近年来，全国高血压患病率均在不断上升，煤矿从业人员由于特殊的工作性质和工作环境，导致其高血压检出率明显高于全国平均水平。当前关于高血压的研究对象大多集中于老年人群，煤矿从业人员的高血压研究相对较少且多为现状研究，尤其并未有统一的针对煤矿从业人员的高血压风险预测模型。为对煤矿从业人员的高血压情况做出提前控制和预防，本研究收集鄂尔多斯某煤业集团煤矿从业人员职业健康体检数据，对高血压危险因素进行分析并建立了更适合煤矿从业人员的高血压风险预测模型。

本文对该煤业集团煤矿从业人员的发病特点和规律进行分析，按人口学特征划分类别，比较各个组别的人数构成比、收缩压（SBP）、舒张压（DBP）和高血压检出率；用Logistic单因素分析初步筛选出该煤矿从业人员高血压的相关危险因素，并对职业暴露各组基线资料进行比较，分析排除混杂因素之后职业暴露情况与高血压检出率的关系；运用Logistic多因素回归分析确定煤矿从业人员的高血压危险因素，明确要纳入预测模型的指标。根据筛选出的高血压危险因素，依据Framingham心脏危险评分的步骤得到煤矿从业人员高血压危险因素得分系统和预测模型公式，确定高血压预警点，得到基于Framingham危险评分的煤矿从业人员高血压风险预测模型；选取最适合该群体的二分类算法XGBoost构建煤矿从业人员XGBoost高血压风险预测模型，经过参数寻优和特征变量重要性排序，选取70%数据作为训练集，30%数据作为测试集对模型进行训练，建立预测模型。将Framingham危险评分模型与XGBoost模型进行对比分析，选取最优预测模型对该群体中暂未患高血压个体的10年内高血压发病风险进行预测，基于高血压风险预测结果和危险因素分析，提出煤矿从业人员的高血压防治措施建议。

研究结果表明：性别、年龄、吸烟、饮酒、职业暴露、BMI、高血压家族史是该煤矿从业人员高血压危险因素，在排除其他混杂因素的影响下，职业暴露情况仍是高血压的重要危险因素；Framingham高血压危险评分预测模型更适合应用于该群体的高血压风险预测；该群体中暂未患高血压的人群中有60人（10.73%）已达到一级高危预警，有37人（6.62%）已达到二级高危预警，有7人（1.25%）已达到三级高危预警；而后根据预测结果和危险因素分析提出相应的对策建议。本研究分析了煤矿从业人员高血压相关危险因素，构建出适合煤矿从业人员的高血压风险预测模型并对鄂尔多斯该煤业集团暂未患高血压的人员10年内的高血压风险进行预测。在一定程度上补充了煤矿从业人员的职业健康研究，为煤矿企业和煤矿从业人员高血压防治提供依据，减少其因身体情况而导致的不安全行为的发生。

In recent years, the prevalence rate of hypertension has been rising all over the country. Due to the special work nature and working environment, the detection rate of hypertension among coal mine employees is obviously higher than the national average level. At present, most of the research objects on hypertension are concentrated in the elderly population, and the researches on hypertension of coal mine employees are relatively few and most of them are status quo studies, especially there is no unified hypertension risk prediction model for coal mine employees. In order to control and prevent the hypertension of coal mine employees in advance, this study collected the occupational health examination data of coal mine employees in a coal industry group in Ordos, analyzed the risk factors of hypertension, and established a more suitable hypertension risk prediction model for coal mine employees.

