期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到139篇文章
< 1 2 … 7 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Predictors of one-year adverse outcomes after laparoscopic resection for hepatocellular carcinoma:Development and validation of an early-warning model 认领 引用
1
作者 Wei Feng Qing-Wang Ye +3 位作者 Qi-Le Wang Si-Ying Chen Yao Ma Fan-Lai Meng 《World Journal of Gastroenterology》 SCIE CAS 2026年第6期41-56,共16页
BACKGROUND The global burden of primary liver cancer(PLC)continues to rise.Although minimally invasive,especially laparoscopic,resection is increasingly performed for early-stage disease,1-year adverse outcomes(recurr... BACKGROUND The global burden of primary liver cancer(PLC)continues to rise.Although minimally invasive,especially laparoscopic,resection is increasingly performed for early-stage disease,1-year adverse outcomes(recurrence,metastasis,or mortality)remain common.Widely used scores,such as the albumin-bilirubin grade,primarily assess hepatic reserve and may not fully reflect tumor biology or systemic inflammation for individualized early prognostic warning.This study aimed to develop and validate a least absolute shrinkage and selection operator(LASSO)-based model to predict 1-year adverse outcomes after minimally invasive PLC resection.AIM To identify predictors of short-term(1-year)adverse outcomes following minimally invasive PLC resection and construct an individualized postoperative prognostic model using LASSO regression.METHODS This retrospective study included patients with PLC who underwent minimally invasive resection at The Affiliated Suqian Hospital of Xuzhou Medical University between January 2019 and January 2023.Prognostic predictors were identified using LASSO regression and incorporated into a logistic regression model.Model performance and clinical utility were evaluated using receiver operating characteristic curves,calibration plots,and decision curve analysis.The dataset was randomly divided into training(n=277)and internal validation(n=144)cohorts.An external validation cohort of 138 patients with PLC(February 2023 to June 2024)was used to assess generalizability.RESULTS Receiver operating characteristic analysis indicated good performance of the logistic regression model based on six predictors,white blood cell count,tumor diameter,vascular invasion,portal vein infiltration,cirrhosis,and alphafetoprotein,with area under the curve(AUC)values of 0.756[95%confidence interval(CI):0.687-0.824]and 0.750(95%CI:0.659-0.841)in the training and internal validation cohorts,respectively.The model exhibited strong calibration(training,P=0.6951;external validation,P=0.5223)and clear net clinical benefit across risk thresholds.External validation further supported its generalizability(n=138;AUC=0.735,95%CI:0.640-0.830).Compared with albumin-bilirubin,the LASSO-based risk score showed higher though non-significant AUCs in the training(0.756 vs 0.691;DeLong P=0.206)and external(0.735 vs 0.717;P=0.803)cohorts and comparable performance in the internal validation cohort(0.750 vs 0.753;P=0.968).CONCLUSION LASSO regression was used to identify six independent predictors of adverse 1-year outcomes after minimally invasive PLC resection.The resulting risk score model demonstrates reliable discrimination,calibration,and clinical utility for individualized prognostic assessment. 展开更多
关键词 Primary liver cancer Minimally invasive resection Outcomes Predictors Least absolute shrinkage and selection operator regression Prognostic model
暂未订购 下载PDF
Clinical characteristics of and risk factors for hepatolithiasis developed after surgery for congenital biliary dilatation 认领 引用
2
作者 Fumio Asano Ryusei Matsuyama +4 位作者 Takafumi Kumamoto Masato Shinkai Daisuke Morioka Satoru Shinoda Itaru Endo 《World Journal of Gastrointestinal Surgery》 SCIE 2026年第1期174-184,共11页
