A5033430702- Pancreatic and Hepatic Oncology Research
- Pancreatitis Pathology and Treatment
- COVID-19 epidemiological studies
- Brain Tumor Detection and Classification
- COVID-19 Clinical Research Studies
- AI in cancer detection
- COVID-19 and healthcare impacts
- Radiomics and Machine Learning in Medical Imaging
- Cardiac, Anesthesia and Surgical Outcomes
- Advanced Causal Inference Techniques
- Remote-Sensing Image Classification
- Sepsis Diagnosis and Treatment
- Air Quality and Health Impacts
- Remote Sensing in Agriculture
- Statistical Methods and Bayesian Inference
- Hemodynamic Monitoring and Therapy
- Statistical Methods and Inference
- Climate Change and Health Impacts
- Machine Learning in Healthcare
- Gallbladder and Bile Duct Disorders
- COVID-19 Impact on Reproduction
- Medical Imaging and Analysis
- Dementia and Cognitive Impairment Research
- Medical Image Segmentation Techniques
- Diverse Scientific Research Studies
West China Medical Center of Sichuan University
2020-2024
Sichuan University
2019-2024
West China Hospital of Sichuan University
2019-2024
Chengdu Medical College
2022
Abstract The Einstein Probe (EP) is an interdisciplinary mission of time-domain and X-ray astronomy. Equipped with a wide-field lobster-eye focusing imager, EP will discover cosmic transients monitor the variability known sources in 0.5–4 keV, at combination detecting sensitivity cadence that not accessible to previous current monitoring missions. can perform quick characterisation or outbursts Wolter-I telescope onboard. In this paper, science objectives are presented. expected enlarge...
The identification and enumeration of medicinal plants at high elevations is an important part accurate yield calculations. However, the current assessment plant reserves continues to rely on field sampling surveys, which are cumbersome time-consuming. Recently, unmanned aerial vehicle (UAV) remote sensing deep learning (DL) have provided ultrahigh-resolution imagery high-accuracy object recognition techniques, respectively, providing excellent opportunity improve manual surveying plants....
Abstract Introduction The automatic segmentation of the liver is a crucial step in obtaining quantitative biomarkers for accurate clinical diagnosis and computer-aided decision support systems. This task challenging due to frequent presence noise sampling artifacts computerized tomography (CT) images, as well complex background, variable shapes, blurry boundaries liver. Standard medical images based on full-supervised convolutional networks demands dense annotations. Such learning framework...
Background Timely and accurate prediction of short-term mortality is critical in intensive care units (ICUs), where patients’ conditions change rapidly. Traditional scoring systems, such as the Simplified Acute Physiology Score Chronic Health Evaluation, rely on static variables collected within first 24 hours admission do not account for continuously evolving clinical states. These systems lack real-time adaptability, interpretability, generalizability. With increasing availability...
Abstract Background Climate change caused by environmental pollution is the most important one of many health hazards currently faced human beings. In particular, extreme temperature an risk factor for death from respiratory and circulatory diseases. This study aims to explore meteorological-health effect find out vulnerable individuals events in a less developed city western China. Method We collected meteorological data diseases Mianyang City 2013 2019. The nonlinear distributed lag model...
Objective To examine the current prevalence and cost of paediatric off-label drug prescriptions in Gansu, China, potential influencing factors. Design The paediatrics was evaluated according to National Medical Products Administration instructions China Pharmaceutical Reference (China Reference, MCDEX) database. evidence prescription determined by existing clinical practice guidelines Thomson Grade Micromedex 2021 compendium. We used logistic regression investigate characteristics that...
This study investigated the association between body mass index (BMI) trajectories in late middle age and incident diabetes later years. A total of 11,441 participants aged 50-60 years from Health Retirement Study with at least 2 self-reported BMI records were included. Individual representing average changes per year generated using multilevel modeling. Adjusted risk ratios (ARRs) 95% confidence intervals (95% CIs) calculated. Associations different genetic risks estimated for 5,720...
