切换至 "中华医学电子期刊资源库"

中华脑科疾病与康复杂志(电子版) ›› 2025, Vol. 15 ›› Issue (06) : 342 -351. doi: 10.3877/cma.j.issn.2095-123X.2025.06.004

临床研究

CTP跨时相放射组学模型预测急性脑梗死溶栓后出血转化风险
宋丽娜1, 安鹏2,()   
  1. 1441000 湖北襄阳,湖北医药学院附属襄阳市第一人民医院神经内科
    2441000 湖北襄阳,湖北医药学院附属襄阳市第一人民医院放射科
  • 收稿日期:2024-12-22 出版日期:2025-12-15
  • 通信作者: 安鹏

Temporal radiomics model based on cranial CT perfusion imaging for predicting hemorrhagic transformation risk after thrombolysis in acute cerebral infarction

Lina Song1, Peng An2,()   

  1. 1Department of Neurology, Xiangyang No.1 People's Hospital, Hubei University of Medicine, Xiangyang 441000, China
    2Department of Radiology, Xiangyang No.1 People's Hospital affiliated to Hubei University of Medicine, Xiangyang 441000, China
  • Received:2024-12-22 Published:2025-12-15
  • Corresponding author: Peng An
引用本文:

宋丽娜, 安鹏. CTP跨时相放射组学模型预测急性脑梗死溶栓后出血转化风险[J/OL]. 中华脑科疾病与康复杂志(电子版), 2025, 15(06): 342-351.

Lina Song, Peng An. Temporal radiomics model based on cranial CT perfusion imaging for predicting hemorrhagic transformation risk after thrombolysis in acute cerebral infarction[J/OL]. Chinese Journal of Brain Diseases and Rehabilitation(Electronic Edition), 2025, 15(06): 342-351.

目的

探讨基于脑CT灌注(CTP)的Delta放射组学对预测急性脑梗死静脉溶栓后出血转化(HT-ACI)的价值。

方法

回顾性纳入湖北医药学院附属襄阳第一人民医院神经内科自2016年10月至2024年10月接受CTP检查及静脉溶栓治疗的419例急性脑梗死患者,依据溶栓后颅脑CT或MRI结果分为HT-ACI组(114例)和非HT-ACI组(305例)。按7∶3比例将患者按时间顺序划分为训练集(HT-ACI组80例和非HT-ACI组214例)与测试集(HT-ACI组34例和非HT-ACI组91例)。在训练集中,利用3D Slicer勾画梗死区感兴趣区域,提取Delta放射组学评分(Delta Radscore),同时获取CTP血流动力学参数[脑血容量(CBV)、脑血流量(CBF)、达峰时间(TTP)],结合年龄、性别、美国国立卫生研究院卒中量表(NIHSS)评分、病史等临床资料,通过多因素Logistic回归分析构建HT-ACI的预测模型,包括临床模型(基于临床资料,包括年龄、NIHSS等)、影像模型(基于影像资料,包括CBF、Delta Radscore等)、组合模型(合并临床与影像资料),并采用DeLong检验比较模型性能,决策曲线分析评估临床净获益,XGBoost算法验证预测结果。

结果

训练集结果显示,2组患者的NIHSS评分、抗凝药使用、年龄、梗死面积、表观扩散系数差值、CBF及Delta Radscore比较,差异有统计学意义(P<0.05);组合模型(AUC=0.878)预测性能优于临床模型(AUC=0.725)与影像模型(AUC=0.818),XGBoost进一步验证梗死面积、年龄、CBF及Delta Radscore与HT-ACI相关,决策曲线提示组合模型具有更高的临床净获益。测试集中验证的结果与训练集一致,并构建列线图以简化预测流程。

结论

基于CTP的Delta放射组学组合模型可早期反映缺血脑组织血流动力学状态,对预测HT-ACI有重要临床意义,有助于指导治疗决策、降低出血风险并改善预后。

Objective

To explore the value of Delta radiomics based on cerebral CT perfusion (CTP) in predicting hemorrhagic transformation after intravenous thrombolysis in acute cerebral infarction (HT-ACI).

