目的分析基于Clavien-Dindo分级的腹腔镜胆总管探查术(laparoscopic common bile duct exploration,LCBDE)术后并发症的相关因素,构建对应的预测模型并验证其效能。方法采用前瞻性研究,选取2023年1月至2025年5月于太仓市第一人民医院行L...目的分析基于Clavien-Dindo分级的腹腔镜胆总管探查术(laparoscopic common bile duct exploration,LCBDE)术后并发症的相关因素,构建对应的预测模型并验证其效能。方法采用前瞻性研究,选取2023年1月至2025年5月于太仓市第一人民医院行LCBDE的病人285例,以2∶1随机分为训练集、验证集,分别190例、95例。随访统计病人术后并发症Clavien-Dindo分级,将训练集病人中发生Clavien-Dindo分级≥Ⅱ级并发症者分为并发症≥Ⅱ级组,无并发症及Clavien-Dindo分级Ⅰ级并发症者分为并发症0~Ⅰ级组。比较两组一般资料,经多因素logistic回归模型分析ClavienDindo分级≥Ⅱ级并发症的影响因素,建立对应的预测模型,采用受试者操作特征(ROC)曲线、校正曲线验证其效能及区分度。结果并发症≥Ⅱ级组26例,并发症0~Ⅰ级组164例,并发症≥Ⅱ级组美国麻醉医师协会(ASA)分级≥Ⅲ级构成比、合并中/重度急性胆管炎构成比、查尔森合并症指数(Charlson comorbidity index,CCI)、术中出血量均高于并发症0~Ⅰ级组(均P<0.05),白蛋白水平低于并发症0~Ⅰ级组(P<0.05)。多因素logistic回归模型显示,以下因素是LCBDE术后发生Clavien-Dindo分级≥Ⅱ级并发症的危险因素:ASA分级≥Ⅲ级(OR=3.550,95%CI:1.271~9.915),CCI评分(OR=2.617,95%CI:1.151~5.949),合并中/重度急性胆管炎(OR=2.171,95%CI:1.296~3.635),术中出血量(OR=2.872,95%CI:1.322~6.241),均P<0.05;白蛋白(OR=0.426,95%CI:0.200~0.904)是保护因素(P<0.05);建立logistic回归方程:Logit函数=–12.874–0.854X1(白蛋白)+1.267X2(ASA分级≥Ⅲ级)+0.962X3(CCI评分)+0.775X4(合并中/重度急性胆管炎)+1.055X5(术中出血量)。ROC曲线显示,该模型预测训练集术后发生Clavien-Dindo分级≥Ⅱ级并发症的曲线下面积(AUC)为0.929,敏感度为84.62%,特异度为98.17%,预测验证集术后发生Clavien-Dindo分级≥Ⅱ级并发症的AUC为0.920,敏感度为92.31%,特异度为81.71%。HosmerLemeshow检验显示,该预测模型预测训练集、验证集病人术后发生Clavien-Dindo分级≥Ⅱ级并发症的概率与实际概率比较,差异均无统计学意义(训练集:χ^(2)=6.036,P=0.702;验证集:χ^(2)=7.254,P=0.512)。结论ASA分级≥Ⅲ级、CCI评分、合并中/重度急性胆管炎、术中出血量是LCBDE术后发生Clavien-Dindo分级≥Ⅱ级并发症的危险因素,白蛋白是保护因素,对应的预测模型经验证具有良好的预测效能。展开更多
A series of true triaxial unloading tests are conducted on sandstone specimens with a single structural plane to investigate their mechanical behaviors and failure characteristics under different in situ stress states...A series of true triaxial unloading tests are conducted on sandstone specimens with a single structural plane to investigate their mechanical behaviors and failure characteristics under different in situ stress states.The experimental results indicate that the dip angle of structural plane(θ)and the intermediate principal stress(σ2)have an important influence on the peak strength,cracking mode,and rockburst severity.The peak strength exhibits a first increase and then decrease as a function ofσ2 for a constantθ.However,whenσ2 is constant,the maximum peak strength is obtained atθof 90°,and the minimum peak strength is obtained atθof 30°or 45°.For the case of an inclined structural plane,the crack type at the tips of structural plane transforms from a mix of wing and anti-wing cracks to wing cracks with an increase inσ2,while the crack type around the tips of structural plane is always anti-wing cracks for the vertical structural plane,accompanied by a series of tensile cracks besides.The specimens with structural plane do not undergo slabbing failure regardless ofθ,and always exhibit composite tensile-shear failure whatever theσ2 value is.With an increase inσ2 andθ,the intensity of the rockburst is consistent with the tendency of the peak strength.By analyzing the relationship between the cohesion(c),internal friction angle(φ),andθin sandstone specimens,we incorporateθinto the true triaxial unloading strength criterion,and propose a modified linear Mogi-Coulomb criterion.Moreover,the crack propagation mechanism at the tips of structural plane,and closure degree of the structural plane under true triaxial unloading conditions are also discussed and summarized.This study provides theoretical guidance for stability assessment of surrounding rocks containing geological structures in deep complex stress environments.展开更多
