基于两样本孟德尔随机化与可解释机器学习算法的冠心病风险预测模型构建及发病因素探究

吴炬; 刘光阳; 明天娇; 伍亚舟; 李芳

doi:10.16016/j.2097-0927.202507090

您当前的位置：

首页 >

文章列表页 >

基于两样本孟德尔随机化与可解释机器学习算法的冠心病风险预测模型构建及发病因素探究

智能医学与预测模型 | 更新时间：2026-02-04

- 基于两样本孟德尔随机化与可解释机器学习算法的冠心病风险预测模型构建及发病因素探究
- Etiological factors for coronary heart disease and construction of a risk prediction model using two-sample MR and interpretable machine learning
- 陆军军医大学学报 2026年48卷第2期页码：229-241
- 作者机构：
  
  1.陆军军医大学（第三军医大学）：，军事预防医学系军队卫生统计学教研室，重庆
  2.陆军军医大学（第三军医大学）：，基础医学院无军籍大队，重庆
  3.对外经济贸易大学国际经济贸易学院，北京
- 作者简介：
  
  李芳，E-mail： oucfli@163.com
- 基金信息：
  
  国家自然科学基金项目(82173621)
- DOI：10.16016/j.2097-0927.202507090
  中图分类号： R195.1;R195.4;R541.4
- 收稿：2025-07-28，
  
  修回：2025-11-11，
  
  录用：2025-11-11，
  
  纸质出版：2026-01-30
- 稿件说明：
移动端阅览
吴炬，刘光阳，明天娇，等.基于两样本孟德尔随机化与可解释机器学习算法的冠心病风险预测模型构建及发病因素探究［J］.陆军军医大学学报，2026，48（02）：229-241.DOI：10.16016/j.2097-0927.202507090.

WU J，LIU G Y，MING T J，et al.Etiological factors for coronary heart disease and construction of a risk prediction model using two-sample MR and interpretable machine learning［J］.J Army Med Univ，2026，48（02）：229-241.DOI：10.16016/j.2097-0927.202507090.
吴炬，刘光阳，明天娇，等.基于两样本孟德尔随机化与可解释机器学习算法的冠心病风险预测模型构建及发病因素探究［J］.陆军军医大学学报，2026，48（02）：229-241.DOI：10.16016/j.2097-0927.202507090. DOI：

WU J，LIU G Y，MING T J，et al.Etiological factors for coronary heart disease and construction of a risk prediction model using two-sample MR and interpretable machine learning［J］.J Army Med Univ，2026，48（02）：229-241.DOI：10.16016/j.2097-0927.202507090. DOI：

摘要

目的

本研究旨在利用临床数据和基因变异数据，探究冠心病（coronary heart disease， CHD）的危险因素及其因果关联，并构建可解释的风险预测模型。

方法

本研究为回顾性研究，从Kaggle平台和IEU OpenGWAS Project数据库分别收集临床数据和基因变异数据队列。利用SMOTEENN混合采样技术平衡数据，结合Logistic回归模型和两样本MR方法筛选危险因素并分析其因果效应。进一步基于随机森林（random forest， RF）、极限梯度提升算法（eXtreme gradient boosting， XGBoost）和神经网络（artificial neural network，ANN）构建风险预测模型，并通过SHAP算法评估特征重要性。

结果

Logistic回归分析显示，性别、年龄、教育程度、吸烟、高血压、总胆固醇、收缩压和血糖与CHD显著相关（

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405405&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405404&type=

2.28600001

2.62466669

0.05），而BMI、舒张压、中风和糖尿病等无显著关联。两样本MR分析表明，BMI（

=1.014，95%

：1.011~1.017，

=1.720×10

-22

）、年龄（

=1.015，95%

：1.012~1.019，

=3.455×10

-18

）、日吸烟量（

=1.007，95%

：1.002~1.011，

=0.005）、高血压（

=1.057，95%

：1.046~1.067，

=5.870×10

-28

）等11个因素与CHD呈正向因果关系；教育程度（

=0.970，95%

：0.960~0.979，

=1.231×10

-9

）和高密度脂蛋白（

=0.990，95%

：0.986~0.993，

=0.002）呈负向因果关系。机器学习模型中，SMOTEENN-RF模型表现最优，准确率达0.887，AUC为0.962。SHAP分析显示，年龄、性别、高血压、收缩压和日吸烟量对模型贡献最大。

结论

年龄、高血压、血脂等关键因素与冠心病显著相关，并成功构建了性能优异的SMOTEENN-RF预测模型，为冠心病的风险预警与精准防治提供了可靠的方法学支持和实用工具。

Abstract

Objective

To investigate the risk factors and causal relationships of coronary heart disease (CHD) by utilizing clinical data and genetic variation data

and construct an interpretable risk prediction model for the disease.