Methods

A retrospective study was conducted on 419 patients with acute cerebral infarction who underwent CTP and received intravenous thrombolysis at the Neurology Department of Xiangyang No. 1 People's Hospital affiliated to Hubei University of Medicine from October 2016 to October 2024. Based on post-thrombolysis cranial CT or MRI findings, patients were categorized into an HT-ACI group (hemorrhagic transformation after acute cerebral infarction, n=114) and a non-HT-ACI group (n=305). Data were chronologically partitioned into a training set (HT-ACI: 80 cases, non-HT-ACI: 214 cases) and a test set (HT-ACI: 34 cases, non-HT-ACI: 91 cases) at a 7∶3 ratio. Within the training set, the infarct region of interest was delineated using 3D Slicer to extract the Delta radiomics score (Delta Radscore). Concurrently, CTP hemodynamic parameters [cerebral blood volume (CBV), cerebral blood flow (CBF), time to peak (TTP)] and clinical data [including age, sex, National Institutes of Health stroke scale (NIHSS) score, and medical history] were collected. Multivariate Logistic regression analysis was employed to develop predictive models of HT-ACI: a clinical model (based on clinical factors: age, NIHSS, etc.), an imaging model (based on imaging features: CBF, Delta Radscore, etc.), and a combined model (integrating both clinical and imaging data). Model performance was compared using DeLong's test for the area under the curve (AUC), clinical net benefit was assessed via decision curve analysis (DCA), and prediction outcomes were validated using the XGBoost algorithm.

Results

In the training set, there were statistically significant differences in NIHSS score, anticoagulant use, age, infarct area, apparent diffusion coefficient difference, CBF, and Delta Radscore between the two groups (P<0.05). The combined model (incorporating clinical, radiological, and Delta radiomic features) demonstrated superior predictive performance (AUC=0.878) compared to the clinical model (AUC=0.725) and the imaging model (AUC=0.818). XGBoost further validated that infarct area, age, CBF, and Delta Radscore were associated with HT-ACI. The decision curve analysis indicated that the combined model had a higher clinical net benefit. The results verified in the test set were consistent with those in the training set, and a nomogram was constructed to simplify the prediction process.

Conclusions

The combined model based on CTP-derived Delta radiomics can early reflect the hemodynamic status of ischemic brain tissue and holds significant clinical value for predicting HT-ACI, aiding in guiding treatment decisions, reducing the risk of hemorrhage, and improving patient prognosis.