BACKGROUND Pancreaticobiliary maljunction(PBM)is a congenital disease in which the pancreatic and bile ducts fuse outside the duodenal wall.Congenital biliary dilatation(CBD)involves PBM and dilatation of the extrahep... BACKGROUND Pancreaticobiliary maljunction(PBM)is a congenital disease in which the pancreatic and bile ducts fuse outside the duodenal wall.Congenital biliary dilatation(CBD)involves PBM and dilatation of the extrahepatic bile duct.The lack of Oddi sphincter action at the confluence results in the retrograde flow of pancreatic juice into the bile duct,placing patients with CBD at high risk of biliary carcinoma.The standard treatment for CBD is complete extrahepatic bile duct resection(EHBR).Hepatolithiasis(HL),a late complication following CBD surgery,has a deleterious clinical impact;further research is necessary to elu-cidate its risk factors.AIM To clarify the clinical impact of and risk factors for HL after CBD surgery.METHODS A retrospective study was conducted with 223 CBD patients who underwent EHBR across three tertiary hospitals to investigate postoperative complications.An exploratory analysis was performed to identify factors associated with HL development.Risk factors were subsequently identified using least absolute shrinkage and selection operator(LASSO)analysis.RESULTS HL was observed in 15/223(6.7%)patients.Two of those patients developed liver failure owing to biliary cirrhosis;one died, and the other received liver transplantation. Two patients requiredmajor hepatectomy. The majority of the remaining patients required repeated enteroscopic and/or percutaneouslithotomy procedures. LASSO analysis revealed older age at surgery as an independent risk factor for HL;the timedependentreceiver operating characteristic analysis at 6 years after surgery revealed a cutoff age of 31 years.CONCLUSIONHL following CBD surgery has a markedly deleterious clinical impact. Advanced age at the time of CBD surgerywas identified as an independent risk factor for HL. 展开更多
关键词 Congenital biliary dilatation Pancreaticobiliary maljunction Postoperative complications Hepatolithiasis Least absolute shrinkage and selection operator regulation
暂未订购 下载PDF
Construction and validation of a machine learning algorithm-based predictive model for difficult colonoscopy insertion 认领 引用
3
作者 Ren-Xuan Gao Xin-Lei Wang +6 位作者 Ming-Jie Tian Xiao-Ming Li Jia-Jia Zhang Jun-Jing Wang Jing Gao Chao Zhang Zhi-Ting Li 《World Journal of Gastrointestinal Endoscopy》 2025年第7期149-161,共13页
BACKGROUND Difficulty of colonoscopy insertion(DCI)significantly affects colonoscopy effectiveness and serves as a key quality indicator.Predicting and evaluating DCI risk preoperatively is crucial for optimizing intr... BACKGROUND Difficulty of colonoscopy insertion(DCI)significantly affects colonoscopy effectiveness and serves as a key quality indicator.Predicting and evaluating DCI risk preoperatively is crucial for optimizing intraoperative strategies.AIM To evaluate the predictive performance of machine learning(ML)algorithms for DCI by comparing three modeling approaches,identify factors influencing DCI,and develop a preoperative prediction model using ML algorithms to enhance colonoscopy quality and efficiency.METHODS This cross-sectional study enrolled 712 patients who underwent colonoscopy at a tertiary hospital between June 2020 and May 2021.Demographic data,past medical history,medication use,and psychological status were collected.The endoscopist assessed DCI using the visual analogue scale.After univariate screening,predictive models were developed using multivariable logistic regression,least absolute shrinkage and selection operator(LASSO)regression,and random forest(RF)algorithms.Model performance was evaluated based on discrimination,calibration,and decision curve analysis(DCA),and results were visualized using nomograms.RESULTS A total of 712 patients(53.8%male;mean age 54.5 years±12.9 years)were included.Logistic regression analysis identified constipation[odds ratio(OR)=2.254,95%confidence interval(CI):1.289-3.931],abdominal circumference(AC)(77.5–91.9 cm,OR=1.895,95%CI:1.065-3.350;AC≥92 cm,OR=1.271,95%CI:0.730-2.188),and anxiety(OR=1.071,95%CI:1.044-1.100)as predictive factors for DCI,validated by LASSO and RF methods.Model performance revealed training/validation sensitivities of 0.826/0.925,0.924/0.868,and 1.000/0.981;specificities