[1]程弘禹,吴迪,刘志伟,等.基于LASSO-Logistic回归的急性缺血性卒中溶栓抵抗风险模型建立及效能评估[J].陕西医学杂志,2026,(9):1239-1243.[doi:DOI:10.3969/j.issn.1000-7377.2026.09.014]
　CHENG Hongyu,WU Di,LIU Zhiwei,et al.Development and performance evaluation of a risk model for thrombolytic resistance in acute ischemic stroke based on LASSO-Logistic regression[J].,2026,(9):1239-1243.[doi:DOI:10.3969/j.issn.1000-7377.2026.09.014]
点击复制

基于LASSO-Logistic回归的急性缺血性卒中溶栓抵抗风险模型建立及效能评估

《陕西医学杂志》[ISSN:1000-7377/CN:61-1281/TN]

卷:
期数:
2026年9期
页码:
1239-1243
栏目:
临床研究
出版日期:
2026-09-05

文章信息/Info

Title:
Development and performance evaluation of a risk model for thrombolytic resistance in acute ischemic stroke based on LASSO-Logistic regression
作者:
程弘禹; 吴迪; 刘志伟; 李丹
（江苏省人民医院宿迁医院神经内科,江苏 宿迁 223800）
Author(s):
CHENG Hongyu; WU Di; LIU Zhiwei; LI Dan
[Department of Neurology,Jiangsu Province （Suqian） Hospital,Suqian 223800,China]
关键词:
急性缺血性脑卒中; 静脉溶栓; 溶栓抵抗; LASSO回归; Logistic模型; 风险评分
Keywords:
Acute ischemic stroke; Intravenous thrombolysis; Thrombolytic resistance; LASSO regression; Logistic model; Risk score
分类号:
R 743
DOI:
DOI:10.3969/j.issn.1000-7377.2026.09.014
文献标志码:
A
摘要:
目的：借助LASSO惩罚回归与Logistic回归相耦合的策略，构建急性缺血性脑卒中（AIS）患者接受静脉溶栓后出现溶栓抵抗的预测模型，并系统评价其鉴别能力与临床适配性。方法：回顾性收集行阿替普酶静脉溶栓治疗的130例AIS患者的临床资料，根据溶栓后24 h神经功能转归区分为抵抗组（n=40）与非抵抗组（n=90）。经单因素初筛后，采用LASSO回归压缩候选变量，再行多因素Logistic回归确立独立影响因素，依托Bootstrap法（1000次重抽样）实施内部校验，通过受试者工作特征曲线下面积（AUC）及Hosmer-Lemeshow（H-L）检验分别评价区分度和校准度，并据此构建简易赋分体系。结果：LASSO降维后保留基线NIHSS评分、心房颤动病史、入院血糖及中性粒细胞/淋巴细胞比值（NLR）4项预测因子；多因素Logistic回归确认上述指标均为溶栓抵抗的独立危险因素（均P <0.05）。预测模型原始AUC为0.846（95%CI:0.772~0.920），经Bootstrap校正后为0.838；H-L检验χ2=6.82，P=0.557。所建评分系统将受试者划为低危（0~3分）、中危（4~6分）和高危（≥7分）三层，高危组抵抗发生率达76.67%。结论：该联合策略所建模型展现良好的区分能力与概率吻合度，转化为风险评分后可为临床一线快速甄别溶栓抵抗高危个体提供便捷决策辅助工具。
Abstract:
Objective:To develop a predictive model for thrombolytic resistance following intravenous thrombolysis in patients with acute ischemic stroke (AIS) using a combined LASSO-penalized regression and Logistic regression strategy,and to systematically evaluate its discriminative ability and clinical applicability.Methods:Clinical data of 130 AIS patients who received intravenous alteplase thrombolysis at our hospital were retrospectively collected.Based on neurological outcomes at 24 hours postthrombolysis,patients were divided into a resistance group (n=40) and a nonresistance group (n=90).After univariate screening,LASSO regression was employed to compress candidate variables,followed by multivariate Logistic regression to identify independent influencing factors.Internal validation was performed using the Bootstrap method (1000 resampling iterations).Discriminative ability and calibration were assessed by the area under the receiver operating characteristic curve (AUC) and the Hosmer Lemeshow (HL) test,respectively,and a simplified scoring system was constructed accordingly.Results:After LASSO dimensionality reduction,four predictive factors were retained:baseline NIHSS score,history of atrial fibrillation,admission blood glucose,and neutrophil-to-lymphocyte ratio (NLR).Multivariate Logistic regression confirmed that all four indicators were independent risk factors for thrombolytic resistance (all P<0.05).The original AUC of the prediction model was 0.846 (95%CI:0.772～0.920),and after Bootstrap correction,it was 0.838.The H-L test yielded χ2=6.82,P=0.557.The established scoring system stratified patients into low-risk (0~3 points),intermediate-risk (4~6 points),and high-risk (≥7 points) groups,with the high-risk group showing a resistance rate of 76.67%.Conclusion:The model developed using this combined strategy demonstrates good discriminative ability and probability calibration.After conversion into a risk score,it can serve as a convenient decision-support tool for rapid bedside identification of individuals at high risk for thrombolytic resistance.