图1 脑梗死区影像组学特征及CTP/MR参数提取计算过程示意图A:脑梗死区域ROI勾画、影像组学特征提取;B:CTP/MR参数计算;ROI:感兴趣区域;CBV:脑血容量;TTP:达峰时间;CBF:脑血流量;MTT:平均通过时间;ADC:表观扩散系数
Fig.1 Flowchart of radiomic feature and CTP/MR parameter extraction and computation in the ischemic infarct region
表1 训练集中影响HT-ACI发生的独立危险因素分析
Tab.1 Analysis of independent risk factors affecting the occurrence of HT-ACI in the training set
因素 训练集 单因素分析 多因素分析
HT-ACI组(n=80) 非HT-ACI组(n=214) t/Z/χ2 P P OR(95%CI P OR(95%CI
年龄(岁,mean±SD 61.30±7.56 59.00±8.65 2.041 0.043 0.044 1.03(1.01~1.07) 0.003 1.06(1.02~1.11)
性别[例(%)]     0.547 0.459 0.359 1.27(0.76~2.10)    
41(51.25) 120(56.08)            
39(48.75) 94(43.92)            
冠心病史[例(%)] 15(18.75) 36(16.82) 0.151 0.697 0.698 1.14(0.58~2.22)    
房颤史[例(%)] 24(30.00) 54(25.23) 0.678 0.410 0.411 1.27(0.71~2.24)    
既往卒中[例(%)] 24(30.00) 48(22.43) 1.805 0.179 0.131 1.35(0.91~1.98)    
高血压史[年,MQ1,Q3)] 9(0,15) 9(0,14) 0.619 0.536 0.535 1.01(0.97~1.05)    
糖尿病史[年,MQ1,Q3)] 0(0,10) 0(0,8) 1.510 0.133 0.134 1.04(0.98~1.09)    
吸烟史[年,MQ1,Q3)] 12(0,17) 10(0,15) 0.891 0.374 0.372 1.02(0.98~1.05)    
饮酒史[年,MQ1,Q3)] 13.00(0,20.25) 9.00(0,19.00) 1.430 0.154 0.154 1.02(0.99~1.04)    
BMI(kg/m2,mean±SD 23.51±2.24 23.02±2.54 1.530 0.119 0.130 1.09(0.97~1.20)    
梗死位置[例(%)]     0.959 0.338 0.337 1.15(0.86~1.54)    
基底节区 33(41.25) 104(48.60)            
侧脑室旁 19(23.75) 43(20.09)            
其他 28(35.00) 67(31.31)            
实验室检查指标[MQ1,Q3)]                
PT(s) 12.15(11.07,13.03) 11.70(10.50,12.50) 1.560 0.120 0.121 1.15(0.96~1.38)    
白细胞计数(×109/L) 8.11(6.71,9.82) 8.10(6.81,9.30) 1.290 0.198 0.198 1.09(0.96~1.24)    
D-二聚体(mg/L) 4.00(2.97,4.72) 4.05(3.21,4.70) 0.505 0.614 0.613 0.94(0.77~1.17)    
PLR 15.72(12.51,20.17) 15.20(11.90,19.08) 1.647 0.101 0.113 1.04(0.99~1.09)    
NLR 13.41(10.51,16.03) 11.90(9.43,14.20) 1.571 0.117 0.120 1.05(0.98~1.10)    
梗死面积(cm2,mean±SD 57.70±6.06 52.04±9.89 4.793 <0.001 <0.001 1.09(1.05~1.13) <0.001 1.09(1.04~1.15)
NIHSS评分(分,mean±SD 11.23±2.18 10.33±1.71 3.683 <0.001 <0.001 1.28(1.12~1.48) 0.062 1.18(0.99~1.39)
使用抗凝药[例(%)] 40(50.00) 64(29.91) 10.284 0.001 0.008 1.68(1.15~2.47) 0.071 1.66(0.98~2.78)
CBF[mL/(100 g·min),mean±SD] 2.47±0.78 2.30±0.59 2.011 0.046 0.047 1.49(1.01~2.23) 0.015 1.92(1.14~3.24)
ADC差值(×10-3 mm2/s,mean±SD 437.93±98.25 410.74±101.07 2.068 0.039 0.041 1.01(1.00~1.02) 0.081 1.01(1.00~1.01)
CBV(mL/100 g,mean±SD 0.40±0.03 0.39±0.04 0.792 0.429 0.428 1.32(0.66~2.61)    
TTP(s,mean±SD 1.22±0.16 1.19±0.15 1.241 0.216 0.216 2.84(0.54~14.92)    
Delta Radscore[MQ1,Q3)] 0.37(0.28,0.47) 0.21(0.14,0.30) 9.042 <0.001 <0.001 2.34(1.85~2.96) <0.001 2.66(2.02~3.51)
Radscore 1(mean±SD 2.32±0.54 2.31±0.63 0.203 0.840 0.839 1.05(0.686~1.590)    