This paper analyzes the incidence characteristics and rules of coal mine employees in the coal mining group, divides them into categories according to demographic characteristics, and compares the population composition ratio, systolic blood pressure (SBP), diastolic blood pressure (DBP) and the detection rate of hypertension in each group. Logistic univariate analysis was used to preliminarily screen out the risk factors related to hypertension in the coal mine employees, and the baseline data of occupational exposure groups were compared to analyze the relationship between occupational exposure and the detection rate of hypertension after excluding confounding factors. Multivariate Logistic regression analysis was used to determine the risk factors of hypertension in coal mine employees, and the indicators to be included in the prediction model were clearly defined. According to the selected hypertension risk factors, the hypertension risk factor scoring system and prediction model formula of coal mine employees were obtained according to the steps of Framingham heart risk score, the early warning point of hypertension was determined, and the hypertension risk prediction model of coal mine employees based on Framingham risk score was obtained. XGBoost, the binary classification algorithm most suitable for this group, was selected to build the XGBoost hypertension risk prediction model for coal mine employees. After parameter optimization and importance ranking of characteristic variables, 70% data was selected as the training set and 30% data was selected as the test set to train the model, and the prediction model was established. The Framingham risk score model and XGBoost model were compared and analyzed, and the optimal prediction model was selected to predict the risk of hypertension in this group within 10 years. Based on the prediction results of hypertension risk and the analysis of risk factors, the prevention and treatment measures of hypertension for coal mine employees were proposed.

The results showed that gender, age, smoking, drinking, occupational exposure, BMI, family history of hypertension were the risk factors for hypertension in the coal mine employees. Occupational exposure was still the important risk factors for hypertension after excluding other confounding factors. Framingham hypertension risk score prediction model is more suitable for hypertension risk prediction of this group. In this group, 60 people (10.73%) without hypertension have reached the first high risk warning, 37 people (6.62%) have reached the second high risk warning, 7 people (1.25%) have reached the third high risk warning. Then, according to the prediction results and risk factor analysis, the corresponding countermeasures and suggestions are put forward. This study analyzed the risk factors related to hypertension of coal mine employees, built a suitable hypertension risk prediction model for coal mine employees, and predicted the hypertension risk of the employees who did not suffer from hypertension in Ordos coal industry group in 10 years. To a certain extent, it supplements the occupational health research of coal mine employees, provides a basis for the prevention and treatment of hypertension in coal mine enterprises and coal mine employees, and reduces the occurrence of unsafe behaviors caused by their physical conditions.

[1]《中国心血管健康与疾病报告2022》概要[J].中国介入心脏病学杂志,2023,31(07):485-508.

[2]相静,王玖,胡西厚.健康医疗大数据驱动下的疾病风险评估与预测方法探析[J].中国卫生信息管理杂志,2018,15(03):329-333.

[3]M A Y, Rasha K, Shofiqul I, et al. Prevalence, awareness, treatment and control of hypertension in four Middle East countries[J].Journal of hypertension,2017,35(07):1457-1464.

[4]Ahmed.AlWabel, Mohammed.Almufadhi, Faisal.Alayed, et al. Assessment of hypertension and its associated risk factors among medical students in Qassim University[J].Saudi Journal of Kidney Diseases and Transplantation,2018,29(05):1100-1108.

[5]Asiya Abudesimu, Fen Liu, Dilixiati Siti, et al. An assessment of platelet parameters in different ethnic groups with hypertension subtypes and associated risk factors in Xinjiang, China[J].Clinical and Experimental Hypertension,2018,40(06):574-581.

[6]Yi D,Xia D G,Yang J, et al. Association of PPARγ and AGTR1 Polymorphisms with Hypertriglyceridemia in Chinese Population[J].Biomedical and Environmental Sciences,2018,31(08):619-622.

[7]Bjornstad, Petter, Andres-Hernando, et al. Uric Acid Is a Strong Risk Marker for Developing Hypertension From Prehypertension: A 5-Year Japanese Cohort Study[J].Hypertension: An Official Journal of the American Heart Association,2018,71(01):78-86.

[8]申屠光明.影响高血压患者药物治疗依从性相关因素Logistic回归分析[J].海峡药学,2008,20(12):108-110.

