切换至 "中华医学电子期刊资源库"

中华危重症医学杂志(电子版) ›› 2026, Vol. 19 ›› Issue (02) : 122 -130. doi: 10.3877/cma.j.issn.1674-6880.2026.02.005

论著

基于随机森林与LASSO回归的急性心肌梗死PCI术后3年不良事件预测模型构建与验证
周文考1, 袁丽2, 任晓媛3, 谢强4, 苏力德5, 闫敏5, 陈智浩5, 黄灵炎1,()   
  1. 1361100 厦门,厦门大学附属翔安医院急诊医学科(医务室)
    2361100 厦门,厦门大学附属翔安医院肾脏移植科
    3361100 厦门,厦门大学附属翔安医院健康医学中心
    4361100 厦门,厦门大学附属翔安医院超声科
    5361100 厦门,厦门大学附属翔安医院心血管中心
  • 收稿日期:2025-02-02 出版日期:2026-04-30
  • 通信作者: 黄灵炎
  • 基金资助:
    福建省自然科学基金资助项目(2024J08006); 厦门市医疗卫生指导性项目(3502Z20254ZD1257)

Construction and validation of a predictive model for 3-year adverse events after percutaneous coronary intervention in acute myocardial infarction using random forest and LASSO regression

Wenkao Zhou1, Li Yuan2, Xiaoyuan Ren3, Qiang Xie4, Lide Su5, Min Yan5, Zhihao Chen5, Lingyan Huang1,()   

  1. 1Department of Emergency Medicine (Medical Affairs Office), Xiang'an Hospital of Xiamen University, Xiamen 361100, China
    2Department of Kidney Transplantation, Xiang'an Hospital of Xiamen University, Xiamen 361100, China
    3Health Management Center, Xiang'an Hospital of Xiamen University, Xiamen 361100, China
    4Department of Ultrasound, Xiang'an Hospital of Xiamen University, Xiamen 361100, China
    5Cardiovascular Center, Xiang'an Hospital of Xiamen University, Xiamen 361100, China
  • Received:2025-02-02 Published:2026-04-30
  • Corresponding author: Lingyan Huang
引用本文:

周文考, 袁丽, 任晓媛, 谢强, 苏力德, 闫敏, 陈智浩, 黄灵炎. 基于随机森林与LASSO回归的急性心肌梗死PCI术后3年不良事件预测模型构建与验证[J/OL]. 中华危重症医学杂志(电子版), 2026, 19(02): 122-130.

Wenkao Zhou, Li Yuan, Xiaoyuan Ren, Qiang Xie, Lide Su, Min Yan, Zhihao Chen, Lingyan Huang. Construction and validation of a predictive model for 3-year adverse events after percutaneous coronary intervention in acute myocardial infarction using random forest and LASSO regression[J/OL]. Chinese Journal of Critical Care Medicine(Electronic Edition), 2026, 19(02): 122-130.

目的

旨在通过机器学习算法、最小绝对收缩和选择算子(LASSO)回归和差异性分析筛选影响急性心肌梗死(AMI)患者行经皮冠状动脉介入治疗(PCI)术后3年发生不良心血管事件的危险因素,并建立相关预测模型。

方法

纳入2020年1月至2021年12月在厦门大学附属翔安医院进行PCI治疗的400例AMI患者,根据术后3年内是否发生不良心血管事件分为不良事件组(n = 102)和预后良好组(n = 298),并按照7 ∶ 3分为训练集(n = 280)和验证集(n = 120)。采用卡方检验、独立样本t检验和单因素Mann-Whitney U检验等差异性分析方法初步筛选相关危险因素。随机森林和LASSO回归对影响不良预后的临床特征进一步提取。韦恩图综合上述3种方案的交集变量,"rms"程辑包整合交集变量进行列线图绘制,"pROC"和"rmda"程辑包对列线图进行受试者工作特征(ROC)曲线分析和决策曲线分析(DCA)验证。

结果

差异性分析和LASSO回归均筛选出11组危险因素,提取随机森林的前15种临床特征与前两者交集显示,心率、年龄、血肌酐、血红蛋白和左心室舒张末期直径是AMI患者行PCI术后3年发生不良事件的重要因素。基于5种变量构建的相关列线图具有较高诊断价值,训练集准确度为0.643,验证集准确度为0.683。内部验证ROC显示训练集的曲线下面积(AUC)为0.649[95%置信区间(CI)(0.571,0.726),P < 0.001],验证集的AUC为0.796[95%CI(0.699,0.892),P < 0.001]。

结论

通过机器学习、LASSO回归和差异性分析,筛选出了影响AMI患者行PCI术后3年不良事件的关键因素,构建的相关预测模型具有较高价值。

Objective

To identify risk factors for 3-year major adverse cardiovascular events (MACE) in patients with acute myocardial infarction (AMI) after percutaneous coronary intervention (PCI) using machine learning algorithms, least absolute shrinkage and selection operator (LASSO) regression, and differential analysis, and to develop a corresponding predictive model.