表2 测试集中影响HT-ACI发生的独立危险因素分析
Tab.2 Analysis of independent risk factors affecting the occurrence of HT-ACI in the test set
因素 测试集 单因素分析 多因素分析
HT-ACI组(n=34) 非HT-ACI组(n=91) t/Z/χ2 P P OR(95%CI P OR(95%CI
年龄(岁,mean±SD 55.16±7.43 52.18±7.18 2.051 0.042 0.047 1.05(1.01~1.12) <0.001 1.12(1.04~1.21)
性别[例(%)]     0.572 0.449 0.450 1.36(0.61~3.00)    
18(52.94) 55(60.44)            
16(47.06) 36(39.56)            
冠心病史[例(%)] 2(5.88) 13(14.28) 1.655 0.198 0.213 0.37(0.08~1.76)    
房颤史[例(%)] 6(17.65) 21(23.08) 0.430 0.511 0.513 0.71(0.26~1.96)    
既往卒中[例(%)] 8(23.53) 18(19.78) 0.211 0.645 0.399 1.31(0.69~2.48)    
高血压史[年,MQ1,Q3)] 8(0,12) 8(0,13) 0.426 0.673 0.670 0.98(0.93~1.04)    
糖尿病史[年,MQ1,Q3)] 0(0,5) 0(0,0) 0.184 0.854 0.853 1.01(0.92~1.11)    
吸烟史[年,MQ1,Q3)] 9.5(0,13.0) 8.0(0,13.0) 0.790 0.431 0.428 1.03(0.96~1.09)    
饮酒史[年,MQ1,Q3)] 5.00(2.25,14.75) 3.00(0,13.00) 1.470 0.145 0.146 1.04(0.98~1.11)    
BMI(kg/m2,mean±SD 21.01±2.04 20.38±2.25 1.431 0.156 0.157 1.14(0.95~1.36)    
梗死位置[例(%)]     0.987 0.326 0.323 1.25(0.80~1.96)    
基底节区 17(50.00) 51(56.04)            
侧脑室旁 5(14.70) 18(19.78)            
其他 12(35.29) 22(24.17)            
实验室检查指标[MQ1,Q3)]                
PT(s) 10.42(9.52,11.05) 9.91(8.82,10.91) 1.530 0.130 0.132 1.27(0.93~1.78)    
白细胞计数(×109/L) 7.45(6.90,9.03) 7.33(6.31,8.65) 1.020 0.312 0.310 1.12(0.90~1.38)    
D-二聚体(mg/L) 3.69(2.98,3.88) 3.72(2.93,4.35) 1.462 0.146 0.148 0.73(0.48~1.12)    
PLR 13.65(10.61,17.83) 13.70(10.93,17.53) 1.041 0.300 0.299 1.05(0.95~1.14)    
NLR 10.65(8.42,14.12) 10.31(8.15,12.35) 1.301 0.196 0.198 1.08(0.96~1.21)    
梗死面积(cm2,mean±SD 49.92±10.27 44.89±9.67 4.793 0.012 0.015 1.05(1.01~1.11) 0.120 1.04(0.98~1.09)
NIHSS评分(分,mean±SD 9.63±1.51 8.98±1.55 2.090 0.038 0.042 1.30(1.01~1.68) 0.355 1.18(0.83~1.66)
使用抗凝药[例(%)] 16(47.06) 25(27.47) 4.307 0.037 0.037 1.83(1.04~3.23) 0.072 2.16(1.02~4.56)
CBF[mL/(100 g·min),mean±SD] 2.44±0.71 1.90±0.45 5.040 <0.001 <0.001 5.70(2.49~13.02) <0.001 7.73(2.45~24.43)
ADC差值(×10-3 mm2/s,mean±SD 365.91±78.03 335.92±67.50 2.121 0.036 0.040 1.01(1.00~1.02) 0.362 1.00(0.99~1.01)
CBV(mL/100 g,mean±SD 0.36±0.04 0.35±0.03 1.480 0.141 0.142 2.53(0.73~8.81)    
TTP(s,mean±SD 1.06±0.13 1.06±0.14 0.140 0.889 0.888 1.23(0.07~21.24)    
Delta Radscore[MQ1,Q3)] 0.39(0.28,0.44) 0.23(0.16,0.33) 4.312 <0.001 <0.001 13.33(3.49~20.91) <0.001 17.10(3.39~86.14)
Radscore 1(mean±SD 2.11±0.53 2.05±0.49 0.143 0.152 0.154 1.95(1.23~2.95)    
图2 训练集与测试集中3种预测模型的Delong检验非参数ROC曲线A:训练集;B:测试集;ROC:受试者工作特征
Fig.2 Delong test-based nonparametric ROC curves for three predictive models across training and test sets