参考文献/References:

[1]GBD 2019 STROKE COLLABORATORS.Global,regional,and national burden of stroke and its risk factors,1990-2019:A systematic analysis for the Global Burden of Disease Study 2019[J].Lancet Neurol,2021,20(10):795-820.
[2]BERGE E,WHITELEY W,AUDEBERT H,et al.European Stroke Organisation (ESO) guidelines on intravenous thrombolysis for acute ischaemic stroke[J].Eur Stroke J,2021,6(1):Ⅰ-LXⅡ.
[3]SENERS P,TURC G,OPPENHEIM C,et al.Incidence,causes and predictors of early neurological deterioration after intravenous thrombolysis:A systematic review and meta-analysis[J].Neurology,2021,96(7):e935-e945.
[4]WANG Y,WANG Y,DU L,et al.A nomogram to predict early neurological deterioration after intravenous thrombolysis in acute ischemic stroke[J].J Clin Neurosci,2022,100:71-77.
[5]吴健隆,王罗俊,王萱,等.急性缺血性卒中血管内治疗术后癫痫发生率以及危险因素的研究[J].空军军医大学学报,2024,45(12):1435-1440.
[6]HE Z,LIU C,LI X,et al.Using LASSO regression to select predictors and build a model for stroke-associated pneumonia[J].J Stroke Cerebrovasc Dis,2022,31(8):106545.
[7]LI X,ZHANG T,CHEN Y,et al.Incidence and risk factors of thrombolysis resistance after intravenous rt-PA in Chinese population[J].J Thromb Thrombolysis,2022,53(2):346-353.
[8]KIM Y D,CHOI J K,LEE K Y,et al.Impact of baseline NIHSS on early neurological deterioration after intravenous thrombolysis[J].J Clin Neurol,2022,18(5):521-529.
[9]LIU J,CHEN Q,WANG D,et al.Higher baseline NIHSS score predicts poor response to intravenous thrombolysis in acute ischemic stroke[J].Neurol Res,2021,43(9):748-755.
[10]ZHAO W,ZHANG J,LI S,et al.Atrial fibrillation and resistance to thrombolysis in acute ischemic stroke[J].Cerebrovasc Dis,2021,50(4):463-470.
[11]YAO M,NI J,ZHOU L,et al.Elevated fasting blood glucose is predictive of poor outcome in non-diabetic stroke patients:A sub-group analysis from ACROSS[J].Sci Rep,2022,12:12834.
[12]GONZALEZ-MORENO M,RUIZ-GIMENEZ N,SANCHEZ-CIRERA L,et al.Admission hyperglycemia and resistance to intravenous thrombolysis[J].Eur J Neurol,2023,30(6):1672-1680.
[13]SONG S Y,ZHAO X X,RAJAH G,et al.The clinical value of neutrophil-to-lymphocyte ratio in acute ischemic stroke patients treated with intravenous thrombolysis[J].J Inflamm Res,2021,14:3423-3433.