This study investigated the effects of tidal volume (TV) on diagnostic value pulse pressure variation (PPV) and inferior vena cava dispensability index (IVC-DI) for responsiveness during mechanical ventilation. In patients undergoing elective surgery with ventilation, different TVs 6, 9, 12 mL/kg were given two min. The left ventricular outflow tract velocity-time integral (VTI) was measured by transthoracic echocardiography. IVC-DI at sub-xyphoid transabdominal long axis. PPV via radial...
Current approaches to predicting intervention needs and mortality have reached 65-85% accuracy, which falls below clinical decision-making requirements in patients with acute pancreatitis (AP). We aimed accurately predict therapeutic on admission, AP patients, using machine learning (ML).Data were obtained from three databases of admitted AP: one retrospective (Chengdu) two prospective (Liverpool Chengdu) databases. Intervention differences, as well potential predictors, investigated....
Previous research focused on the qualitative discussion of correlation between surgical time and mortality in acute pancreatitis (AP). Recommendations for timing necrotizing are delayed as far possible, without recommendations individuals. The aim this article is to predict intervention with recurrent neural network (RNN). Time series data AP were retrospectively extracted from a hospital China (n = 15,813) develop model, Cerner Health Facts database United States 142,650) was used...
Hepatobiliary tumor is one of the common tumors and cancers in medicine, which seriously affects people’s lives, so how to accurately diagnose it a very serious problem. This article mainly studies diagnostic method microscopic images liver gallbladder tumors. Under this research direction, proposes use convolutional neural network learn hyperspectral it. It found that addition can greatly improve actual map classification accuracy map, effectively success rate treatment. At same time,...
To develop a highly discriminative machine learning model for the prediction of intensive care unit admission (>24h) using easily available preoperative information from electronic health records. An accurate ICU after surgery is great importance surgical risk assessment and appropriate utilization resources.Data were collected retrospectively large hospital, comprising 135,442 adult patients who underwent except cardiac between 1 January 2014, 31 July 2018 in China. Multiple existing...
It is of great significance to establish an assessment model for organ failures in the early stage admission acute pancreatitis (AP). And clinical notes are underutilized. To predict AP patients using hospital, text features obtained from pretrained Chinese Bidirectional Encoder Representations Transformers and attention-based LSTM were combined with structured (laboratory tests, vital signs, demographic characteristics) (respiratory, cardiovascular, renal) 12,748 inpatients West China...
Gentiana szechenyii Kanitz. and veitchiorum Hemsl. are two wild medicinal plants widely used in Tibetan medicine. In recent decades, their populations have declined rapidly due to persistent over-harvesting of flowers. Because flowers small dense, it is difficult rely on manual counting under conditions. The combination deep learning unmanned aerial vehicle remote sensing (UAVRS) a new method for plant surveys. We trained 12 the most advanced or YOLO models custom dataset achieve...
<title>Abstract</title> Background: Transcatheter aortic valve replacement (TAVR) has become a popular alternative to surgical (SAVR) for patients with valvular heart disease (VHD), particularly those anomalies. Objectives: The study aimed compare the risks of post-TAVR complications between bicuspid and tricuspid valves identify associated risk factors. Methods: association type (bicuspid or tricuspid) was assessed. also explored various combinations factors understand their impact on...
Liver cancer is a significant cause of cancer-related mortality worldwide and requires tailored treatment strategies for different types. However, preoperative accurate diagnosis the type presents challenge. This study aims to develop an automatic diagnostic model based on multi-phase contrast-enhanced CT (CECT) images distinguish between hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (ICC), normal individuals.
<sec> <title>BACKGROUND</title> Timely and accurate prediction of short-term mortality is critical in intensive care units (ICUs), where patients’ conditions change rapidly. Traditional scoring systems, such as the Simplified Acute Physiology Score Chronic Health Evaluation, rely on static variables collected within first 24 hours admission do not account for continuously evolving clinical states. These systems lack real-time adaptability, interpretability, generalizability. With increasing...
Objective . In order to find the quantitative relationship between timing of surgical intervention and risk death in necrotizing pancreatitis. Methods The generalized additive model was applied quantitate time (from onset acute pancreatitis first intervention) adjusted for demographic characteristics, infection, organ failure, important lab indicators extracted from Electronic Medical Record West China Hospital Sichuan University. Results We analyzed 1,176 inpatients who had pancreatic...