心脑血管疾病与气象因素关系预测模型的建立与评估

doi:10.3969/j.issn.1673-5765.2024.06.004

摘要/Abstract

摘要： 目的探讨心脑血管疾病的发病状况和气象因素之间的关系，运用机器学习方法预测心脑血管疾病发病风险等级，为疾病防控提供科学依据。
方法以贵州省疾病预防控制中心提供的心脑血管疾病患者为研究对象，通过相关性分析确定模型的预测因子，分别基于支持向量机、极端梯度提升、轻量级梯度提升机、随机森林这4种机器学习模型构建心脑血管疾病发病风险的预测模型。将纳入患者以8∶2的比例分为训练集和测试集。训练集用于模型训练和参数优化，测试集用于评价模型效果。主要以准确率来评价各模型的预测效果。
结果本研究共纳入60岁以上心脑血管疾病患者16 383例，其中女性6507例，且日发病例数表现为不平衡数据，其中诊断类型包括急性心肌梗死、卒中、心绞痛、心源性猝死。日发病例数与气压、气温、湿度3大类26种气象因素存在相关性，与气压、相对湿度呈正相关，与气温呈负相关。采用GridSearchCV函数找出最优权重的配比后，使用机器学习方法构建模型，并通过测试集验证输出模型指标参数。轻量级梯度提升机模型在预测任务中表现最佳，准确率达到85.68%，精确率为82.56%，召回率为85.68%，F1分数为79.56%（均P＜0.05）。心脑血管疾病患者发病前72 h气温的INP值为63 814，是影响日发病例数最重要的气象因素，排名第2和第3的是发病前48 h气温和发病前24 h气温，对应INP值分别为62 002、43 216。
结论基于机器学习方法建立的心脑血管疾病发病预测模型具有较高的预测价值，其中轻量级梯度提升机模型的预测效果最好。

文章导读： 本研究成功构建了基于机器学习的心脑血管疾病发病预测模型，不仅揭示了气象因素与心脑血管疾病发病风险之间的密切联系，而且通过轻量级梯度提升机模型的优异表现，为心脑血管疾病的早期预警和精准防控提供了强有力的科学依据。

关键词: 心脑血管疾病; 气象因素; 机器学习; 预测模型

Abstract: Objective To explore the relationship between the incidence of cardiovascular and cerebrovascular diseases and meteorological factors, and to predict the incidence risk levels of cardiovascular and cerebrovascular diseases using machine learning methods, with the aim of providing the scientific basis for disease prevention and control.
Methods Patients with cardiovascular and cerebrovascular diseases, whose information were provided by the Guizhou Center for Disease Control and Prevention, were selected as subjects. The predictive factors of the model were determined through correlation analysis, and the prediction models for the risk of cardiovascular and cerebrovascular diseases were constructed based on four machine learning models: support vector machine, extreme gradient boosting, light gradient boosting machine, and random forest. The included patients were divided into the training set and the testing set in the ratio of 8∶2. The training set was used for model training and parameter optimization, and the testing set was used to evaluate the effect of the model. The predictive performance of each model was mainly evaluated by accuracy.
Results A total of 16 383 patients over 60 years of age with cardiovascular and cerebrovascular diseases were included in this study, including 6507 women. The number of daily cases was unbalanced, in which the diagnostic types included acute myocardial infarction, stroke, angina pectoris, and sudden cardiac death. The number of daily cases was correlated with 26 meteorological factors in 3 categories including air pressure, air temperature, and humidity, and was positively correlated with air pressure and relative humidity, but negatively correlated with air temperature. The GridSearchCV function was used to find the optimal weight ratio, the machine learning method was used to construct the model, and the output model index parameters were verified through the testing set. The light gradient boosting machine model performed best in the prediction task, with an accuracy of 85.68%, a precision of 82.56%, a recall of 85.68%, and the F1 score was 79.56% (all P<0.05). The INP value of the temperature of 72 h before the onset of cardiovascular and cerebrovascular diseases was 63 814, which was the most important meteorological factor affecting the number of daily cases. The temperatures of 48 h before the onset and 24 h before the onset respectively ranked second and third, corresponding to INP values of 62 002 and 43 216.
Conclusions The prediction models of cardiovascular and cerebrovascular diseases based on machine learning methods have high predictive value. Among them, the light gradient boosting machine model presented the best performance.