[14]YU S,ARIMA H,BERTMAR C,et al.Neutrophil to lymphocyte ratio and early clinical outcomes in patients with acute ischemic stroke[J].J Neurol Sci,2022,441:120373.
[15]WANG L,SONG Q,WANG Y,et al.Neutrophil-to-lymphocyte ratio predicts thrombolysis resistance in acute ischemic stroke patients[J].Front Aging Neurosci,2023,15:1121184.
[16]XIONG Y,CHEN L,LIU Y,et al.Comparison of LASSO and stepwise regression for variable selection in developing a prognostic model for acute ischemic stroke[J].BMC Med Res Methodol,2023,23(1):132.
[17]WANG Y,ZHOU J,ZHANG Q,et al.A prediction model for early neurological deterioration after thrombolysis:A nomogram based on clinical and laboratory variables[J].Front Aging Neurosci,2022,14:910131.
[18]LIU X,ZHAO X,YANG M,et al.Comparison of different machine learning models for predicting early neurological deterioration in stroke patients after thrombolysis[J].Comput Math Methods Med,2022,2022:9856412.
[19]AMARENCO P,KIM J S,LABREUCHE J,et al.A simple risk score for predicting early recurrent ischemic stroke in patients with atrial fibrillation[J].JAMA Neurol,2021,78(7):836-842.
[20]WYNANTS L,VAN CALSTER B,COLLINS G S,et al.Prediction models for diagnosis and prognosis of COVID-19 infection:Systematic review and critical appraisal[J].BMJ,2020,369:m1328.
[21]RILEY R D,ENSOR J,SNELL K I E,et al.Calculating the sample size required for developing a clinical prediction model[J].BMJ,2020,368:m441.
[22]LEE K J,THOMPSON S G,HARBORD R M.The promise and pitfalls of individual participant data meta-analysis for prediction model development[J].J Clin Epidemiol,2022,142:259-268.
[23]YANG W,LEE J,KIM B S,et al.CT perfusion parameters predict early neurological deterioration after thrombolysis[J].AJNR Am J Neuroradiol,2022,43(10):1465-1471.
[24]KATAN M,ELKIND M S V.The potential role of blood biomarkers in patients with acute ischemic stroke:A practice-based update[J].Stroke,2021,52(1):e20-e33.
[25]ZHANG J,LI Y,LIU G,et al.Prediction models for stroke outcome:Current status and future directions[J].Lancet Digit Health,2023,5(8):e520-e529.

相似文献/References:

[1]李 斌,王高临,韩桂浩,等.Solitaire AB支架机械取栓联合动脉溶栓治疗急性缺血性脑卒中疗效观察[J].陕西医学杂志,2024,(6):806.[doi:DOI:10.3969/j.issn.1000-7377.2024.06.018]
[2]张 磊,王宜兵,常 成,等.血清Hepc-25、SMAD3、IRAK4在急性缺血性脑卒中患者血管介入治疗术后脑出血转化中的水平变化及检测意义[J].陕西医学杂志,2024,(11):1548.[doi:DOI:10.3969/j.issn.1000-7377.2024.11.024]
[3]王 萌,杜俊秋.急性缺血性脑卒中相关性肺炎危险因素分析及急性缺血性脑卒中相关分析评分的预测价值[J].陕西医学杂志,2025,54(1):97.[doi:DOI:10.3969/j.issn.1000-7377.2025.01.019]
　WANG Meng,DU Junqiu.Analysis of risk factors for acute ischemic stroke-associated pneumonia and the predictive value of AIS-APS score[J].,2025,54(9):97.[doi:DOI:10.3969/j.issn.1000-7377.2025.01.019]
[4]王雨婵,李 莎,赵 新.血清微小RNA-34b、微小RNA-181c与急性缺血性脑卒中患者机械取栓治疗预后关系研究[J].陕西医学杂志,2025,54(5):640.[doi:DOI:10.3969/j.issn.1000-7377.2025.05.013]
　WANG Yuchan,LI Sha,ZHAO Xin.Relationship between serum miR-34b,miR-181c and the prognosis of mechanical thrombectomy therapy in patients with acute ischemic stroke[J].,2025,54(9):640.[doi:DOI:10.3969/j.issn.1000-7377.2025.05.013]
[5]张佳乐,李传坤.血清可溶性CD40配体、甘露聚糖结合凝集素相关丝氨酸蛋白酶3联合检测在老年急性缺血性脑卒中诊断中的价值[J].陕西医学杂志,2025,54(7):978.[doi:DOI:10.3969/j.issn.1000-7377.2025.07.021]
　ZHANG Jiale,LI Chuankun.The application value of serum sCD40L combined with MASP-3 in the diagnosis of acute ischemic stroke in the elderly[J].,2025,54(9):978.[doi:DOI:10.3969/j.issn.1000-7377.2025.07.021]
[6]王智茜,张佳慧,赵忆.急性缺血性脑卒中介入治疗后血清谷胱甘肽过氧化物酶、S100A12、微小核糖核酸-130a水平变化与继发性脑出血的相关性分析[J].陕西医学杂志,2026,(1):73.[doi:DOI:10.3969/j.issn.1000-7377.2026.01.013]
　WANG Zhiqian,ZHANG Jiahui,ZHAO Yi.Correlation analysis of serum GSHPx,S100A12,miR-130a levels and secondary cerebral hemorrhage after acute ischemic stroke intervention[J].,2026,(9):73.[doi:DOI:10.3969/j.issn.1000-7377.2026.01.013]
[7]隋 菱,王红梅.血清miR-214、TLR4、Galectin-3与急性缺血性脑卒中患者预后关系研究[J].陕西医学杂志,2026,(5):669.[doi:DOI:10.3969/j.issn.1000-7377.2026.05.017]
　SUI Ling,WANG Hongmei.Relationship between serum miR-214,TLR4,Galectin-3 and prognosis in patients with acute ischemic stroke[J].,2026,(9):669.[doi:DOI:10.3969/j.issn.1000-7377.2026.05.017]
[8]岳蒙丽,夏元亮,锁六军,等.急性缺血性脑卒中静脉溶栓后出血转化结局的预测模型构建与内部验证[J].陕西医学杂志,2026,(9):1248.[doi:DOI:10.3969/j.issn.1000-7377.2026.09.016]
　YUE Mengli,XIA Yuanliang,SUO Liujun,et al.Developing and internally validating a nomogram to predict hemorrhage following IV thrombolysis in acute ischemic stroke[J].,2026,(9):1248.[doi:DOI:10.3969/j.issn.1000-7377.2026.09.016]
[9]胡振顺,崔国庆,康智勇,等.多模态CT关键灌注参数联合侧支循环评分在急性缺血性脑卒中患者静脉溶栓后出血性转化中的预测价值[J].陕西医学杂志,2026,(4):485.[doi:DOI:10.3969/j.issn.1000-7377.2026.04.009]
　HU Zhenshun,CUI Guoqing,KANG Zhiyong,et al.The predictive value of multimodal CT key perfusion parameters combined with collateral circulation score in hemorrhagic transformation after intravenous thrombolysis in patients with acute ischemic stroke[J].,2026,(9):485.[doi:DOI:10.3969/j.issn.1000-7377.2026.04.009]

备注/Memo

备注/Memo:
江苏省重点研发计划项目（2025SF-1206）
更新日期/Last Update: 2026-09-15