Methods

A retrospective cohort analysis was conducted on the clinical data and genetic variation data collected from the Kaggle platform and the IEU OpenGWAS Project database

respectively. SMOTEENN mixed sampling was used to balance the data. Logistic regression models and two-sample Mendelian randomization (MR) were combined to screen risk factors and analyze their causal effects. Then risk prediction models were further constructed using random forest (RF)

eXtreme gradient boosting (XGBoost)

and artificial neural networks (ANN)

and feature importance was assessed with the SHAP algorithm.

Results

Logistic regression analysis showed that gender

age

education level

smoking

hypertension

total cholesterol (TC)

systolic blood pressure (SBP)

and blood glucose were significantly associated with CHD (

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405427&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405419&type=

2.28600001

2.62466669

0.05)

while body mass index (BMI)

diastolic blood pressure (DBP)

history of stroke

and diabetes had no such association. Two-sample MR analysis indicated that BMI (

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405422&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405421&type=

4.74133301

2.62466669

=1.014

95%

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405468&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405429&type=

3.72533321

2.62466669

: 1.011 to 1.017

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405427&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405419&type=

2.28600001

2.62466669

=1.720×10

-22

)

age (

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405422&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405421&type=

4.74133301

2.62466669

=1.015

95%

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405468&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405429&type=

3.72533321

2.62466669

: 1.012 to 1.019

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405427&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405419&type=

2.28600001

2.62466669

=3.455×10

-18

)

number of cigarettes smoked per smoker per day (

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405422&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405421&type=

4.74133301

2.62466669

=1.007

95%

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405468&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405429&type=

3.72533321

2.62466669

: 1.002 to 1.011

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405427&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405419&type=

2.28600001

2.62466669

=0.005)

hypertension (

=1.057

95%

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405468&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405429&type=

3.72533321

2.62466669

: 1.046 to 1.067

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405427&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405419&type=

2.28600001

2.62466669

=5.870×10

-28

) were positively associated with CHD; Education level (

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405422&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405421&type=

4.74133301

2.62466669

=0.970

95%

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405468&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405429&type=

3.72533321

2.62466669

: 0.960 to 0.979

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405427&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405419&type=

2.28600001

2.62466669

=1.231×10

-9

) and high-density lipoprotein (

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405422&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405421&type=

4.74133301

2.62466669

=0.990

95%

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405468&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405429&type=

3.72533321

2.62466669

: 0.986 to 0.993

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405427&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=100405419&type=

2.28600001

2.62466669

=0.002) were negatively associated with CHD. In the machine learning models

the SMOTEENN-RF performed best

with an accuracy rate of 0.887 and an AUC value of 0.962. SHAP analysis indicated that age

gender

hypertension

SBP

and cigarettes smoked per day contributed most to the model.

Conclusion

Key risk factors such as age

hypertension

and blood lipid levels are significantly correlated with CHD. A high-performing SMOTEENN-RF prediction model is successfully constructed

providing reliable methodological support and practical tool for CHD risk early warning and precision prevention and treatment.

关键词

Keywords

references

SHAKYA S ， SHRESTHA A ， ROBINSON S ， et al . Global comparison of the economic costs of coronary heart disease： a systematic review and meta-analysis ［J］. BMJ Open ， 2025 ， 15 （ 1 ）： e084917 . DOI： 10.1136/bmjopen-2024-084917 http://dx.doi.org/10.1136/bmjopen-2024-084917 .

徐兴梅，胡阳，邓洁，等 . 冠心病心理障碍及其诊治进展［J］. 中国老年保健医学， 2022 ， 20 （ 1 ）： 99 - 103 . DOI： 10.3969/j.issn.1672-2671.2022.01.030 http://dx.doi.org/10.3969/j.issn.1672-2671.2022.01.030 .

XU X M ， HU Y ， DENG J ， et al . Psychological disorders of coronary heart disease and its progress in diagnosis and treatment ［J］. Chin J Geriatr Care ， 2022 ， 20 （ 1 ）： 99 - 103 . DOI： 10.3969/j.issn.1672-2671.2022.01.030 http://dx.doi.org/10.3969/j.issn.1672-2671.2022.01.030 .

AMINORROAYA A ， YOOSEFI M ， REZAEI N ， et al . Global， regional， and national quality of care of ischaemic heart disease from 1990 to 2017： a systematic analysis for the Global Burden of Disease Study 2017 ［J］. Eur J Prev Cardiol ， 2022 ， 29 （ 2 ）： 371 - 379 . DOI： 10.1093/eurjpc/zwab066 http://dx.doi.org/10.1093/eurjpc/zwab066 .