Methods

A total of 400 AMI patients who underwent PCI at Xiang'an Hospital of Xiamen University between January 2020 and December 2021 were retrospectively enrolled. Patients were divided into a MACE group (n = 102) and a good prognosis group (n = 298) according to the occurrence of adverse cardiovascular events within 3 years after PCI, and were further divided into a training set (n = 280) and a validation set (n = 120) in a 7 ∶ 3 ratio. Chi-square test, independent samples t-test, and Mann-Whitney U test were used for preliminary screening of potential risk factors. Random forest and LASSO regression were further applied to identify important clinical features associated with poor prognosis. A Venn diagram was used to obtain the intersection variables from the three methods. The "rms" package was used to construct a nomogram based on the selected variables. The predictive performance of the model was evaluated using receiver operating characteristic (ROC) curve analysis and decision curve analysis with the "pROC" and "rmda" packages.

Results

The differential analysis and LASSO regression respectively identified 11 risk factors. Among the 15 features selected by the random forest model, five overlapping variables were identified, including heart rate, age, serum creatinine, hemoglobin, and left ventricular end-diastolic diameter. The nomogram constructed based on these five variables demonstrated good predictive performance, with an accuracy of 0.643 in the training set and 0.683 in the validation set. The area under the ROC curve was 0.649 [95% confidence interval (CI) (0.571, 0.726), P < 0.001] in the training set and 0.796 [95%CI (0.699, 0.892), P < 0.001] in the validation set.

Conclusions

Through machine learning, LASSO regression, and differential analysis, key factors influencing adverse events within 3 years after PCI in AMI patients are identified. The constructed predictive model has high value in forecasting such events.