[9]D.E. Morisky, L.W. Green, D.M. Levine. Concurrent and predictive validity of a self-reported measure of medication adherence[J].Medical care,1986:67-74.

[10]汪宏莉,韩延柏,陈涛,等.老年人高血压风险预测肥胖指标筛选[J].中国公共卫生,2020,36(01):105-109.

[11]潘佩,何森,陈晓平.内脏脂肪指数对高血压的预测价值[J].中华高血压杂志,2022,30(05):430-434.

[12]陈欣,王丹,刘佳莉,等.不同风险预测模型评估高血压人群10年心血管疾病风险的比较[J].中华高血压杂志,2023,31(10):929-936.

[13]冶成芳,任映丽,王梦卉,等.高血压前期人群发生心血管疾病的风险预测列线图模型构建[J].实用心脑肺血管病杂志,2023,12(05):1-6.

[14]张妍妍,马霞,王雪,等.Logistic回归分析联合ROC曲线综合评价老年高血压群体认知损害的预测指标[J].联勤军事医学,2023,37(09):771-777.

[15]冯雪辉,方鑫,张谦,等.内蒙古地区35～75岁人群肥胖指标对高血压患病的预测效果[J].中华疾病控制杂志,2023,27(07):794-799+849.

[16]吴月惟,綦苗苗,孔月琼,等.海南省居民高血压患病风险预测模型建立与验证[J].中国预防医学杂志,2023,24(02):93-101.

[17]沙吉旦·阿不都热衣木,宋星明,哈力沙·艾尔肯江,等.H型高血压的影响因素及其预测模型构建[J].实用心脑肺血管病杂志,2023,31(08):54-58+65.

[18]曹宏,索霞,黄建军.煤矿职工高血压发病危险因素调查[J].职业与健康,2009,25(04):344-346.

[19]张卫清,信雅菊.煤矿工人高血压状况调查分析[J].中国疗养医学,2011,20(12):1127-1128.

[20]邱卉,范红敏,秦天榜,等.职业因素与煤矿工人高血压前期和高血压的关系研究[J].工业卫生与职业病,2013,39(05):288-292.

[21]王富丽,秦天榜,范红敏,等.职业紧张与煤矿工人高血压的关系研究[J].工业卫生与职业病,2013,39(02):87-93.

[22]刁祥玉.煤矿职工高血压发病原因分析及护理干预[J].职业卫生与病伤,2015,30(04):245-247.

[23]李静峰.煤矿职工高血压患病情况分析[J].基层医学论坛,2011,15(26):799-800.

[24]殷金珠,陈淑婷,乔楠,等.男性煤矿井下工人高血压影响因素分析[J].中国职业医学,2022,49(02):201-205+210.

[25]陈金,苏军,宋壮志,等.内蒙古部分地区农村居民高血压患病情况及相关因素的Logistic回归分析[J].河北医药,2018(02):285-287.

[26]冷冰.重庆市居民社会经济地位与高血压病的关系研究[D].重庆医科大学,2015.

[27]谢霏,谢利,李鑫,等.重庆市南岸区中老年人高血压合并糖尿病的患病率及影响因素分析[J].中华流行病学杂志,2019,40(06):666-669.

[28]黄华,夏俊瑞,刘灿,等.合肥市包河区成人慢性病流行状况及影响因素分析[J].安徽预防医学杂志,2018,24(03):166-171+183.

[29]赵秀丽,陈捷,崔艳丽,等.中国14省市高血压现状的流行病学研究[J].中华医学杂志,2006,86(16):1148-1152.

[30]Wang J, Zhang L, Wang F, et al. Prevalence, awareness, treatment, and control of hypertension in China:results from a national survey[J].Am J Hypertens,2014,27(11):1355-1361.

[31]王栋,王洁,汤成春,等.南京市城区社区居民高血压现况调查及影响因素分析[J]. 东南大学学报(医学版),2014,33(05):581-585.