of 0.602/0.511,0.510/0.562,and 0.977/0.526;and corresponding area under the receiver operating characteristic curves(AUCs)of 0.780(0.737-0.823)/0.726(0.654-0.799),0.754(0.710-0.798)/0.723(0.656-0.791),and 1.000(1.000-1.000)/0.754(0.688-0.820),respectively.DCA indicated optimal net benefit within probability thresholds of 0-0.9 and 0.05-0.37.The RF model demonstrated superior diagnostic accuracy,reflected by perfect training sensitivity(1.000)and highest validation AUC(0.754),outperforming other methods in clinical applicability.CONCLUSION The RF-based model exhibited superior predictive accuracy for DCI compared to multivariable logistic and LASSO regression models.This approach supports individualized preoperative optimization,enhancing colonoscopy quality through targeted risk stratification. 展开更多
关键词 Colonoscopy Difficulty of colonoscopy insertion Machine learning algorithms Predictive model Logistic regression Least absolute shrinkage and selection operator regression Random forest
暂未订购 下载PDF
基于麻雀搜索算法优化TPA-LSTM的火电厂NOx排放预测 认领 引用 被引量：5
4
作者 金秀章 张瑾 陈佳政 《控制工程》 CSCD 北大核心 2026年第6期1035-1043,共9页
针对燃煤机组状态多变导致选择性催化还原(selective catalytic reduction,SCR)入口NOx浓度大范围波动的问题,提出了一种基于麻雀搜索算法(sparrow search algorithm,SSA)优化时序模式注意力机制长短期记忆(temporal pattern attenti... 针对燃煤机组状态多变导致选择性催化还原(selective catalytic reduction,SCR)入口NOx浓度大范围波动的问题,提出了一种基于麻雀搜索算法(sparrow search algorithm,SSA)优化时序模式注意力机制长短期记忆(temporal pattern attention mechanism long short-term memory,TPA-LSTM)神经网络的预测模型。首先,通过NOx生成机理分析出与其相关的辅助变量;然后,利用套索(least absolute shrinkage and selection operator,LASSO)算法筛选出与其相关度最高的几组辅助变量,通过最大信息系数(maximal information coefficient,MIC)计算各辅助变量与NOx浓度之间的延迟时间,使用包含辅助变量和迟延时间的信息作为模型的输入;最后,通过SSA优化TPA-LSTM神经网络的超参数,建立NOx排放TPA-LSTM神经网络预测模型。仿真结果表明,加入TPA机制的LSTM神经网络预测模型的性能明显优于传统的LSTM神经网络,证明了所提模型的有效性。 展开更多
关键词 麻雀搜索算法 时序模式注意力机制 辅助变量 套索算法 最大信息系数
暂未订购 下载PDF
Predicting the magnitude of risk for non-curative endoscopic submucosal dissection in superficial esophageal cancer using explainable artificial intelligence 认领 引用
5
作者 Zi-Chen Luo Hai-Yang Guo +9 位作者 Xin-Rui Chen Cheng-Yu Zhang Yu-Tong Cui Ji Zuo Hao-Rui Li Xue-Mei Hou Hao Chen Shao-Bi Song Xian-Fei Wang Xiao Tang 《World Journal of Gastrointestinal Oncology》 SCIE 2026年第2期122-138,共17页
BACKGROUND Endoscopic submucosal dissection(ESD)serves as a critical treatment modality for superficial esophageal cancer.However,non-curative resection is significantly associated with residual tumors and unfavorable... BACKGROUND Endoscopic submucosal dissection(ESD)serves as a critical treatment modality for superficial esophageal cancer.However,non-curative resection is significantly associated with residual tumors and unfavorable prognosis.Effective preoperative predictive tools are currently lacking.AIM To develop and validate a machine learning-based prediction model for accurate preoperative assessment of the risk of non-curative ESD resection.METHODS This multicenter retrospective study included 366 superficial esophageal cancer patients from the Affiliated Hospital of North Sichuan Medical College as a training set,and 129 patients from Langzhong People’s Hospital as an independent external validation set.Predictors were selected using least absolute shrinkage and selection operator and multivariate logistic regression.Nine machine learning classifiers,including logistic regression,LightGBM,and XGBoost,were integrated to develop the models,and SHapley Additive exPlanations(SHAP)were employed to achieve risk visualization.RESULTS Key predictive factors identified included esophageal stricture,computed tomography-based esophageal wall thickening>7 mm,endoscopically estimated invasion depth>superficial layer(SM1)(endoscopic ultrasound or magnifying endoscopy with narrow-band imaging collectively referred to as EOM>SM1),multiple lesions,circumferential ratio≥3/4,and preoperative pathological type.The logistic regression model constructed with these factors demonstrated optimal performance(training set area under the curve(AUC)=0.887;internal validation AUC=0.872;external validation AUC=0.849).SHAP analysis further revealed computed tomographybased esophageal wall thickening>7 mm and EOM>SM1 as core risk-driving factors.CONCLUSION The logistic regression prediction model developed in this study effectively identifies patients at high risk of noncurative resection prior to ESD.By incorporating SHAP-based interpretability,the model provides a reliable and transparent tool to support clinical decision-making. 展开更多