表1 AMI患者行PCI术后3年内不良事件组和预后良好组差异性分析
变量 不良事件组(n = 102) 预后良好组(n = 298) t/χ2/Z P
年龄(岁, ± s 66 ± 12 61 ± 11 3.856 < 0.001
性别[例(%)]     1.925 0.165
28(27.5) 62(20.8)    
74(72.5) 236(79.2)    
高血压[例(%)] 61(59.8) 164(55.0) 0.703 0.402
糖尿病[例(%)] 33(32.4) 89(29.9) 0.222 0.638
犯罪血管[例(%)]     0.842 0.656
左前降支 55(53.9) 145(48.7)    
左旋冠状动脉 15(14.7) 49(16.4)    
右冠状动脉 32(31.4) 104(34.9)    
病理性Q波[例(%)] 60(58.8) 133(44.6) 6.130 0.013
心肌梗死史[例(%)] 16(15.7) 29(9.7) 2.699 0.100
前壁心肌梗死[例(%)] 62(60.8) 136(45.6) 6.974 0.008
killip分级[例(%)]     9.764 0.002
Ⅰ ~ Ⅱ级 65(63.7) 236(79.2)    
Ⅲ ~ Ⅳ级 37(36.3) 62(20.8)    
支架数量[例(%)]     0.718 0.698
一支 68(66.7) 187(62.8)    
两支 30(29.4) 101(33.9)    
三支 4(3.9) 10(3.4)    
血尿素氮(mmol/L, ± s 6.8 ± 1.9 6.7 ± 2.2 0.351 0.726
血糖(mmol/L, ± s 7.7 ± 2.7 7.7 ± 2.6 0.180 0.857
中性粒细胞百分比(%, ± s 76 ± 13 75 ± 11 1.118 0.264
白细胞(× 109/L, ± s 11 ± 4 10 ± 4 1.515 0.130
收缩压(mmHg, ± s 131 ± 27 132 ± 28 0.348 0.728
心率(次/min, ± s 80 ± 19 76 ± 16 2.134 0.033
血肌酐(μmol/L, ± s 77 ± 16 72 ± 16 2.618 0.009
血尿酸(μmol/L, ± s 333 ± 79 336 ± 70 0.324 0.746
血红蛋白(g/L, ± s 139 ± 16 146 ± 16 3.825 < 0.001
血小板(× 109/L, ± s 241 ± 60 228 ± 55 1.913 0.056
白蛋白(g/L, ± s 37.8 ± 4.0 38.0 ± 3.8 0.645 0.520
总胆固醇(mmol/L, ± s 5.9 ± 1.0 5.6 ± 1.0 2.432 0.015
甘油三酯(mmol/L, ± s 1.06 ± 0.67 1.12 ± 0.74 0.676 0.499
高密度脂蛋白(mmol/L, ± s 1.26 ± 0.28 1.19 ± 0.26 2.229 0.026
低密度脂蛋白[mmol/L,MP25P75)] 3.02(2.49,3.73) 3.00(2.50,3.60) 0.728 0.467
肌钙蛋白I(μg/L, ± s 18 ± 12 16 ± 13 1.455 0.146
D-二聚体[mg/L,MP25P75)] 0.90(0.30,1.60) 1.20(0.50,1.80) 2.006 0.045
肌酸激酶同工酶(U/L, ± s 130 ± 89 129 ± 92 0.103 0.918
Gensini评分(分, ± s 73 ± 31 76 ± 31 0.936 0.350
左心室舒张末期直径(mm, ± s 52 ± 7 50 ± 6 3.018 0.003
左心房直径(mm, ± s 38 ± 5 37 ± 6 1.872 0.062
表2 训练集与验证集AMI患者各变量比较
变量 训练集(n = 280) 验证集(n = 120) t/χ2/Z P
不良事件[例(%)]     0.010 0.920
预后良好组 209(74.6) 89(74.2)    
不良事件组 71(25.4) 31(25.8)    
年龄(岁, ± s 62 ± 11 63 ± 12 0.840 0.401
性别[例(%)]     2.458 0.117
69(24.6) 21(17.5)    
211(75.4) 99(82.5)    
高血压[例(%)] 162(57.9) 63(52.5) 0.980 0.322
糖尿病[例(%)] 90(32.1) 32(26.7) 1.188 0.276
犯罪血管[例(%)]     4.320 0.115
左前降支 146(52.1) 54(45.0)    
左旋冠状动脉 38(13.6) 26(21.7)    
右冠状动脉 96(34.3) 40(33.3)    
病理性Q波[例(%)] 130(46.4) 63(52.5) 1.240 0.265
心肌梗死史[例(%)] 30(10.7) 15(12.5) 0.268 0.604
前壁心肌梗死[例(%)] 139(49.6) 59(49.2) 0.008 0.930
killip分级[例(%)]     0.006 0.940
Ⅰ ~ Ⅱ级 211(75.4) 90(75.0)    
Ⅲ ~ Ⅳ级 69(24.6) 30(25.0)    
支架数量[例(%)]     3.381 0.184
一支 177(63.2) 78(65.0)    
两支 96(34.3) 35(29.2)    
三支 7(2.5) 7(5.8)    
血尿素氮(mmol/L, ± s 6.7 ± 2.1 6.6 ± 2.3 0.498 0.619
血糖(mmol/L, ± s 7.7 ± 2.6 7.8 ± 2.5 0.113 0.910
中性粒细胞百分比(%, ± s 75 ± 12 77 ± 12 1.739 0.083
白细胞(× 109/L, ± s 10 ± 31 10 ± 4 1.210 0.227
收缩压(mmHg, ± s 131 ± 27 135 ± 29 1.364 0.173
心率(次/min, ± s 76 ± 16 77 ± 17 0.460 0.646
血肌酐(μmol/L, ± s 72 ± 16 75 ± 16 1.160 0.247