Key words: Cardiovascular and cerebrovascular disease; Meteorological factor; Machine learning; Prediction model

中图分类号:

尚媛媛, 杜正静, 陈静怡, 彭波, 龙杰琦. 心脑血管疾病与气象因素关系预测模型的建立与评估[J]. 中国卒中杂志, 2024, 19(6): 632-639.

SHANG Yuanyuan, DU Zhengjing, CHEN Jingyi, PENG Bo, LONG Jieqi. Establishment and Evaluation of the Prediction Models of the Relationship between Cardiovascular and Cerebrovascular Diseases and Meteorological Factors[J]. Chinese Journal of Stroke, 2024, 19(6): 632-639.

参考文献

[1] 施仲伟. 回眸过去30年全球和中国的心血管疾病负担及其危险因素——1990年至2019年全球心血管疾病负担及其危险因素报告解读[J]. 诊断学理论与实践，2021，20（4）：349-355.
SHI Z W. A review of the global burden of cardiovascular disease and its risk factors in China over the past 30 years—an interpretation of the global burden of cardiovascular disease and its risk factors report from 1990 to 2019[J]. J Diagn Concepts Pract，2021，20（4）：349-355.
[2] WANG C，ZHU H R，RAO C J. Machine learning-based decision-making mechanism for risk assessment of cardiovascular disease[J]. Computer Modeling in Engineering & Sciences，2024，138（1）：691-718.
[3] LI F C，WU P，ONG H H，et al. Evaluating and mitigating bias in machine learning models for cardiovascular disease prediction[J/OL]. J Biomed Inform，2023，138：104294[2024-05-01]. https://doi.org/10.1016/j.jbi.2023.104294.
[4] 毛宇清，尹东屏，孙宁，等. 南京市心脑血管疾病的医疗气象预报研究[J]. 气象，2010，36（11）：82-87.
MAO Y Q，YIN D P，SUN N，et al. Research on medical-meteorological forecast models of cardiovascular-cerebrovascular diseases in Nanjing[J]. Meteorological Monthly，2010，36（11）：82-87.
[5] 郭志恒，刘青萍，刘芳，等. 基于机器学习算法的脑卒中疾病早期预测模型研究[J]. 计算机与数字工程，2021，49（11）：2180-2183，2247.
GUO Z H，LIU Q P，LIU F，et al. Early prediction model of stroke based on machine learning algorithm[J]. Computer & Digital Engineering，2021，49（11）：2180-2183，2247.
[6] 程学伟，韩兆洲. 市域脑卒中疾病与气象因素的关系及预测[J]. 气象，2018，44（6）：837-843.
CHENG X W，HAN Z Z. Relationship between stroke and meteorological factors and its prediction in urban areas[J]. Meteorological Monthly，2018，44（6）：837-843.
[7] DRITSAS E，TRIGKA M. Efficient data-driven machine learning models for cardiovascular diseases risk prediction[J/OL]. Sensors（Basel），2023，23（3）：1161[2024-05-01]. https://doi.org/10.3390/s23031161.
[8] TAYLAN O，ALKABAA A S，ALQABBAA H S，et al. Early prediction in classification of cardiovascular diseases with machine learning，neuro-fuzzy and statistical methods[J/OL]. Biology（Basel），2023，12（1）：117[2024-05-01]. https://doi.org/10.3390/biology12010117.
[9] 邹文蕊，王渝，孙跃民，等. 急性冠脉综合征院前急救分析及与气象因素的关系[J]. 中国慢性病预防与控制，2020，28（8）：591-595.
ZOU W R，WANG Y，SUN Y M，et al. Analysis on the association of pre-hospital first aid for acute coronary syndrome with meteorological elements[J]. Chin J Prev Contr Chron Dis，2020，28（8）：591-595.
[10] 蒲志宏，刘艳群，王红. 心血管病与气象条件的关系[J]. 中国社区医师，2019，35（15）：6-7.
PU Z H，LIU Y Q，WANG H. Relationship between cardiovascular diseases and meteorological conditions[J]. Chinese Community Doctors，2019，35（15）：6-7.