[32]Di Angelantonio E, Bhupathiraju S N, Wormser D, et al. Body-mass index and all-cause mortality: individual-participant-data meta-analysis of 239 prospective studies in four continents[J].The Lancet,2016,388(10046):776-786.

[33]Wang Z, Chen Z, Zhang L, et al. Status of hypertension in China: results from the China Hypertension Survey, 2012–2015[J].Circulation,2018,137(22):2344-2356.

[34]刘军,路方红,吴凡,等.老年高血压与体重指数关系的研究[J].中国老年学杂志,2005(10):1172-1174.

[35]王增武,郝光,王馨,等.我国中年人群超重/肥胖现况及心血管病危险因素聚集分析[J].中华高血压杂志,2014,22(10):1000.

[36]冯宝玉,陈纪春,李莹,等.中国成年人超重和肥胖与高血压发病关系的随访研究[J].Chinese journal of Epidemiology,2016,37(05):606-611.

[37]冯长龙,张永忠,李秀兰,等.高血压前期流行病学研究进展[J].白求恩医学杂志,2018,16(04):403-405．

[38]周辉,曹霞,王雅琴,等.长沙市社区高血压前期流行病学调查及危险因素分析[J].中南大学学报(医学版),2016,41(07):750-756.

[39]黄燕惠,余昌泽,王家骥,等.中山市镇区成年人高血压患病影响因素分析[J].中华疾病控制杂志,2014,18(10):940-943.

[40]郑文秋,郝春艳.锦州市社区老年高血压患病现状及影响因素[J].解放军预防医学杂志,2016,34(04):513-515.

[41]孙娇,王永红.江苏省南通市男性出租车司机高血压患病率现状及因素分析[J].基层医学论坛,2024,28(06):14-16+20.

[42]冯雅,孙弥环,郭益莉,等.中青年体检人群高血压前期检出情况及其危险因素分析[J].实用预防医学,2024,31(02):227-230.

[43]熊华利,刘代强,唐大乂,等.男性晨醒后吸第一支烟的时间与高血压患病的相关性分析[J].现代预防医学,2024,51(02):309-313+359.

[44]Dong G H, Qian Z, Xaverius P K, et al. Association between long-term air pollution and increased blood pressure and hypertension in China[J].Hypertension,2013,61(3):578-584.

[45]Shang Y, Sun Z, Cao J, et al. Systematic review of Chinese studies of short-term exposure to air pollution and daily mortality[J].Environment international,2013,54:100-111.

[46]Cakmak S, Dales R, Leech J, et al. The influence of air pollution on cardiovascular and pulmonary function and exercise capacity: Canadian Health Measures Survey (CHMS)[J].Environmental research,2011,111(08):1309-1312.

[47]Chuang K J, Yan Y H, Cheng T J. Effect of air pollution on blood pressure, blood lipids, and blood sugar: a population-based approach[J].Journal of occupational and environmental medicine,2010,52(03):258-262.

[48]Wu S, Deng F, Huang J, et al. Blood pressure changes and chemical constituents of particulate air pollution: results from the healthy volunteer natural relocation (HVNR) study[J].Environmental health perspectives,2013,121(01):66-72.

[49]Jacobs L, Buczynska A, Walgraeve C, et al. Acute changes in pulse pressure in relation to constituents of particulate air pollution in elderly persons[J].Environmental Research,2012,11760-67.

[50]Hoffmann B, Luttmann-Gibson H, Cohen A, et al. Opposing effects of particle pollution, ozone, and ambient temperature on arterial blood pressure[J].Environmental health perspectives,2012,120(02):241-246.

[51]Liu L , Ruddy T, Dalipaj M, et al. Effects of Indoor, Outdoor, and Personal Exposure to Particulate Air Pollution on Cardiovascular Physiology and Systemic Mediators in Seniors[J].Journal of Occupational and Environmental Medicine,2009,51(09):1088-1098.