血尿酸(μmol/L, ± s 335 ± 73 337 ± 71 0.326 0.745
血红蛋白(g/L, ± s 144 ± 17 144 ± 16 0.311 0.756
血小板(× 109/L, ± s 230 ± 56 236 ± 56 0.975 0.330
白蛋白(g/L, ± s 38.0 ± 3.8 37.9 ± 4.0 0.363 0.717
总胆固醇(mmol/L, ± s 5.7 ± 1.1 5.6 ± 1.0 0.167 0.867
甘油三酯(mmol/L, ± s 1.1 ± 0.7 1.1 ± 0.8 0.536 0.592
高密度脂蛋白(mmol/L, ± s 1.20 ± 0.27 1.23 ± 0.27 1.170 0.243
低密度脂蛋白[mmol/L,MP25P75)] 3.0(2.5,3.6) 3.0(2.5,3.7) 0.579 0.562
肌钙蛋白I(μg/L, ± s 16 ± 13 18 ± 13 1.067 0.287
D-二聚体[mg/L,MP25P75)] 1.0(0.4,1.8) 1.2(0.4,1.8) 0.782 0.434
肌酸激酶同工酶(U/L, ± s 128 ± 90 133 ± 93 0.519 0.604
Gensini评分(分, ± s 75 ± 31 77 ± 31 0.455 0.649
左心室舒张末期直径(mm, ± s 50 ± 6 51 ± 6 1.090 0.277
左心房直径(mm, ± s 37.3 ± 5.7 36.9 ± 6.1 0.690 0.491
表3 深度机器学习结果详情
表4 机器学习算法间对比详情
表5 特征变量重要性详情
图1 LASSO回归系数筛选图(a)、轨迹图(b)和3种分析方法筛选出的变量交汇韦恩图(c)注:LASSO.最小绝对收缩和选择算子
表6 LASSO回归非零系数详情
图2 AMI患者行PCI术后3年发生不良事件预测的列线图及其验证曲线注:AMI.急性心肌梗死;PCI.经皮冠状动脉介入治疗;ROC.受试者工作特征;DCA.决策曲线分析;a图为预测模型列线图;b图为列线图相关ROC曲线;c图为列线图为未标准化DCA验证曲线;d图为列线图标准化DCA验证曲线
1
Gaba P, Bhatt DL. Promise of a novel classification system for acute myocardial infarction[J]. Can J Cardiol, 2024, 40 (1): 15-17.
2
Zhu D, Zhang X, Fang Y, et al. Identification of a lactylation-related gene signature as the novel biomarkers for early diagnosis of acute myocardial infarction[J]. Int J Biol Macromol, 2024, 282 (Pt 6): 137431.
3
Yu F, Xu Y, Peng J. Evaluation of a nomogram model for predicting in-hospital mortality risk in patients with acute ST-elevation myocardial infarction and acute heart failure post-PCI[J]. Scand Cardiovasc J, 2024, 58 (1): 2387001.
4
Zhu L, Liu Y, Wang K, et al. Regulated cell death in acute myocardial infarction: molecular mechanisms and therapeutic implications[J]. Ageing Res Rev, 2025, 104: 102629.
5
Zhang S, Zhu Z, Luo M, et al. The optimal definition and prediction nomogram for left ventricular remodelling after acute myocardial infarction[J]. ESC Heart Fail, 2023, 10 (5): 2955-2965.
6
柯晴潆,沈延飞,许强宏,等.预测脓毒性心肌病患者院内死亡风险列线图模型的构建及验证[J/OL].中华危重症医学杂志(电子版)202417(1):10-18.
7
Alkhalil M, De Maria GL, Akbar N, et al. Prospects for precision medicine in acute myocardial infarction: patient-level insights into myocardial injury and repair[J]. J Clin Med, 2023, 12 (14): 4668.
8
Kim M, Kang D, Kim MS, et al. Acute myocardial infarction prognosis prediction with reliable and interpretable artificial intelligence system[J]. J Am Med Inform Assoc, 2024, 31 (7): 1540-1550.
9
中华医学会心血管病学分会,中华心血管病杂志编辑委员会.急性ST段抬高型心肌梗死诊断和治疗指南(2019)[J].中华心血管病杂志201947(10):766-783.
10
Welt FGP, Batchelor W, Spears JR, et al. Reperfusion injury in patients with acute myocardial infarction: JACC scientific statement[J]. J Am Coll Cardiol, 2024, 83 (22): 2196-2213.
11
Imbesi A, Greco A, Spagnolo M, et al. Targeting inflammation after acute myocardial infarction[J]. J Am Coll Cardiol, 2025, 86 (15): 1146-1169.
12