[11] 张楠，侯斌，乔丽，等. 气象因素对心脑血管疾病影响的研究概况[J]. 中西医结合心脑血管病杂志，2018，16（9）：1193-1196.
ZHANG N，HOU B，QIAO L，et al. Overview of the effects of meteorological factors on cardiovascular and cerebrovascular diseases[J]. Chinese Journal of Integrative Medicine on Cardio-/Cerebrovascuiar Disease，2018，16（9）：1193-1196.
[12] 林亚楠，郭岩，杨西，等. 大连市气象因素与急性脑梗死发病的相关性分析[J]. 中国脑血管病杂志，2018，15（3）：113-118.
LIN Y N，GUO Y，YANG X，et al. Correlation analysis between meteorological factors and onset of acute cerebral infarction in Dalian[J]. Chinese Journal of Cerebrovascular Diseases，2018，15（3）：113-118.
[13] 陈念，王春茹. 气象环境因素与脑卒中发病的相关性研究[J]. 医学信息，2019，32（16）：34-37.
CHEN N，WANG C R. Research of correlation between meteorological environmental factors and the onset of stroke[J]. Journal of Medical Information，2019，32（16）：34-37.
[14] 张楠，尚可政，刘继锋，等. 脑血管病的气象危险指数预报研究[J/OL]. 陕西气象，2018（1）：16-20[2024-05-01]. https://doi.org/10.3969/j.issn.1006-4354.2018.01.003.
ZHANG N，SHANG K Z，LIU J F，et al. Prediction of meteorological risk index of cerebrovascular diseases[J/OL]. Journal of Shaanxi Meteorology，2018（1）：16-20[2024-05-01]. https://doi.org/10.3969/j.issn.1006-4354.2018.01.003.
[15] 尚晶，孙兆彬，苗世光，等. 北京地区温度预报对心脑血管疾病的健康影响及经济效益评估[J]. 气象学报，2023，81（3）：520-529.
SHANG J，SUN Z B，MIAO S G，et al. Health impact and economic benefit of temperature forecast on cardiovascular mortality in Beijing[J]. Acta Meteorologica Sinica，2023，81（3）：520-529.
[16] 聂晓峰，贾少贤，廉青青，等. 2022年运城市居民心脑血管疾病死亡状况分析[J]. 中西医结合心脑血管病杂志，2023，21（19）：3658-3661.
NIE X F，JIA S X，LIAN Q Q，et al. Analysis of deaths from cardiovascular and cerebrovascular diseases in Yuncheng city residents in 2022[J]. Chinese Journal of Integrative Medicine on Cardio-/Cerebrovascuiar Disease，2023，21（19）：3658-3661.
[17] 何芬芬，董意麟，吕恒，等. 山东省平邑县日均气温对心脑血管疾病每日死亡影响的时间序列研究[J]. 蚌埠医学院学报，2023，48（5）：646-651.
HE F F，DONG Y L，LYU H，et al. Effect of the doily mean temperature on the death of cardiovascular and cerebrovascular diseases in Pingyi，Shandong Province：a time-series study[J]. J Bengbu Med Coll，2023，48（5）：646-651.
[18] 王雯艺，杨浩峰，苏德奇，等. 2019—2021年乌鲁木齐市昼夜温差对心脑血管疾病住院量的影响[J]. 公共卫生与预防医学，2023，34（2）：50-55.
WANG W Y，YANG H F，SU D Q，et al. Effect of diurnal temperature difference on hospital admissions for cardiovascular and cerebrovascular diseases in Urumqi in 2019—2021[J]. J Pub Health Prev Med，2023，34（2）：50-55.
[19] GEBRE K R，RAMANAN K V，RAGHAVAN S，et al. A machine learning approach to identify individualized baseline MRI，plasma，cardiovascular and lifestyle predictors of a 5‐year cognitive decline[J/OL]. Alzheimer’s Dement，2023，19（Suppl. 24）：e082831[2024-05-01]. https://doi.org/10.1002/alz.082831.
[20] LEE J，CHOI Y，KO T，et al. Prediction of cardiovascular complication in patients with newly diagnosed type 2 diabetes using an XGBoost/GRU-ODE-Bayes-based machine-learning algorithm[J]. Endocrinol Metab（Seoul），2024，39（1）：176-185.