[52]Mordukhovich I, Wilker E, Suh Macintosh H, et al. Black Carbon Exposure, Oxidative Stress Genes, and Blood Pressure in a Repeated Measures Study[J].Environmental Health Perspectives,2009,117(11):1767-1772.

[53]Wilker E H, Baccarelli A, Suh H, et al. Black Carbon Exposures, Blood Pressure, and Interactions with Single Nucleotide Polymorphisms in MicroRNA Processing Genes[J].Environmental Health Perspectives,2010,118(07):943-948.

[54]Zhao X, Sun Z, Ruan Y, et al. Personal Black Carbon Exposure Influences Ambulatory Blood PressureNovelty and Significance[J].Atmos Res,2014,63(04):871-877.

[55]Chen S Y, Su T C, Lin Y L, et al. Short-term Effects of Air Pollution on Pulse Pressure Among Nonsmoking Adults[J].Epidemiology,2012,23(02):341-348.

[56]Guo X, Zou L, Zhang X, et al. Prehypertension: a meta-analysis of the epidemiology, risk factors, and predictors of progression[J].Texas heart institute journal,2011,38(06):643.

[57]Erem C, Hacihasanoglu A, Kocak M, et al. Prevalence of prehypertension and hypertension and associated risk factors among Turkish adults: Trabzon Hypertension Study[J].Journal of public health,2009,31(01):47-58.

[58]常永丽.河北省邢台市城乡居民高血压患病情况及其影响因素的流行病学调查研究[J].实用心脑肺血管病杂志,2015,23(11):37-40.

[59]刘晓红,曾长佑,胡志勇.丽水市区居民高血压患病及影响因素分析[J].实用预防医学,2016,23(03):339-341.

[60]韩冰,周刚,冯石献,等.河南省居民高血压相关危险因素分析[J].郑州大学学报(医学版),2014,49(01):89-92.

[61]李金梅,隋虹,付金林,等.黑龙江省居民高血压患病及影响因素分析[J].中国公共卫生,2009,25(01):23-24.

[62]赵晶,季艳微,奚彩艳.哈尔滨市健康体检人群高血压患病情况及影响因素分析[J].华南预防医学,2024,50(02):175-178.

[63]刘奇.高血压合并糖尿病前期中医证候特点及相关心血管危险因素研究[D].新疆医科大学,2021.

[64]曾奇.成年居民BMI轨迹影响因素及其与高血压发病的研究[D].重庆医科大学,2021.

[65]Camilla T, Andrea F, Elhassan M, et al. Nation-wide hypertension screening in Italy: data from May Measurements Month 2017-Europe[J].European heart journal supplements : journal of the European Society of Cardiology,2019,21(SD):D66-D70.

[66]杨琴,袁丽.糖尿病风险预测模型的研究进展[J].中华护理杂志,2010,45(07):668-670.

[67]Wang R, Zhao Y, He X, et al. Impact of hypertension on health-related quality of life in a population-based study in Shanghai, China[J].Public Health,2009,123(08):534-539.

[68]Gao Y, Chen G, Tian H, et al. Prevalence of hypertension in China:across-sectional study[J].PLoS One,2013,8(06):e65938.

[69]Liang Y, Liu R, Du S, et al. Trends in incidence of hypertension in Chinese adults, 1991-2009:The China Health and Nutrition Survey[J].Int J Cardiol,2014,175(01):96-101.

[70]Cameron AC, Lang NN, Touyz RM. Drug Treatment of Hypertension:Focus on Vascular Health[J].Drugs,2016,76(16):1529-1550.

[71]Wang A, An N, Chen G, et al. Predicting hypertension without measurement: a non-invasive, questionnaire-based approach[J].Expert Systems with Applications,2015,42(21):7601-7609.

[72]Lafreniere D, Zulkernine F, Barber D, et al. Using machine learning to predict hypertension from a clinical dataset[J].Computational Intelligence.2017.