关键词 Superficial esophageal cancer Non-curative resection Least absolute shrinkage and selection operator regression Machine learning Endoscopic submucosal dissection
暂未订购 下载PDF
基于SHAP可解释性机器学习的老年糖尿病患者衰弱风险预测模型构建与验证 认领 引用
6
作者 邓舜芝 康圣琴 +3 位作者 方苗苗 王雪菲 巫海娣 莫永珍 《现代临床护理》 2026年第1期1-11,共11页
目的构建与验证基于可解释性机器学习的老年糖尿病患者衰弱预测模型,以早期识别高风险患者。方法采用便利抽样法,选择2024年1月至5月本市某三级甲等综合医院住院的232例老年糖尿病患者作为研究对象。227例患者完成研究,按照7∶3的比例... 目的构建与验证基于可解释性机器学习的老年糖尿病患者衰弱预测模型,以早期识别高风险患者。方法采用便利抽样法,选择2024年1月至5月本市某三级甲等综合医院住院的232例老年糖尿病患者作为研究对象。227例患者完成研究,按照7∶3的比例随机分为训练集(158例)与测试集(69例),分别用于模型构建与验证。采用最小绝对收缩和选择算子(least absolute shrinkage and selection operator,LASSO)回归与Boruta算法筛选特征变量,并基于逻辑回归(logistic regression,LR)、支持向量机(support vector machine,SVM)和极端梯度提升树(extreme gradient boosting,XGBoost)构建机器学习模型。通过曲线下面积(area under curve,AUC)、灵敏度、特异度、F1分数等指标评估模型性能,并通过DeLong检验比较模型间的AUC差异。最优模型利用沙普利加和解释(Shapley additive explanation,SHAP)方法,对关键预测因子进行解释,并基于Streamlit开发网页计算器,实现模型可视化。结果227例老年糖尿病患者中99例合并衰弱(43.6%)。XGBoost模型综合表现最优,在训练集和测试集中,DeLong检验显示XGBoost的AUC高于LR和SVM(均P<0.001)。训练集AUC为0.920,准确性为0.842,灵敏度为0.783,特异度为0.887,阳性预测值(positive predictive value,PPV)为0.845,阴性预测值(negative predictive value,NPV)为0.840,F1分数为0.810。测试集AUC为0.806,准确性为0.681,灵敏度为0.633,特异度为0.743,PPV为0.731,NPV为0.744,F1分数为0.620。SHAP可解释分析显示,衰弱的预测因子重要性排序依次为:认知障碍、查尔斯共病指数、慢性疼痛、体育锻炼量、肌少症、营养状态、糖尿病肾病。结论基于SHAP可解释XGBoost的衰弱预测模型可有效识别老年糖尿病患者的衰弱高风险因素,能为其健康管理策略提供支持。 展开更多
关键词 糖尿病 老年人 衰弱 沙普利加和解释 最小绝对收缩和选择算子 逻辑回归 支持向量机 极端梯度提升树
暂未订购 下载PDF
基于血清微小核糖核酸与临床因素的食管癌内镜黏膜下剥离术后复发预测模型 认领 引用
7
作者 姚成云 朱芳来 伍平 《实用临床医药杂志》 CAS 2026年第5期81-87,共7页
目的探讨整合临床因素及血清微小核糖核酸-204(miR-204)、微小核糖核酸-134(miR-134)构建的预测早期食管癌患者内镜黏膜下剥离术(ESD)后复发风险的机器学习模型的预测价值。方法按照1∶1比例选取早期食管癌患者作为研究对象,包括ESD后1... 目的探讨整合临床因素及血清微小核糖核酸-204(miR-204)、微小核糖核酸-134(miR-134)构建的预测早期食管癌患者内镜黏膜下剥离术(ESD)后复发风险的机器学习模型的预测价值。方法按照1∶1比例选取早期食管癌患者作为研究对象,包括ESD后1年内复发患者与未复发患者各100例,分别纳入复发组与未复发组。比较2组患者的临床资料,采用最小绝对收缩与选择算子(LASSO)回归模型筛选变量,构建随机森林(RF)、逻辑回归(LR)、极限梯度提升(XGBoost)、支持向量机(SVM)共4种机器学习模型。绘制受试者工作特征(ROC)曲线,分析4种机器学习模型对早期食管癌ESD后复发的预测效能。另选取早期食管癌ESD后复发患者与未复发患者各50例作为外部验证集,通过校准曲线和决策曲线分析(DCA)对综合预测效能最佳的模型进行验证。结果2组患者在病变长径、病灶浸润深度、病灶环周范围、切缘阳性及血清miR-204、miR-134水平方面比较,差异有统计学意义(P<0.05)。4种机器学习模型中,RF模型预测术后复发的F1分数和曲线下面积(AUC)最高,综合预测效能最佳;RF模型中,重要特征变量排序依次为病灶环周范围、miR-204、miR-134、切缘阳性、病灶浸润深度、病变长径。在外部验证集中,RF模型的C指数为0.892,Brier评分=0.112分;校准曲线、DCA曲线显示,RF模型预测值与实际发生率接近,且其风险阈值范围为15%~100%时,具有显著的净获益。结论基于病灶环周范围、miR-204、miR-134、切缘阳性、病灶浸润深度、病变长径这6个重要特征变量构建的4种机器学习模型中,RF模型对早期食管癌ESD后复发风险的综合预测效能最佳,具有较高的区分度、准确度及良好的临床适用性。 展开更多
关键词 早期食管癌 内镜黏膜下剥离术 术后复发 微小核糖核酸-204 微小核糖核酸-134 机器学习模型 随机森林模型 最小绝对收缩与选择算子回归模型
暂未订购 下载PDF
增强型体外反搏治疗心力衰竭疗效的列线图预测模型 认领 引用
8
作者 匡征南 袁德敏 《中国现代药物应用》 2026年第15期1-6,共6页
目的构建并评价一种基于增强型体外反搏(EECP)治疗心力衰竭疗效的预测模型,以识别影响治疗效果的关键因素,辅助临床决策。方法本研究为单中心回顾性队列研究,分析100例心力衰竭患者的临床资料,依据最后一次随访时的堪萨斯城心肌病调查问... 目的构建并评价一种基于增强型体外反搏(EECP)治疗心力衰竭疗效的预测模型,以识别影响治疗效果的关键因素,辅助临床决策。方法本研究为单中心回顾性队列研究,分析100例心力衰竭患者的临床资料,依据最后一次随访时的堪萨斯城心肌病调查问卷(KCCQ)物理限制评分分为康复良好组(≥47.5分)和康复欠佳组(0.05);康复欠佳组收缩压、脑钠肽(BNP)、高血压占比高于康复良好组,EECP治疗占比、血红蛋白、左心室射血分数(LVEF)、KCCQ物理限制评分低于康复良好组,6 min步行距离短于康复良好组(P<0.05)。Lasso回归共筛选出4个关键变量,分别为收缩压、是否患有高血压、血红蛋白、是否接受EECP治疗,纳入多因素Logistic回归分析后结果显示,EECP治疗[OR=18.10,95%CI=(1.32,28.14),P=0.042<0.05]和较高血红蛋白水平[OR=1.66,95%CI=(1.28,2.89),P=0.009<0.05]是康复良好的独立促进因素,而合并高血压[OR=0.00,95%CI=(0.00,0.13),P=0.049<0.05]为康复良好的独立危险因素。所构建列线图模型在训练集中表现出优异的区分能力[AUC=0.991,95%CI=(0.978,1.000)],且经校准曲线和DCA验证具有良好的校准性和临床适用性。结论本研究建立的EECP疗效预测模型能够有效识别影响心力衰竭患者康复的关键因素,具备较高的预测准确性与临床应用价值,有助于实现个体化治疗与优化管理策略。 展开更多
关键词 心力衰竭 增强型体外反搏 疗效预测模型 最小绝对收缩和选择算子回归 多因素Logistic回归
暂未订购 下载PDF
基于超声参数联合临床数据构建产后盆底功能障碍性疾病的列线图诊断模型 认领 引用
9
作者 孙艳平 林雁 张苗苗 《海南医学》 CAS 2026年第15期2250-2257,共8页