Federated learning is a machine learning framework designed to protect privacy by keeping training data on clients’devices without sharing private data.It trains a global model through collaboration between clients a...Federated learning is a machine learning framework designed to protect privacy by keeping training data on clients’devices without sharing private data.It trains a global model through collaboration between clients and the server.However,the presence of data heterogeneity can lead to inefficient model training and even reduce the final model’s accuracy and generalization capability.Meanwhile,data scarcity can result in suboptimal cluster distributions for few-shot clients in centralized clustering tasks,and standalone personalization tasks may cause severe overfitting issues.To address these limitations,we introduce a federated learning dual optimization model based on clustering and personalization strategy(FedCPS).FedCPS adopts a decentralized approach,where clients identify their cluster membership locally without relying on a centralized clustering algorithm.Building on this,FedCPS introduces personalized training tasks locally,adding a regularization term to control deviations between local and cluster models.This improves the generalization ability of the final model while mitigating overfitting.The use of weight-sharing techniques also reduces the computational cost of central machines.Experimental results on MNIST,FMNIST,CIFAR10,and CIFAR100 datasets demonstrate that our method achieves better personalization effects compared to other personalized federated learning methods,with an average test accuracy improvement of 0.81%–2.96%.Meanwhile,we adjusted the proportion of few-shot clients to evaluate the impact on accuracy across different methods.The experiments show that FedCPS reduces accuracy by only 0.2%–3.7%,compared to 2.1%–10%for existing methods.Our method demonstrates its advantages across diverse data environments.展开更多
文摘目的分析基于Clavien-Dindo分级的腹腔镜胆总管探查术(laparoscopic common bile duct exploration,LCBDE)术后并发症的相关因素,构建对应的预测模型并验证其效能。方法采用前瞻性研究,选取2023年1月至2025年5月于太仓市第一人民医院行LCBDE的病人285例,以2∶1随机分为训练集、验证集,分别190例、95例。随访统计病人术后并发症Clavien-Dindo分级,将训练集病人中发生Clavien-Dindo分级≥Ⅱ级并发症者分为并发症≥Ⅱ级组,无并发症及Clavien-Dindo分级Ⅰ级并发症者分为并发症0~Ⅰ级组。比较两组一般资料,经多因素logistic回归模型分析ClavienDindo分级≥Ⅱ级并发症的影响因素,建立对应的预测模型,采用受试者操作特征(ROC)曲线、校正曲线验证其效能及区分度。结果并发症≥Ⅱ级组26例,并发症0~Ⅰ级组164例,并发症≥Ⅱ级组美国麻醉医师协会(ASA)分级≥Ⅲ级构成比、合并中/重度急性胆管炎构成比、查尔森合并症指数(Charlson comorbidity index,CCI)、术中出血量均高于并发症0~Ⅰ级组(均P<0.05),白蛋白水平低于并发症0~Ⅰ级组(P<0.05)。多因素logistic回归模型显示,以下因素是LCBDE术后发生Clavien-Dindo分级≥Ⅱ级并发症的危险因素:ASA分级≥Ⅲ级(OR=3.550,95%CI:1.271~9.915),CCI评分(OR=2.617,95%CI:1.151~5.949),合并中/重度急性胆管炎(OR=2.171,95%CI:1.296~3.635),术中出血量(OR=2.872,95%CI:1.322~6.241),均P<0.05;白蛋白(OR=0.426,95%CI:0.200~0.904)是保护因素(P<0.05);建立logistic回归方程:Logit函数=–12.874–0.854X1(白蛋白)+1.267X2(ASA分级≥Ⅲ级)+0.962X3(CCI评分)+0.775X4(合并中/重度急性胆管炎)+1.055X5(术中出血量)。ROC曲线显示,该模型预测训练集术后发生Clavien-Dindo分级≥Ⅱ级并发症的曲线下面积(AUC)为0.929,敏感度为84.62%,特异度为98.17%,预测验证集术后发生Clavien-Dindo分级≥Ⅱ级并发症的AUC为0.920,敏感度为92.31%,特异度为81.71%。HosmerLemeshow检验显示,该预测模型预测训练集、验证集病人术后发生Clavien-Dindo分级≥Ⅱ级并发症的概率与实际概率比较,差异均无统计学意义(训练集:χ^(2)=6.036,P=0.702;验证集:χ^(2)=7.254,P=0.512)。结论ASA分级≥Ⅲ级、CCI评分、合并中/重度急性胆管炎、术中出血量是LCBDE术后发生Clavien-Dindo分级≥Ⅱ级并发症的危险因素,白蛋白是保护因素,对应的预测模型经验证具有良好的预测效能。
基金supports from the National Natural Science Foundation of China (Grant Nos.52004143 and 52374095)the open fund for the Laboratory of Mining Response and Disaster Prevention and Control in Deep Coal Mines (Grant No.SKLMRDPC21KF06).