图3 HT-ACI预测模型在训练集和验证集中的临床决策曲线分析A:训练集;B:测试集;HT-ACI:急性脑梗死静脉溶栓后出血转化
Fig.3 Decision curve analysis of HT-ACI prediction models in training and test sets
图4 HT-ACI-XGBoost预测模型输出的SHAP值分析结果HT-ACI:急性脑梗死静脉溶栓后出血转化;PLR:血小板与淋巴细胞比值;CBF:脑血流量;ADC:表观扩散系数;NLR:中性粒细胞与淋巴细胞计数比值;PT:凝血酶原时间;BMI:体质量指数;NIHSS:美国国立卫生研究院卒中量表;CBV:脑血容量;TTP:达峰时间
Fig.4 SHAP analysis results of the HT-ACI-XGBoost prediction model output
图5 基于组合模型风险因素构建的HT-ACI预测列线图工具A:列线图;B:校准曲线;HT-ACI:急性脑梗死静脉溶栓后出血转化;CBF:脑血流量
Fig.5 HT-ACI prediction nomogram tool based on combined model risk factors
[1]
Liu J, Tao W, Wang Z, et al. Radiomics-based prediction of hemorrhage expansion among patients with thrombolysis/thrombectomy related-hemorrhagic transformation using machine learning[J]. Ther Adv Neurol Disord, 2021, 14: 17562864211060029. DOI: 10.1177/17562864211060029.
[2]
Wang R, Zeng J, Wang F, et al. Risk factors of hemorrhagic transformation after intravenous thrombolysis with rt-PA in acute cerebral infarction[J]. QJM, 2019, 112(5): 323-326. DOI: 10.1093/qjmed/hcy292.
[3]
张子豪,景瑞,赵浩.血清NLRP3炎症小体及其下游炎症因子水平与大动脉粥样硬化型脑梗死患者溶栓后出血转化及预后的关系[J].中华脑科疾病与康复杂志(电子版), 2024, 14(6): 365-372. DOI: 10.3877/cma.j.issn.2095-123X.2024.06.008.
[4]
Liu X, Zhang J, Tian C, et al. The relationship of leukoaraiosis, haemorrhagic transformation and prognosis at 3 months after intravenous thrombolysis in elderly patients aged ≥ 60 years with acute cerebral infarction[J]. Neurol Sci, 2020, 41(11): 3195-3200. DOI: 10.1007/s10072-020-04398-2.
[5]
Ren H, Song H, Wang J, et al. A clinical-radiomics model based on noncontrast computed tomography to predict hemorrhagic transformation after stroke by machine learning: a multicenter study[J]. Insights Imaging, 2023, 14(1): 52. DOI: 10.1186/s13244-023-01399-5.
[6]
陈显金,吴芹芹,何长春,等.利用多模态医学数据和机器学习构建脑出血预后预测模型的研究[J].中华脑科疾病与康复杂志(电子版), 2023, 13(4): 193-198. DOI: 10.3877/cma.j.issn.2095-123X.2023.04.001.
[7]
Heo J, Sim Y, Kim BM, et al. Radiomics using non-contrast ct to predict hemorrhagic transformation risk in stroke patients undergoing revascularization[J]. Eur Radiol, 2024, 34(9): 6005-6015. DOI: 10.1007/s00330-024-10618-6.
[8]
Tomaszewska-Lampart I, Wiącek M, Bartosik-Psujek H. Risk factors for infarct growth and haemorrhagic or oedematous complications after endovascular treatment-a literature review[J]. Neurol Neurochir Pol, 2022, 56(5): 389-398. DOI: 10.5603/PJNNS.a2022.0056.
[9]
Sun T, Yu HY, Zhan CH, et al. Non-contrast CT radiomics-clinical machine learning model for futile recanalization after endovascular treatment in anterior circulation acute ischemic stroke[J]. BMC Med Imaging, 2024, 24(1): 178. DOI: 10.1186/s12880-024-01365-7.
[10]