目的联合经阴道盆底超声和临床数据构建产后盆底功能障碍性疾病(PFD)的列线图诊断模型,为临床筛查防治提供参考依据。方法前瞻性纳入2022年6月至2025年2月期间郑州市妇幼保健院接收的150例产后6~8周初产妇,所有产妇均接受经阴道盆底超... 目的联合经阴道盆底超声和临床数据构建产后盆底功能障碍性疾病(PFD)的列线图诊断模型,为临床筛查防治提供参考依据。方法前瞻性纳入2022年6月至2025年2月期间郑州市妇幼保健院接收的150例产后6~8周初产妇,所有产妇均接受经阴道盆底超声检查,根据是否发生PFD分为PFD组(n=41)和非PFD组(n=109)。收集和比较所有产妇一般资料和经阴道盆底超声参数,利用最小绝对收缩和选择算法(LASSO)回归方程筛选有差异项目,通过Logistic进行多因素分析,得到产后PFD发生的独立影响因素。构建列线图诊断模型并采用受试者工作特征(ROC)曲线和校准曲线评估其区分度和校准度。结果单因素分析结果显示,PFD组年龄、第二产程>1 h占比、阴道分娩占比、新生儿体质量、最大Valsalva动作下膀胱尿道后角(PUVA)、最大Valsalva动作下肛提肌裂孔面积(LHA)和膀胱颈移动距离(BND)均高于非PFD组,膀胱颈至耻骨联合下缘距离(BSD)低于非PFD组,差异有统计学意义(P1 h(OR=4.835,95%CI:1.256~18.617)、阴道分娩(OR=8.260,95%CI:1.665~40.969)、新生儿体质量(OR=6.876,95%CI:1.484~31.866)、Valsalva动作下PUVA(OR=1.071,95%CI:1.017~1.129)、Valsalva动作下LHA(OR=1.739,95%CI:1.307~2.314)和BND(OR=1.234,95%CI:1.067~1.427)是产后PFD发生的独立危险因素,均P1 h、阴道分娩、新生儿体质量、最大Valsalva动作下PUVA、最大Valsalva动作下LHA和BND,且基于上述危险因素的联合诊断模型的诊断价值良好,可帮助医师及早识别出PFD产妇,临床也可结合产妇实际临床特征和盆底超声参数,适时调整治疗方案。 展开更多
关键词 经阴道盆底超声 临床数据 产后盆底功能障碍性疾病 最小绝对收缩和选择算法 列线图 诊断模型
暂未订购 下载PDF
基于可解释性因子选择的多模型耦合式大坝变形预测方法 认领 引用 被引量：2
10
作者 柳聪聪 张锋 +2 位作者 胡超 张启灵 郭永成 《长江科学院院报》 CSCD 北大核心 2026年第1期144-154,共11页
目前,传统、单一模型难以全面捕捉大坝变形数据的复杂性和多样性,导致其预测性能和解释能力受限。为解决上述问题,通过对多种预测模型的组合与优化,提出了一种高效且具备可解释性的大坝变形预测方法。首先,利用最小绝对值收缩和选择算子... 目前,传统、单一模型难以全面捕捉大坝变形数据的复杂性和多样性,导致其预测性能和解释能力受限。为解决上述问题,通过对多种预测模型的组合与优化,提出了一种高效且具备可解释性的大坝变形预测方法。首先,利用最小绝对值收缩和选择算子(LASSO)在众多环境变量中高效筛选,既简化模型输入,又解释了因子选择的可靠性。然后,采用长短期记忆(LSTM)网络对大坝变形进行预测,并引入注意力机制,增强对重要信息的提取。最后,通过Bagging算法集成多个模型预测结果,进一步提高整体预测的准确度、稳定性和泛化能力。以某碾压混凝土重力坝为例,所构建的模型具有较高的预测精度,各测点上平均MAE、MSE、RMSE依次为0.052、0.005、0.067 mm。将耦合模型与多种常用模型对比分析,结果表明耦合模型能够更准确地捕捉到大坝变形的动态变化,为预测模型研究提供了一种简洁高效的方法。 展开更多
关键词 大坝变形预测 最小绝对值收缩和选择算子(LASSO) 注意力机制 长短期记忆(LSTM) Bagging算法 耦合模型
暂未订购 下载PDF
基于LASSO回归的列线图与决策树构建乳腺癌患者预后预测模型 认领 引用 被引量：1
11
作者 闫慈 秦帅刚 +2 位作者 刘亚洁 付爱玲 阿布都沙拉木·依米提 《现代肿瘤医学》 CAS 2026年第4期540-550,共11页
目的:探讨乳腺癌患者5年生存预后的影响因素,构建生存预测模型,并评估其预测准确性。方法:调取2010年1月至2020年12月在新疆医科大学附属肿瘤医院因乳腺癌初治住院的17104例女性患者的病案数据及随访资料。依据LASSO(the least absolute... 目的:探讨乳腺癌患者5年生存预后的影响因素,构建生存预测模型,并评估其预测准确性。方法:调取2010年1月至2020年12月在新疆医科大学附属肿瘤医院因乳腺癌初治住院的17104例女性患者的病案数据及随访资料。依据LASSO(the least absolute shrinkage and selection operator,LASSO)回归筛选出与乳腺癌预后强相关的变量构建乳腺癌患者5年生存预测模型,在此基础上绘制列线图和决策树,并与传统Logistic回归做比较,采用受试者工作曲线下面积(area under receiver operating characteristic curve,AUC)对模型的预测效能进行评价。结果:LASSO回归共筛选出16个乳腺癌预后影响因素,分别是年龄、民族、初潮年龄、肿瘤分期、肿瘤家族史、手术分组、组织学分级、雌激素受体状态、孕激素受体状态、Ki-67表达水平、HER-2 Fish状态、放疗、化疗、靶向治疗、内分泌治疗、新辅助治疗。决策树根节点为肿瘤分期,共7个内部节点、9个结果节点和16条决策路径。各自变量的重要性由高到低分别为肿瘤分期、年龄、肿瘤家族史、Ki-67表达水平、组织学分级、HER-2 Fish状态、手术类型、新辅助治疗。对列线图和决策树预测模型进行验证,列线图、决策树、Logistic回归的AUC值分别为0.934、0.917、0.903。结论:本研究构建的LASSO回归可用于乳腺癌患者临床数据筛选与预后强相关的变量,列线图与决策树模型预测效能良好,且列线图预测性能最优,该方法有助于医务人员对乳腺癌患者制定个体化动态综合治疗方案。 展开更多
关键词 乳腺癌 LASSO回归 列线图 决策树 预后预测
暂未订购 下载PDF
脓毒症相关性心肌损伤患者临床转归分析及预测列线图构建 认领 引用 被引量：1
12
作者 李加涌 朱轶 +1 位作者 罗春阳 陈旭锋 《南京医科大学学报（自然科学版）》 CAS 北大核心 2026年第3期418-424,443,共7页
目的:探讨脓毒症相关性心肌损伤(sepsis-associated myocardial injury,SAMI)的流行病学现状及其对预后的影响,并通过构建列线图以期早期识别SAMI高危群体。方法:采用回顾性研究,收集2023年7月—2024年12月于南京医科大学第一附属医院... 目的:探讨脓毒症相关性心肌损伤(sepsis-associated myocardial injury,SAMI)的流行病学现状及其对预后的影响,并通过构建列线图以期早期识别SAMI高危群体。方法:采用回顾性研究,收集2023年7月—2024年12月于南京医科大学第一附属医院急诊医学科住院的脓毒症患者临床资料,统计SAMI发病率,绘制28 d Kaplan-Meier生存曲线比较SAMI对脓毒症预后影响,通过最小绝对收缩和选择算子(least absolute shrinkage and selection operator,LASSO)回归以及Boruta算法分别对临床变量进行筛选,并采用多因素Logistic回归分析构建SAMI早期预测模型。结果:共纳入353例脓毒症患者,其中195例(55.2%)患者在病程中发生SAMI。SAMI组患者28 d死亡风险显著高于无SAMI患者(HR=2.342,P<0.001)。通过LASSO回归和Boruta算法行变量筛选并取交集,最终纳入年龄、冠心病史、肌酐、尿素氮、D-二聚体和降钙素原共6个变量构建预测模型并绘制列线图,预测模型具有较好的区分度,Bootstrap重复抽样1000次的受试者工作特征(receiver operating characteristic,ROC)曲线下面积为0.770(95%CI:0.767~0.773,P<0.001),校准曲线拟合良好,决策曲线分析示在阈值概率0~0.95区间内,预测模型有较好的净收益。结论:SAMI是脓毒症患者常见并发症,并导致不良预后,基于临床变量构建的列线图具有较好的临床应用前景。 展开更多
关键词 脓毒症相关性心肌损伤 LASSO回归 Boruta算法 列线图
暂未订购 下载PDF
An Interpretable Temporal Convolutional Framework for Granger Causality Analysis 认领 引用
13
作者 Aoxiang Dong Andrew Starr Yifan Zhao 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第3期665-679,共15页