文摘A series of true triaxial unloading tests are conducted on sandstone specimens with a single structural plane to investigate their mechanical behaviors and failure characteristics under different in situ stress states.The experimental results indicate that the dip angle of structural plane(θ)and the intermediate principal stress(σ2)have an important influence on the peak strength,cracking mode,and rockburst severity.The peak strength exhibits a first increase and then decrease as a function ofσ2 for a constantθ.However,whenσ2 is constant,the maximum peak strength is obtained atθof 90°,and the minimum peak strength is obtained atθof 30°or 45°.For the case of an inclined structural plane,the crack type at the tips of structural plane transforms from a mix of wing and anti-wing cracks to wing cracks with an increase inσ2,while the crack type around the tips of structural plane is always anti-wing cracks for the vertical structural plane,accompanied by a series of tensile cracks besides.The specimens with structural plane do not undergo slabbing failure regardless ofθ,and always exhibit composite tensile-shear failure whatever theσ2 value is.With an increase inσ2 andθ,the intensity of the rockburst is consistent with the tendency of the peak strength.By analyzing the relationship between the cohesion(c),internal friction angle(φ),andθin sandstone specimens,we incorporateθinto the true triaxial unloading strength criterion,and propose a modified linear Mogi-Coulomb criterion.Moreover,the crack propagation mechanism at the tips of structural plane,and closure degree of the structural plane under true triaxial unloading conditions are also discussed and summarized.This study provides theoretical guidance for stability assessment of surrounding rocks containing geological structures in deep complex stress environments.
基金supported by the Foundation of President of Hebei University(XZJJ202303).
文摘Federated learning is a machine learning framework designed to protect privacy by keeping training data on clients’devices without sharing private data.It trains a global model through collaboration between clients and the server.However,the presence of data heterogeneity can lead to inefficient model training and even reduce the final model’s accuracy and generalization capability.Meanwhile,data scarcity can result in suboptimal cluster distributions for few-shot clients in centralized clustering tasks,and standalone personalization tasks may cause severe overfitting issues.To address these limitations,we introduce a federated learning dual optimization model based on clustering and personalization strategy(FedCPS).FedCPS adopts a decentralized approach,where clients identify their cluster membership locally without relying on a centralized clustering algorithm.Building on this,FedCPS introduces personalized training tasks locally,adding a regularization term to control deviations between local and cluster models.This improves the generalization ability of the final model while mitigating overfitting.The use of weight-sharing techniques also reduces the computational cost of central machines.Experimental results on MNIST,FMNIST,CIFAR10,and CIFAR100 datasets demonstrate that our method achieves better personalization effects compared to other personalized federated learning methods,with an average test accuracy improvement of 0.81%–2.96%.Meanwhile,we adjusted the proportion of few-shot clients to evaluate the impact on accuracy across different methods.The experiments show that FedCPS reduces accuracy by only 0.2%–3.7%,compared to 2.1%–10%for existing methods.Our method demonstrates its advantages across diverse data environments.