王成龙，何新叶，李燕奇，等 . 冠心病危险因素分析及机器学习算法构建预测模型研究［J］. 中国循证心血管医学杂志， 2023 ， 15 （ 12 ）： 1334 - 1337 . DOI： 10.3969/j.issn.1674-4055.2023.12.12 http://dx.doi.org/10.3969/j.issn.1674-4055.2023.12.12 .

WANG C L ， HE X Y ， LI Y Q ， et al . Analysis of coronary heart disease risk factors and construction of disease prediction models ［J］. Chin J Evid Bases Cardiovasc Med ， 2023 ， 15 （ 12 ）： 1334 - 1337 . DOI： 10.3969/j.issn.1674-4055.2023.12.12 http://dx.doi.org/10.3969/j.issn.1674-4055.2023.12.12 .

JOLOUDARI J H ， HASSANNATAJ JOLOUDARI E ， SAADATFAR H ， et al . Coronary artery disease diagnosis； ranking the significant features using a random trees model ［J］. Int J Environ Res Public Health ， 2020 ， 17 （ 3 ）： 731 . DOI： 10.3390/ijerph17030731 http://dx.doi.org/10.3390/ijerph17030731 .

GARAVAND A ， SALEHNASAB C ， BEHMANESH A ， et al . Efficient model for coronary artery disease diagnosis： a comparative study of several machine learning algorithms ［J］. J Healthc Eng ， 2022 ， 2022 ： 5359540 . DOI： 10.1155/2022/5359540 http://dx.doi.org/10.1155/2022/5359540 .

NAUSHAD S M ， HUSSAIN T ， INDUMATHI B ， et al . Machine learning algorithm-based risk prediction model of coronary artery disease ［J］. Mol Biol Rep ， 2018 ， 45 （ 5 ）： 901 - 910 . DOI： 10.1007/s11033-018-4236-2 http://dx.doi.org/10.1007/s11033-018-4236-2 .

ZHANG T X ， HUANG S M ， XIE P F ， et al . Development of machine learning tools for predicting coronary artery disease in the Chinese population ［J］. Dis Markers ， 2022 ， 2022 ： 6030254 . DOI： 10.1155/2022/6030254 http://dx.doi.org/10.1155/2022/6030254 .

黄浩东，刘小株，龚军，等 . 基于机器学习算法建立2型糖尿病患者冠心病辅助诊断模型［J］. 复旦学报（医学版）， 2022 ， 49 （ 2 ）： 226 - 233， 256 . DOI： 10.3969/j.issn.1672-8467.2022.02.010 http://dx.doi.org/10.3969/j.issn.1672-8467.2022.02.010 .

HUANG H D ， LIU X Z ， GONG J ， et al . Auxiliary diagnosis model of coronary heart disease in patients with type 2 diabetes mellitus based on machine learning algorithm ［J］. Fudan Univ J Med Sci ， 2022 ， 49 （ 2 ）： 226 - 233， 256 . DOI： 10.3969/j.issn.1672-8467.2022.02.010 http://dx.doi.org/10.3969/j.issn.1672-8467.2022.02.010 .

LARSSON S C ， BUTTERWORTH A S ， BURGESS S . Mendelian randomization for cardiovascular diseases： principles and applications ［J］. Eur Heart J ， 2023 ， 44 （ 47 ）： 4913 - 4924 . DOI： 10.1093/eurheartj/ehad736 http://dx.doi.org/10.1093/eurheartj/ehad736 .

WANG H Y ， LI X K ， YUAN Y ， et al . Association of machine learning ultrasound radiomics and disease outcome in triple negative breast cancer ［J］. Am J Cancer Res ， 2022 ， 12 （ 1 ）： 152 - 164 .

NONG X Z ， HUANG S Y ， HE F C ， et al . Can a robust machine learning-based integrated framework benefit universal water quality evaluation applications？ Comparative view in the whole coastal regions of China ［J］. Mar Pollut Bull ， 2025 ， 220 ： 118399 . DOI： 10.1016/j.marpolbul.2025.118399 http://dx.doi.org/10.1016/j.marpolbul.2025.118399 .

XU Y ， YE W ， SONG Q Y ， et al . Using machine learning models to predict the duration of the recovery of COVID-19 patients hospitalized in Fangcang shelter hospital during the Omicron BA. 2.2 pandemic ［J］. Front Med ， 2022 ， 9 ： 1001801 . DOI： 10.3389/fmed.2022.1001801 http://dx.doi.org/10.3389/fmed.2022.1001801 .