Zhang Y, Xie G, Zhang L, et al. Constructing machine learning models based on non-contrast CT radiomics to predict hemorrhagic transformation after stoke: a two-center study[J]. Front Neurol, 2024, 15: 1413795. DOI: 10.3389/fneur.2024.1413795.
[11]
Ma Y, Xu DY, Liu Q, et al. Nomogram prediction model for the risk of intracranial hemorrhagic transformation after intravenous thrombolysis in patients with acute ischemic stroke[J]. Front Neurol, 2024, 15: 1361035. DOI: 10.3389/fneur.2024.1361035.
[12]
Klingbeil KD, Koch S, Dave KR. Potential link between post-acute ischemic stroke exposure to hypoglycemia and hemorrhagic transformation[J]. Int J Stroke, 2020, 15(5): 477-483. DOI: 10.1177/1747493017743797.
[13]
Hao Y, Zhou H, Pan C, et al. Prediction factors and clinical significance of different types of hemorrhagic transformation after intravenous thrombolysis[J]. Eur J Med Res, 2023, 28(1): 509. DOI: 10.1186/s40001-023-01503-x.
[14]
苗楠,宗子钰.脑出血后继发性脑损伤与线粒体相关机制的研究进展[J].中华神经创伤外科电子杂志, 2024, 10(2): 107-111. DOI: 10.3877/cma.j.issn.2095-9141.2024.02.008.
[15]
You S, Wang Y, Wang X, et al. Twenty-four-hour post-thrombolysis NIHSS score as the strongest prognostic predictor after acute ischemic stroke: ENCHANTED study[J]. J Am Heart Assoc, 2024, 13(18): e036109. DOI: 10.1161/jaha.124.036109.
[16]
李刚,潘晓帆,田雪,等. CT灌注成像参数及血栓弹力图对急性前循环脑梗死早期神经功能恶化的预测价值分析[J].中华神经创伤外科电子杂志, 2024, 10(4): 226-232. DOI: 10.3877/cma.j.issn.2095-9141.2024.04.006.
[17]
Xu Q, Zhu Y, Zhang X, et al. Clinical features and flair radiomics nomogram for predicting functional outcomes after thrombolysis in ischaemic stroke[J]. Front Neurosci, 2023, 17: 1063391. DOI: 10.3389/fnins.2023.1063391.
[18]
Gu Y, Xu C, Zhang Z, et al. Association between infarct location and haemorrhagic transformation of acute ischaemic stroke after intravenous thrombolysis[J]. Clin Radiol, 2024, 79(3): e401-e407. DOI: 10.1016/j.crad.2023.11.024.
[19]
Wen X, Xiao Y, Hu X, et al. Prediction of hemorrhagic transformation via pre-treatment CT radiomics in acute ischemic stroke patients receiving endovascular therapy[J]. Br J Radiol, 2023, 96(1147): 20220439. DOI: 10.1259/bjr.20220439.
[20]
Huang YH, Chen ZJ, Chen YF, et al. The value of ct-based radiomics in predicting hemorrhagic transformation in acute ischemic stroke patients without recanalization therapy[J]. Front Neurol, 2024, 15: 1255621. DOI: 10.3389/fneur.2024.1255621.
[21]
安鹏.基于临床影像资料对子痫的预测研究[D].南京:南京中医药大学, 2024.
[22]
Shi L, Rong Y, Daly M, et al. Cone-beam computed tomography-based delta-radiomics for early response assessment in radiotherapy for locally advanced lung cancer[J]. Phys Med Biol, 2020, 65(1): 015009. DOI: 10.1088/1361-6560/ab3247.