[73]Shinde S R, Bhadikar P S. A genetic algorithm, information gain and artificial neural network based approach for hypertension diagnosis[C].2016 International Conference on Inventive,2016:1-7.

[74]M. W. L. Moreira, J. J. P. C. Rodrigues, A. M. B. Oliveira, et al. Predicting hypertensive disorders in high-risk pregnancy using the random forest approach[J].2017 IEEE International Conference on Communications (ICC),2017,pp.1-5.

[75]Luo Y, Li Y, Lu Y, et al. The prediction of hypertension based on convolution neural network[C]//2018 IEEE 4th International Conference on Computer and Communications (ICCC).2018,2122-2127.

[76]Majid N,Kemal P. Automatic Classification of Hypertension Types Based on Personal Features by Machine Learning Algorithms[J].Mathematical Problems in Engineering,2020,1-13.

[77]Ren Y, Fei H, Liang X, et al. A hybrid neural network model for predicting kidney disease in hypertension patients based on electronic health records[J].BMC Medical Informatics and Decision Making,2019,19(51):1-8.

[78]Paynter NP, Cook NR, Everett BM, et al. Prediction of incident hypertension riskin women with currently normal blood pressure[J].Am J Med.2009,122:464-471.

[79]Kshirsagar AV, Chiu YL, Bomback AS, et al. A hypertension risk score for middle-aged and older adults[J].J ClinHypertens(Greenwich).2010,12:800-808.

[80]Bozorgmanesh M, Hadaegh F, Mehrabi Y, et al. A point-score system superior to blood Pressure measures alone for predicting incident hypertension: Tehran Lipid and Glucose Study[J].J Hypertens.2011,29:1486-1493.

[81]Chien KL, Hsu HC, Su TC, et al. Prediction models for the risk of new-onset hypertension in ethnic Chinese in Taiwan[J].J Hum Hypertens.201I;25:294-303.

[82]Chen Y, Yu S, Chen S, et al. The Current Situation of Hypertension among Ruralminimal Assurance Family Participants in Liaoning(China);:A Cross-Sectional Study[J].Int J Environ Res Public Health,2016,13(12):E1199.

[83]郑黎强.辽宁省阜新县农村社会环境高血压高发区高血压发病风险预测模型的验证与建立[D].辽宁:中国医科大学,2014.

[84]于涛,刘焕乐,冯新,等.基于健康管理队列的高血压风险预测模型[J].山东大学学报(医学版),2017,55(06):61-63.

[85]石福艳.常见慢性病危险因素测量及风险等级评估方法研究[D].第四军医大学,2015.

[86]Mcgrane M M, Essery E, Obbagy J, et al. Dairy Consumption, Blood Pressure, and Risk of Hypertension:An Evidence-Based Review of Recent Literature[J].Curr Cardiovasc Risk Rep,2011,5(04):287-298.

[87]刘娟,赵欢欢,马祖长,等.基于CatBoost算法和模糊分类系统的青年人血压预测方法[J].北京生物医学工程,2020,39(06):601-608.

[88]李国奇,刘静,王薇,等.中国35-64岁人群15年高血压发生风险预测研究[J]中华高血压杂志,2014,22(10):1000.

[89]曹茜.常见慢性病危险因素分析及风险评估模型的建立[D].山西医科大学,2018.

[90]周伟英,朱美英,陆殷昊,等.利用Framingham脑卒中概率模型估计老年人群的脑卒中风险[J].上海预防医学,2015,27(10):598-601．

[91]黄久仪,曹奕丰,郭吉平,等.应用改良弗明汉卒中风险评估工具预测中国人卒中风险[J].中国脑血管杂志,2013,10(05):228-232.

[92]Parikh NI, Pencina MJ, Wang TJ, et al. A risk score for predicting near-termincidence of hypertension:the Framingham Heart Study[J].Ann Intern Med.2008,148:102-110.