Udell JA, Bahit MC, Campbell P, et al. Prevention of heart failure after acute myocardial infarction[J]. Lancet, 2025, 406 (10508): 1154-1170.
13
Wang Y, Lu Y, Liu C, et al. Association between serum calcium level and the risk of acute kidney injury in patients with acute myocardial infarction: evidences from the MIMIC-IV database[J]. Ren Fail, 2024, 46 (2): 2401137.
14
Galli M, Niccoli G, De Maria G, et al. Coronary microvascular obstruction and dysfunction in patients with acute myocardial infarction[J]. Nat Rev Cardiol, 2024, 21 (5): 283-298.
15
Chapman AR, Taggart C, Boeddinghaus J, et al. Type 2 myocardial infarction: challenges in diagnosis and treatment[J]. Eur Heart J, 2025, 46 (6): 504-517.
16
Patti G, Cumitini L, Bosco M, et al. Impact of a personalized, strike early and strong lipid-lowering approach on low-density lipoprotein-cholesterol levels and cardiovascular outcome in patients with acute myocardial infarction[J]. Eur Heart J Cardiovasc Pharmacother, 2025, 11 (2): 143-154.
17
Dettling A, Huber K, Kristensen SD, et al. Antiplatelet therapy in acute myocardial infarction complicated by cardiogenic shock[J]. Clin Res Cardiol, 2025, 114 (10): 1237-1245.
18
Matter MA, Tschaikowsky T, Stahli BE, et al. Acute-on-chronic inflammation in acute myocardial infarction[J]. Curr Opin Cardiol, 2024, 39 (6): 535-542.
19
庞慧,李新立. CCL2作为心血管疾病潜在治疗靶点的前景与挑战[J/OL].中华危重症医学杂志(电子版)202417(4):336-341.
20
Dieter EG, Nanjundappa A. Sex differences in acute myocardial infarction[J]. Expert Rev Cardiovasc Ther, 2024, 22 (6): 201-202.
21
Bansal M, Mehta A, Balakrishna AM, et al. Race, ethnicity, and gender disparities in acute myocardial infarction[J]. Crit Care Clin, 2024, 40 (4): 685-707.
22
Wu L, Zhou B, Liu D, et al. LASSO regression-based diagnosis of acute ST-segment elevation myocardial infarction (STEMI) on electrocardiogram (ECG)[J]. J Clin Med, 2022, 11 (18): 5408.
23
Villa E, Saso L, Chichiarelli S, et al. Antioxidant cardioprotection in acute myocardial infarction: from mechanisms to therapeutic strategies[J]. Front Biosci (Landmark Ed), 2025, 30 (8): 27678.
24
Wu Y, Chen H, Li L, et al. Construction of novel gene signature-based predictive model for the diagnosis of acute myocardial infarction by combining random forest with artificial neural network[J]. Front Cardiovasc Med, 2022, 9: 876543.
25
Eser P, Jaeger E, Marcin T, et al. Acute and chronic effects of high-intensity interval and moderate-intensity continuous exercise on heart rate and its variability after recent myocardial infarction: a randomized controlled trial[J]. Ann Phys Rehabil Med, 2022, 65 (1): 101444.
26
D'Antonio G, Di Fazio N, Pellegrini L et al. Immunohistochemical assessment of acute myocardial infarction: a systematic review[J]. Int J Mol Sci, 2025, 26 (18): 8901.
27