[23]
Meng Y, Wang H, Wu C, et al. Prediction model of hemorrhage transformation in patient with acute ischemic stroke based on multiparametric MRI radiomics and machine learning[J]. Brain Sci, 2022, 12(7): 858. DOI: 10.3390/brainsci12070858.
[24]
曹勇勇,付饶,吕宏尧,等.基于人工智能的影像组学与数字病理学研究在脑胶质瘤诊断中的应用进展[J].中华脑科疾病与康复杂志(电子版), 2020, 10(4): 230-233. DOI: 10.3877/cma.j.issn.2095-123X.2020.04.007.
[25]
Zhai D, Wu Y, Cui M, et al. Combinations of clinical factors, CT signs, and radiomics for differentiating high-density areas after mechanical thrombectomy in patients with acute ischemic stroke[J]. AJNR Am J Neuroradiol, 2025, 46(1): 66-74. DOI: 10.3174/ajnr.A8434.
[26]
Jiang YL, Zhao QS, Li A, et al. Advanced machine learning models for predicting post-thrombolysis hemorrhagic transformation in acute ischemic stroke patients: a systematic review and meta-analysis[J]. Clin Appl Thromb Hemost, 2024, 30: 10760296241279800. DOI: 10.1177/10760296241279800.
[1] 李东晖. 重症烧伤患者多重耐药菌感染风险的机器学习预测模型构建及验证[J/OL]. 中华实验和临床感染病杂志(电子版), 2025, 19(06): 368-377.
[2] 张亚琼, 张雨霖, 丁科, 张晓霞, 胡文佳, 陈铁龙, 宋世会, 熊勇. 人类免疫缺陷病毒感染/获得性免疫缺陷综合征患者接受抗反转录病毒治疗四年后发生免疫重建不全的风险预测模型[J/OL]. 中华实验和临床感染病杂志(电子版), 2025, 19(06): 335-344.
[3] 徐世伟, 廖杜荣, 张镐, 叶辉, 陈志平, 雒洪志. 基于一种新炎症-营养指标构建结直肠癌术前淋巴结转移预测模型[J/OL]. 中华普通外科学文献(电子版), 2025, 19(06): 383-389.
[4] 罗仲燃, 曾智豪, 黄梦娟, 何晓艺. 乳腺癌术后腋窝淋巴结负荷的多因素分析及预测模型的建立及验证[J/OL]. 中华普外科手术学杂志(电子版), 2026, 20(01): 46-50.
[5] 谷瑞辰, 林福杨, 刘永达. 术前尿培养阴性患者PCNL术后尿路感染的预测模型构建[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2025, 19(06): 772-777.
[6] 黄少坚, 梁汉标, 李清平, 唐善华, 李青妍, 李芷西, 黄灿, 王小振, 陈灿辉, 王恺, 李川江. 基于影像组学和临床特征构建肝癌新辅助/转化治疗后病理学完全缓解预测模型[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(06): 860-867.
[7] 林水荣, 宋子敏, 于玺, 李绍强, 华赟鹏, 沈顺利. 术前抗病毒治疗对HBV相关肝癌肝切除术后肝衰竭影响[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(05): 700-706.
[8] 刘燕, 马亦旻. 消化道早癌患者内镜黏膜下剥离术后局部复发预测模型构建与验证[J/OL]. 中华消化病与影像杂志(电子版), 2025, 15(06): 576-582.
[9] 王超, 张晓会, 李晓帆, 赵海丹. 维持性血液透析患者感染与心脑血管死亡风险的比较及联合预测模型构建[J/OL]. 中华临床医师杂志(电子版), 2025, 19(09): 675-681.
[10] 郭岩, 赵灵芝, 石光英. 代谢相关脂肪性肝病患者发生冠心病的风险预测模型[J/OL]. 中华临床医师杂志(电子版), 2025, 19(09): 682-688.
[11] 皇立媛, 浦洁, 王苏贵, 陈婷婷, 朱德慧, 胡雪. 中青年脑卒中患者应激障碍风险预测模型的构建与验证[J/OL]. 中华临床医师杂志(电子版), 2025, 19(07): 504-512.
[12] 王春伟, 杜青. 急性脑梗死患者THRIVE评分、NLR值、血清ACA、GFAP水平与静脉溶栓预后的相关性[J/OL]. 中华卫生应急电子杂志, 2025, 11(06): 325-328.
[13] 孙程贺, 田润杞, 王储, 李跃龙. 小窝蛋白-1对前循环大血管闭塞患者桥接治疗后颅内出血转化的预测价值[J/OL]. 中华脑血管病杂志(电子版), 2025, 19(06): 483-489.
[14] 张旭, 唐娟, 申婧, 杨琼, 高沛沛, 田苗苗, 马志翔, 姚恩生. 依达拉奉右莰醇联合阿替普酶动脉溶栓治疗急性脑梗死的临床疗效[J/OL]. 中华脑血管病杂志(电子版), 2025, 19(06): 490-495.
[15] 张克玲, 于丹. 急性缺血性卒中再灌注治疗的研究进展[J/OL]. 中华脑血管病杂志(电子版), 2025, 19(06): 532-537.
阅读次数
全文


摘要


AI


AI小编
你好!我是《中华医学电子期刊资源库》AI小编,有什么可以帮您的吗?