Most existing parametric approaches for detecting linear or nonlinear Granger causality(GC)face challenges in estimating appropriate time delays,a critical factor for accurate GC detection.This issue becomes particula... Most existing parametric approaches for detecting linear or nonlinear Granger causality(GC)face challenges in estimating appropriate time delays,a critical factor for accurate GC detection.This issue becomes particularly pronounced in nonlinear complex systems,which are often opaque and consist of numerous components or variables.In this paper,we propose a novel temporal convolutional network(TCN)-based end-to-end GC detection approach called the interpretable temporal convolutional framework(ITCF).Unlike conventional deep learning models,which act like a“black box”and are difficult to analyse the interactions between variables,the proposed ITCF is able to detect both linear and nonlinear GC and automatically estimate time delay during the multivariant time series prediction.Specifically,GC is obtained by employing the least absolute shrinkage and selection operator(Lasso)regression during the prediction of multivariate time series using TCN.Then,time delays can be estimated by interpreting the TCN kernels.We propose a convolutional hierarchical group Lasso(cHGL),a hierarchical regularisation approach to effectively utilise temporal information within each TCN channel for enhanced GC detection.Additionally,as far as we are concerned,this paper is the first to integrate the Iterative Soft-Thresholding Algorithm into the backpropagation of TCN to optimise the proposed cHGL,which enables causal channel selection and induces sparsity within each TCN channel to remove redundant temporal information,ultimately creating an end-to-end GC detection framework.The testing results of four experiments,involving two simulations and two real data,demonstrate that the proposed ITCF,in comparison with state-ofthe-art,offers a more reliable estimation of GC relationships in complex systems featuring intricate dynamics,limited data lengths,or numerous variables. 展开更多
关键词 Granger causality(GC) interpretable deep learning iterative soft-thresholding algorithm(ISTA) least absolute shrinkage and selection operator(Lasso) temporal convolutional network(TCN)
暂未订购 下载PDF
Breast cancer stem cell activity driven by ME18D gene expression in the tumor microenvironment 认领 引用
14
作者 De-Yang Guo Zhang-Yi Liu Qian-Chuan Yi 《World Journal of Stem Cells》 SCIE 2026年第1期49-65,共17页
BACKGROUND Breast cancer is one of the most prevalent malignancies affecting women worldwide,with approximately 2.3 million new cases diagnosed annually.Breast cancer stem cells(BCSCs)play pivotal roles in tumor initi... BACKGROUND Breast cancer is one of the most prevalent malignancies affecting women worldwide,with approximately 2.3 million new cases diagnosed annually.Breast cancer stem cells(BCSCs)play pivotal roles in tumor initiation,progression,metastasis,therapeutic resistance,and disease recurrence.Cancer stem cells possess selfrenewal capacity,multipotent differentiation potential,and enhanced tumorigenic activity,but their molecular characteristics and regulatory mechanisms require further investigation.AIM To comprehensively characterize the molecular features of BCSCs through multiomics approaches,construct a prognostic prediction model based on stem cellrelated genes,reveal cell-cell communication networks within the tumor microenvironment,and provide theoretical foundation for personalized treatment strategies.METHODS Flow cytometry was employed to detect the expression of BCSC surface markers(CD34,CD45,CD29,CD90,CD105).Transcriptomic analysis was performed to identify differentially expressed genes.Least absolute shrinkage and selection operator regression analysis was utilized to screen key prognostic genes and construct a risk scoring model.Single-cell RNA sequencing and spatial transcriptomics were applied to analyze tumor heterogeneity and spatial gene expression patterns.Cell-cell communication network analysis was conducted to reveal interactions between stem cells and the microenvironment.RESULTS Flow cytometric analysis revealed the highest expression of CD105(96.30%),followed by CD90(68.43%)and CD34(62.64%),while CD29 showed lower expression(7.16%)and CD45 exhibited the lowest expression(1.19%).Transcriptomic analysis identified 3837 significantly differentially expressed genes(1478 upregulated and 2359 downregulated).Least absolute shrinkage and selection operator regression analysis selected 10 key prognostic genes,and the constructed risk scoring