Krittanawong C, Khawaja M, Tamis-Holland JE, et al. Acute myocardial infarction: etiologies and mimickers in young patients[J]. J Am Heart Assoc, 2023, 12 (18): e029971.
28
Zhu Y, Lai Y, Hu Y, et al. The mechanisms underlying acute myocardial infarction in chronic kidney disease patients undergoing hemodialysis[J]. Biomed Pharmacother, 2024, 177: 117050.
29
Saggu JS, Seelhammer TG, Esmaeilzadeh S, et al. Mechanical circulatory support for acute myocardial infarction cardiogenic shock: review and recent updates[J]. J Cardiothorac Vasc Anesth, 2025, 39 (4): 1049-1066.
30
Portela GT, Carson JL, Swanson SA, et al. Effect of four hemoglobin transfusion threshold strategies in patients with acute myocardial infarction and anemia: a target trial emulation using MINT trial data[J]. Ann Intern Med, 2024, 177 (11): 1489-1498.
31
Benedikt M, Aziz F, Froschl T, et al. Impact of baseline ECG characteristics on changes in cardiac biomarkers and echocardiographic metrices after acute myocardial infarction treated with Empagliflozin[J]. Sci Rep, 2024, 14 (1): 15083.
32
雒尧,崔蕾.急性心肌梗死体外膜肺氧合治疗后二尖瓣腱索断裂一例[J/OL].中华危重症医学杂志(电子版)202417(6):514-516.
[1] 邬明嫄, 李婷婷, 鲜欣欣, 罗朝阳, 杨青, 卢漫. 基于超微血流成像血管指数的列线图模型诊断肢端黑色素瘤引流区域淋巴结的价值[J/OL]. 中华医学超声杂志(电子版), 2026, 23(04): 276-282.
[2] 袁智帆, 刘锦辉, 丁尚伟, 周大治, 陈俊君, 何志忠, 陈沛芬, 冷晓玲. 超声瘤内、瘤周影像组学联合临床特征构建列线图模型评估乳腺癌新辅助化疗效果[J/OL]. 中华医学超声杂志(电子版), 2026, 23(02): 112-123.
[3] 丁彩霞, 曲景辉, 裴英宏, 李静娜, 郑晓瑜, 徐岭植, 李思思. 基于RNA结合蛋白基因表达特征的乳腺癌预后预测模型构建及评价分析[J/OL]. 中华乳腺病杂志(电子版), 2026, 20(03): 138-147.
[4] 卢帅, 陈建明, 李敏娟, 单祎宁, 曹仁巍, 查晔军, 蒋协远. 基于NHANES数据库分析抑郁与骨质疏松性骨折愈合不良的关联及预测模型构建与验证[J/OL]. 中华损伤与修复杂志(电子版), 2026, 21(03): 167-176.
[5] 李琳, 庞乐, 潘霞, 朱磊, 王桂子, 刘梅. 汉中社区老年人口腔衰弱与躯体衰弱的横断面关联分析及风险评估模型构建[J/OL]. 中华口腔医学研究杂志(电子版), 2026, 20(03): 217-224.
[6] 王珩, 马金曼, 王弼偲. 腹主动脉瘤腔内修复术后并发症的风险因素分析及预测模型构建[J/OL]. 中华普外科手术学杂志(电子版), 2026, 20(03): 292-295.
[7] 黄楚曦, 吴卓. 人工智能在膀胱癌影像中的应用进展[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2026, 20(03): 241-247.
[8] 徐宏博, 胡玉良, 魏雪栋, 金李晨, 武克风, 陈逸伦, 陆兵, 周守军, 侯建全. 基于临床和CT影像组学特征的机器学习模型对经皮肾镜术后脓毒症的预测价值[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2026, 20(03): 297-306.
[9] 陈志坚, 俞建达, 林泽润, 林宏焕, 易长昱, 池小斌, 吕立志, 陈永标. 基于术前影像肿瘤负荷评分的模型对单发肝细胞癌微血管侵犯的预测价值[J/OL]. 中华肝脏外科手术学电子杂志, 2026, 15(03): 379-385.
[10] 马凯蒂, 哈团结. 基于机器学习的糖尿病肾脏病患者疲乏状态诊断预测模型构建[J/OL]. 中华肾病研究电子杂志, 2026, 15(03): 144-150.
[11] 黄霞, 张和平, 何永成. 机器学习驱动的IgA肾病精准治疗:疗效评估、预后预测及临床转化[J/OL]. 中华肾病研究电子杂志, 2026, 15(03): 166-169.
[12] 韩一梅, 冯仕川, 陈志娟. 高脂血症性急性胰腺炎复发的危险因素及其列线图预测模型构建[J/OL]. 中华消化病与影像杂志(电子版), 2026, 16(03): 222-228.
[13] 孙娟华, 白引苗, 孔胜男, 王梦雪, 王文慧, 张红梅. 胰腺癌患者化疗相关性恶心呕吐风险列线图构建及验证[J/OL]. 中华消化病与影像杂志(电子版), 2026, 16(02): 114-119.
[14] 刘莹, 陈中闯, 陈雪英, 程云涛, 甘立军. 腔内影像学与功能学评估指导下的西罗莫司涂层球囊在冠心病中的应用进展[J/OL]. 中华诊断学电子杂志, 2026, 14(02): 120-125.
[15] 梁怡凡, 牟婧宇, 吴雅婷, 邳靖陶, 陈乐, 武剑. 不同人工智能模型预测脑卒中不良预后诊断效能的荟萃分析[J/OL]. 中华脑血管病杂志(电子版), 2026, 20(03): 308-319.
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?