王晓丽，施天行，彭德荣，等 . 两种机器学习算法构建老年冠心病患病风险评估模型的效能比较研究［J］. 中华全科医学， 2021 ， 19 （ 4 ）： 523 - 527 . DOI： 10.16766/j.cnki.issn.1674-4152.001852 http://dx.doi.org/10.16766/j.cnki.issn.1674-4152.001852 .

WANG X L ， SHI T X ， PENG D R ， et al . Comparative study on the effectiveness of two machine learning algorithms in constructing risk assessment models of coronary heart disease in the elderly ［J］. Chin J Gen Pract ， 2021 ， 19 （ 4 ）： 523 - 527 . DOI： 10.16766/j.cnki.issn.1674-4152.001852 http://dx.doi.org/10.16766/j.cnki.issn.1674-4152.001852 .

SHI Y J ， XIANG Y ， YE Y X ， et al . A framework for detecting causal effects of risk factors at an individual level based on principles of Mendelian randomisation： applications to modelling individualised effects of lipids on coronary artery disease ［J］. EBioMedicine ， 2025 ， 113 ： 105616 . DOI： 10.1016/j.ebiom.2025.105616 http://dx.doi.org/10.1016/j.ebiom.2025.105616 .

LIN Z T ， DENG Y Q ， PAN W . Combining the strengths of inverse-variance weighting and Egger regression in Mendelian randomization using a mixture of regressions model ［J］. PLoS Genet ， 2021 ， 17 （ 11 ）： e1009922 . DOI： 10.1371/journal.pgen.1009922 http://dx.doi.org/10.1371/journal.pgen.1009922 .

BURGESS S ， DAVEY SMITH G ， DAVIES N M ， et al . Guidelines for performing Mendelian randomization investigations： update for summer 2023 ［J］. Wellcome Open Res ， 2023 ， 4 ： 186 . DOI： 10.12688/wellcomeopenres.15555.3 http://dx.doi.org/10.12688/wellcomeopenres.15555.3 .

BOWDEN J ， DAVEY SMITH G ， BURGESS S . Mendelian randomization with invalid instruments： effect estimation and bias detection through Egger regression ［J］. Int J Epidemiol ， 2015 ， 44 （ 2 ）： 512 - 525 . DOI： 10.1093/ije/dyv080 http://dx.doi.org/10.1093/ije/dyv080 .

KIM S ， LEE J ， NAM S H . Artificial intelligence applications in intracerebral hemorrhage care： implications for clinical and nursing practice - a narrative literature review ［J］. Front Rehabil Sci ， 2025 ， 6 ： 1620335 . DOI： 10.3389/fresc.2025.1620335 http://dx.doi.org/10.3389/fresc.2025.1620335 .

IKRAM R M A ， WANG M ， MOAYEDI H ， et al . Application of smart technologies for predicting soil erosion patterns ［J］. Sci Rep ， 2025 ， 15 ： 26479 . DOI： 10.1038/s41598-025-12125-0 http://dx.doi.org/10.1038/s41598-025-12125-0 .

WEN J ， SHI X W ， LIU Y ， et al . Malnutrition mediates the association between handgrip status and asthma risk： an observational and prospective cohort study from multiple European countries ［J］. Front Nutr ， 2025 ， 12 ： 1555888 . DOI： 10.3389/fnut.2025.1555888 http://dx.doi.org/10.3389/fnut.2025.1555888 .

MA C S ， LEI M . Time series prediction for monitoring cardiovascular health in autistic patients ［J］. Front Psychiatry ， 2025 ， 16 ： 1623986 . DOI： 10.3389/fpsyt.2025.1623986 http://dx.doi.org/10.3389/fpsyt.2025.1623986 .

RAHMAN F ， AL RIFAI M ， BLAHA M J ， et al . Relation of diastolic blood pressure and coronary artery calcium to coronary events and outcomes （from the multi-ethnic study of atherosclerosis）［J］. Am J Cardiol ， 2017 ， 120 （ 10 ）： 1797 - 1803 . DOI： 10.1016/j.amjcard.2017.07.094 http://dx.doi.org/10.1016/j.amjcard.2017.07.094 .

KIM M S ， KIM W J ， KHERA A V ， et al . Association between adiposity and cardiovascular outcomes： an umbrella review and meta-analysis of observational and Mendelian randomization studies ［J］. Eur Heart J ， 2021 ， 42 （ 34 ）： 3388 - 3403 . DOI： 10.1093/eurheartj/ehab454 http://dx.doi.org/10.1093/eurheartj/ehab454 .