model effectively distinguished between high-risk and low-risk patient groups(P<0.001).Single-cell analysis revealed tumor cellular heterogeneity,and spatial transcriptomics demonstrated distinct spatial expression gradients of stem cell-related genes.MED18 gene showed significantly higher expression in malignant tissues(P<0.001)and occupied a central position in cell-cell communication networks,exhibiting significant correlations with tumor cells,macrophages,fibroblasts,and endothelial cells.CONCLUSION This study comprehensively characterized the molecular features of BCSCs through multi-omics approaches,identified reliable surface markers and key regulatory genes,and constructed a prognostic prediction model with clinical application value. 展开更多
关键词 Breast cancer stem cells Surface markers Transcriptomics Least absolute shrinkage and selection operator regression Prognostic model
暂未订购 下载PDF
云南省少数民族地区女性孕期不同阶段睡眠问题及影响因素——基于LASSO-logistic模型 认领 引用
15
作者 焦海星 王一单 +5 位作者 马嘉茹 夏修 黄睿 邓睿 黄巧云 黄源 《中华疾病控制杂志》 CAS CSCD 北大核心 2026年第3期354-360,367,共7页
目的了解云南省少数民族地区孕期女性存在的睡眠问题及影响因素,为改善女性孕期健康提供基础数据。方法2022年5月在云南省某少数民族聚居县对当月所有处于孕期的女性进行睡眠情况调查。采用最小绝对收缩与选择算子(least absolute shrin... 目的了解云南省少数民族地区孕期女性存在的睡眠问题及影响因素,为改善女性孕期健康提供基础数据。方法2022年5月在云南省某少数民族聚居县对当月所有处于孕期的女性进行睡眠情况调查。采用最小绝对收缩与选择算子(least absolute shrinkage and selection operator,LASSO)回归筛选可能影响孕期及不同阶段(孕早、中、晚期)睡眠问题的重要变量,并分别构建logistic回归分析模型分析睡眠问题的影响因素。结果共回收有效问卷712份,其中540名孕妇有睡眠问题(75.84%)。孕中期(82.49%)和孕晚期(82.73%)孕妇睡眠问题发生率均高于孕早期(65.09%)。对于整个孕期,待业/无业(OR=2.158,95%CI:1.163~4.005)、抑郁症状(OR=2.304,95%CI:1.375~3.860)、久坐(OR=3.236.95%CI:1.634~6.408)、孕中期(OR=2.738,95%CI:1.722~4.355)、孕晚期(OR=2.403,95%CI:1.513~3.817)会增加睡眠问题的发生风险(均P<0.05);计划怀孕(OR=0.649,95%CI:0.428~0.984,P=0.042)会降低睡眠问题发生风险。各孕期阶段的睡眠问题影响因素存在差异:孕早期睡眠问题影响因素为高度社会支持、久坐;孕中期为配偶无固定收入、计划怀孕;孕晚期为抑郁症状、配偶高中及以上文化程度、目前与丈夫及其父母同住、既往怀孕史。结论云南省少数民族地区孕期女性的睡眠问题发生率高,且各孕期阶段的睡眠问题影响因素存在差异。缓解抑郁症状、减少久坐、计划怀孕和提高社会支持可能会减少孕期女性睡眠问题的发生风险。 展开更多
关键词 睡眠问题 少数民族 孕期 最小绝对收缩与选择算子 Logistic回归
暂未订购 下载PDF
加工型马铃薯F1群体遗传分析与高效筛选 认领 引用
16
作者 马豆豆 林柏松 +5 位作者 张新杰 王艳红 贾国忠 薛媛媛 刘芳明 崔江慧 《植物研究》 CAS CSCD 北大核心 2026年第3期542-556,共15页
针对加工型马铃薯产量与品质协同选育难、全表型鉴定成本高的问题,本研究通过构建高效综合评价体系,建立了早代简化预测模型。以‘大西洋’ב露辛达’杂交构建的267份F1代群体为材料,连续2 a对24项表型性状进行测定与遗传解析。... 针对加工型马铃薯产量与品质协同选育难、全表型鉴定成本高的问题,本研究通过构建高效综合评价体系,建立了早代简化预测模型。以‘大西洋’ב露辛达’杂交构建的267份F1代群体为材料,连续2 a对24项表型性状进行测定与遗传解析。结果表明:F1群体各性状变异广泛(CV为14.68%~100.97%),呈连续正态分布,符合微效多基因控制的数量遗传规律。其中,淀粉含量与产量表现出显著的正向杂种优势,且具有较高的广义遗传力。通过主成分分析(PCA)提取出9个综合指标(累计方差贡献率为84.80%),结合模糊隶属函数与系统聚类分析,成功筛选出17份具有加工潜力的优良系,其中5份核心材料达到严格的加工品质标准。进一步引入最小绝对收缩与选择算子(LASSO)回归算法,从24项多维表型数据中精准筛选出内聚性、还原糖含量等5项核心指标,构建了马铃薯早代高效筛选的简化模型,从而为加工型马铃薯的精准选育提供可靠的方法学支撑。 展开更多
关键词 马铃薯 F1群体 遗传倾向 最小绝对收缩与选择算子 简化模型
暂未订购 下载PDF
基于门控脉冲神经P系统模型的概率负荷预测 认领 引用
17
作者 随泽远 王军 +2 位作者 彭宏 王德林 宋戈 《中国电力》 CSCD 北大核心 2026年第5期46-56,共11页
传统的确定性负荷预测无法提供负载的不确定性信息,概率负荷预测能够生成预测值不确定性的概率分布,为电网调度决策提供更丰富的信息。为了进一步提高概率负荷预测的精度,提出了一种包含最小绝对收缩和选择算子(least absolute shrinkag... 传统的确定性负荷预测无法提供负载的不确定性信息,概率负荷预测能够生成预测值不确定性的概率分布,为电网调度决策提供更丰富的信息。为了进一步提高概率负荷预测的精度,提出了一种包含最小绝对收缩和选择算子(least absolute shrinkage and selection operator,LASSO)及门控脉冲神经P系统(gated spiking neural P system,GSNP)的LASSO-GSNP模型。首先,运用LASSO从最低温度、最高温度、平均温度、平均湿度和降雨量等外部特征中提取关键特征;随后,提出了改进的GSNP模型实现概率负荷预测,以提升长时间序列预测的性能。使用2个不同尺度的长时间序列数据集作为算例,结果表明,所提模型在预测精度指标和预测区间质量上均优于其他几种典型模型。 展开更多
关键词 概率负荷预测 最小绝对收缩和选择算子 深度神经网络 分位数回归 门控脉冲神经P系统
暂未订购 下载PDF
Sparse reconstruction for fluorescence molecular tomography via a fast iterative algorithm 认领 引用 被引量：4
18
作者 Jingjing Yu Jingxing Cheng +1 位作者 Yuqing Hou Xiaowei He 《Journal of Innovative Optical Health Sciences》 SCIE EI 2014年第3期50-58,共9页
Fluorescence molecular tomography(FMT)is a fast-developing optical imaging modalitythat has great potential in early diagnosis of disease and drugs development.However,recon-struction algorithms have to address a high... Fluorescence molecular tomography(FMT)is a fast-developing optical imaging modalitythat has great potential in early diagnosis of disease and drugs development.However,recon-struction algorithms have to address a highly ill-posed problem to fulfll 3D reconstruction inFMT.In this contribution,we propose an efficient iterative algorithm to solve the large-scalereconstruction problem,in which the sparsity of fluorescent targets is taken as useful a prioriinformation in designing the reconstruction algorithm.In the implementation,a fast sparseapproximation scheme combined with a stage-wise learning strategy enable the algorithm to dealwith the ill-posed inverse problem at reduced computational costs.We validate the proposed fastiterative method with numerical simulation on a digital mouse model.Experimental results demonstrate that our method is robust for different finite element meshes and different Poissonnoise levels. 展开更多
