition therapy. The hemodynamics...
In this paper, we propose a novel method for assigned MURA generation using diffusion model. is well-known problem in the display industry, which difficult to be inspected because it characterized by low contrast, blurry contours, blocky uneven brightness, and irregular shape patterns, most defects have no rules follow. Especially, data-driven deep learning, shortage of samples collecting from pipeline manufactory first challenging problem, sample happens with probability various ways. To...
Abstract Importance This study adopted multi-agent framework in large language models to enhance diagnosis complex medical cases, particularly rare diseases, revealing limitation current training and benchmarking of LLMs healthcare. Objective aimed develop MAC for diagnosis, compare the knowledge base diagnostic capabilities GPT-3.5, GPT-4, context diseases. Design, Setting Participants examined 150 diseases using clinical case reports published after January 1, 2022, from Medline database....
<sec> <title>BACKGROUND</title> Artificial intelligence (AI) and large language models (LLMs) are emerging as the transformative force in various fields, notably medicine. Their effectiveness creating physical exercise rehabilitation program providing information on musculoskeletal (MSK) disorders has yet to be fully explored. </sec> <title>OBJECTIVE</title> To assess quality readability of an LLM’s responses consultation questions addressing phases throughout entire clinical process...
<sec> <title>BACKGROUND</title> The efficacy of large language models (LLMs) in domain-specific medicine, particularly for managing complex diseases such as osteoarthritis (OA), remains largely unexplored. </sec> <title>OBJECTIVE</title> This study focused on evaluating and enhancing the clinical capabilities explainability LLMs specific domains, using OA management a case study. <title>METHODS</title> A benchmark framework was developed to evaluate across spectrum from knowledge...
Building extraction from high-resolution remote sensing images has various applications, such as urban planning and population estimation. However, buildings have intraclass heterogeneity interclass homogeneity in with complex backgrounds, which makes the accurate of building instances challenging regular boundaries difficult to maintain. In this paper, an attention-gated direction-field-optimized instance network (AGDF-Net) is proposed. Two refinements are presented, including...
To retrospectively analysed echocardiographic characteristics of ventricular diverticula in fetuses, children and adults. Echocardiographic 8 3 12 adults were summarised, including the position, type size diverticula, other cardiac extracardiac abnormalities. Meantime, clinical histories, accessory examinations, intraoperative findings cases collected outcomes fetal followed up. There muscular 5 fibrous cases. 2 born, terminated pregnancy lost to follow 1 diverticulum, found Of 14 adult...
Abstract Background Sarcopenia and osteoarthritis are prevalent age-related diseases that mutually exacerbate each other, creating a vicious cycle worsens both conditions. Exercise is key to breaking this detrimental cycle. Facing increasing demand for rehabilitation services within patient demographic, ChatGPT-4 wearable device may increase the availability, efficiency personalization of such health care. Aim To evaluate clinical efficacy cost-effectiveness system implemented on mobile...
<h3>Objective</h3> To study the relationship between NT-proBNP levels obtained on admission and GRACE risk score as well stratification in patients with NSTEACS (UA/NSTEMI). <h3>Methods</h3> We enrolled 126 unstable angina or Non-ST-segment elevation myocardial infarction that admitted our hospital from June of 2009 to May 2010, 84 UA 42 them NSTEMI. Then measured their concentration plasma NT-proBNP, cTnI, CK-MB, liver kidney function, blood coagulation function other Routine laboratory...
People'