陆丕能，孙宁玲，陆鋆，等 . 吸烟量与冠心病关系的病例对照研究［J］. 中华流行病学杂志， 2002 ， 23 （ 4 ）： 297 - 300 . DOI： 10.3760/j.issn： 0254-6450.2002.04.015 http://dx.doi.org/10.3760/j.issn：0254-6450.2002.04.015 .

LU P N ， SUN N L ， LU J ， et al . Case control study on the association of coronary artery disease and cigarette smoking ［J］. Chin J Epidemiol ， 2002 ， 23 （ 4 ）： 297 - 300 . DOI： 10.3760/j.issn： 0254-6450.2002.04.015 http://dx.doi.org/10.3760/j.issn：0254-6450.2002.04.015 .

LALO R ， ZEKJA I ， KAMBERI F . Association of cardiovascular disease risk and health-related behaviors in stroke patients ［J］. Int J Environ Res Public Health ， 2023 ， 20 （ 4 ）： 3693 . DOI： 10.3390/ijerph20043693 http://dx.doi.org/10.3390/ijerph20043693 .

洪天配，母义明，纪立农，等 . 2型糖尿病合并动脉粥样硬化性心血管疾病患者降糖药物应用专家共识［J］. 中国介入心脏病学杂志， 2017 ， 25 （ 7 ）： 361 - 371 . DOI： 10.3969/j.issn.1004-8812.2017.07.001 http://dx.doi.org/10.3969/j.issn.1004-8812.2017.07.001 .

HONG T P ， MU Y M ， JI L N ， et al . Chinese expert consensus on anti-diabetic agents in treating patients with type 2 diabetes and atherosclerotic cardiovascular disease ［J］. Chin J Interv Cardiol ， 2017 ， 25 （ 7 ）： 361 - 371 . DOI： 10.3969/j.issn.1004-8812.2017.07.001 http://dx.doi.org/10.3969/j.issn.1004-8812.2017.07.001 .

BÖHM M ， REIL J C ， DEEDWANIA P ， et al . Resting heart rate： risk indicator and emerging risk factor in cardiovascular disease ［J］. J Tird Mil Med Univ ， 2015 ， 128 （ 3 ）： 219 - 228 . DOI： 10.1016/j.amjmed.2014.09.016 http://dx.doi.org/10.1016/j.amjmed.2014.09.016 .

刘涛，陈勇，赖成民，等 . 脉压与中老年冠心病关系的探讨［J］. 第三军医大学学报， 2006 ， 28 （ 15 ）： 1628 - 1629 . DOI： 10.3321/j.issn： 1000-5404.2006.15.028 http://dx.doi.org/10.3321/j.issn：1000-5404.2006.15.028 .

LIU T ， CHEN Y ， LAI C M ， et al . Relationship between pulse pressure and coronary heart disease in middle-aged and elderly people ［J］. J Tird Mil Med Univ ， 2006 ， 28 （ 15 ）： 1628 - 1629 . DOI： 10.3321/j.issn： 1000-5404.2006.15.028 http://dx.doi.org/10.3321/j.issn：1000-5404.2006.15.028 .

JANKOWSKI P ， WEBER T . Pulse pressure and cardiovascular risk in diseased patients ［J］. J Hum Hypertens ， 2016 ， 30 （ 5 ）： 293 - 294 . DOI： 10.1038/jhh. 2015.83 http://dx.doi.org/10.1038/jhh.2015.83 .

ASSMANN G ， CULLEN P ， EVERS T ， et al . Importance of arterial pulse pressure as a predictor of coronary heart disease risk in PROCAM ［J］. Eur Heart J ， 2005 ， 26 （ 20 ）： 2120 - 2126 . DOI： 10.1093/eurheartj/ehi467 http://dx.doi.org/10.1093/eurheartj/ehi467 .

GRIMES D A ， SCHULZ K F . An overview of clinical research： the lay of the land ［J］. Lancet ， 2002 ， 359 （ 9300 ）： 57 - 61 . DOI： 10.1016/S0140-6736（02）07283-5 http://dx.doi.org/10.1016/S0140-6736（02）07283-5 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

哮喘与内分泌疾病的关联：孟德尔随机化研究与中介分析

主观睡眠问题与表观遗传年龄加速关联的孟德尔随机化研究

基于系统评价和Meta分析的糖尿病足溃疡患者截肢风险预测模型的开发和验证

CT-临床列线图预测甲状腺微小乳头状癌中央区淋巴结转移

心血管手术患者术后呼吸衰竭的危险因素及预测模型构建