关键词 Fluorescence molecular tomography sparse regularization reconstruction algorithm least absolute shrinkage and selection operator.
暂未订购 下载PDF
Development and validation of a three-long noncoding RNA signature for predicting prognosis of patients with gastric cancer 认领 引用 被引量：3
19
作者 Jun Zhang Hai-Yan Piao +3 位作者 Yue Wang Mei-Yue Lou Shuai Guo Yan Zhao 《World Journal of Gastroenterology》 SCIE CAS 2020年第44期6929-6944,共16页
BACKGROUND Gastric cancer(GC)is one of the most frequently diagnosed gastrointestinal cancers throughout the world.Novel prognostic biomarkers are required to predict the prognosis of GC.AIM To identify a multi-long n... BACKGROUND Gastric cancer(GC)is one of the most frequently diagnosed gastrointestinal cancers throughout the world.Novel prognostic biomarkers are required to predict the prognosis of GC.AIM To identify a multi-long noncoding RNA(lncRNA)prognostic model for GC.METHODS Transcriptome data and clinical data were downloaded from The Cancer Genome Atlas.COX and least absolute shrinkage and selection operator regression analyses were performed to screen for prognosis associated lncRNAs.Receiver operating characteristic curve and Kaplan-Meier survival analyses were applied to evaluate the effectiveness of the model.RESULTS The prediction model was established based on the expression of AC007991.4,AC079385.3,and AL109615.2 Based on the model,GC patients were divided into“high risk”and“low risk”groups to compare the differences in survival.The model was re-evaluated with the clinical data of our center.CONCLUSION The 3-lncRNA combination model is an independent prognostic factor for GC. 展开更多
关键词 Gastric cancer Prognosis Least absolute shrinkage and selection operator Survival analysis Long noncoding RNA
暂未订购 下载PDF
Discrimination of Acori Tatarinowii Rhizoma from two habitats based on GC-MS fingerprinting and LASSO-PLS-DA 认领 引用 被引量：4
20
作者 马莎莎 张冰洋 +3 位作者 陈练 章晓娟 任达兵 易伦朝 《Journal of Central South University》 SCIE EI CAS CSCD 2018年第5期1063-1075,共13页
This study is intended to explore the chemical differences of Acori Tatarinowii Rhizoma （ATR） samples collected from two habitats, Sichuan and Anhui provinces, China. Gas chromatography-mass spectrometry （GC-MS） w... This study is intended to explore the chemical differences of Acori Tatarinowii Rhizoma （ATR） samples collected from two habitats, Sichuan and Anhui provinces, China. Gas chromatography-mass spectrometry （GC-MS） was applied to establishing the quantitative chemical fingerprints of ATRs. A total of 104 volatile compounds were identified and quantified with the information of mass spectra and retention index （RI）. Furthermore, least absolute shrinkage and selection operator （LASSO）, a sparse regularization method, combined with subsampling was employed to improve the classification ability of partial least squares-discriminant analysis （PLS-DA）. After variable selection by LASSO, three chemical markers,β-elemene, α-selinene and α-asarone, were identified for the discrimination of ATRs from two habitats, and the total classification correct rate was increased from 82.76% to 96.55%. The proposed LASSO-PLS-DA method can serve as an efficient strategy for screening marked chemical components and geo-herbalism research of traditional Chinese medicines. 展开更多
关键词 Acori Tatarinowii Rhizoma gas chromatography-mass spectrometry least absolute shrinkage and selection operator （LASSO） partial least squares-discriminant analysis
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 7 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