[93]Kivimaki M, Batty GD, Singh-Manoux A, et al. Validating the Framingham Hypertension Risk Score:results from the Whitehall II study[J].Hypertension,2009,54(03):496-501.

[94]Goh L G, Welborm T A, Dhaliwal SS. Independent external validation of cardiovascular disease mortality in women utilising Framingham and SCORE risk models:a mortality follow-up study[J].BMC Womens Health,2014,14:118.

[95]Chien K L, Hsu H C, Su TC, et al. Prediction models for the risk of new-onset hypertension in ethnic Chinese in Taiwan[J].J Hum Hypertens,2011,25:294-303.

[96]Bozorgmanesh M, Hadaegh F, Mehrabi Y, et al. A point-score system superior to blood pressure measures alone for predicting incident hypertension:Tehran Lipid and Glucose Study[J].J Hypertens,2011,29:1486-1493.

[97]张寅,孙雪松,王晓丽,等.基于区域卫生信息平台的高血压居民就诊行为大数据分析[J].中国数字医学,2018,13(09):57-59.

[98]王健美,郭丽环,胡植双,等.基于Framingham风险评分对强直性脊柱炎心血管疾病发生风险的预测分析[J].中西医结合心脑血管病杂志,2023,21(22):4245-4249.

[99]张加生,李科,张丽丽,等.基于Framingham量表评估高血压病患者脑卒中发病风险与颈动脉斑块的关系[J].中国临床神经科学,2024,32(01):46-50.

[100]袁如玉,王海彦,李颖,等.少数民族老年高血压病人服药依从性促进及阻碍因素的质性研究[J].循证护理,2024,10(04):693-696.

[101]熊晓世,朱红云,熊华利.重庆市忠县35～75岁居民高血压、高血糖、高血脂共患情况及相关影响因素[J].实用预防医学,2024,31(03):291-295.

[102]张金玲,郭利红,王小洁.孕晚期妊娠期高血压患者血清串珠素、神经纤毛蛋白-1水平与病情、围生结局的关系[J].国际检验医学杂志,2024,45(04):495-499.

[103]权祥菊,杨卓加,张生林,等.妊娠期高血压产妇孕中期Scr、BUN及UA水平与急性肾损伤程度的相关性[J].西部医学,2024,36(02):243-247.

[104]Yusufali A M, Khatib R, Islam S, et al. Prevalence, awareness, treatment and control of hypertension in four Middle East countries[J].Journal of Hypertension,2017,35(07):1457-1464.

[105]Choi K M, Park H S, Han J H, et al. Prevalence of prehypertension and hypertension in a Korean population: Korean National Health and Nutrition Survey 2001[J].Journal of hypertension,2006,24(08):1515-1521.

[106]Kholopkina N A, Gorblianskil lulu, Piktushanskaia I N, et al. Hypertension and prevalence of risk factors among coal industry workers of the Rostov region [J].Med Tr Prom Ekol,2003(01):19-22.

[107]Becarevic M, Salihefendic N, Zildzic M. Effects of Salt Intake on Blood Pressure in Banovici Coal Mine Workers[J].Materia socio-medica,2014,26(06):385.

[108]郑国华,李玉,李红,等.煤矿职工原发性高血压及其影响因素分析[J].中国公共卫生,2004(06):110-111.

[109]Friedman J H. Greedy Function Approximation: A Gradient Boosting Machine.Ann Stat, 2001, 29(05): 1189-1232.

[110]Chen Tianqi, GUEST R IN C. Xgboost:a scalable tree boosting system[C]. Proceedings of the 22Nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016: 785-794.

[111]蒋晋文,刘伟光.XGBoost算法在制造业质量预测中的应用智能计算机与应用,2017,7(6):58-60.

[112]张晨宇,王慧芳,叶晓君.基于XGBoost算法的电力系统暂态稳定评估[J].电力自动化设备,2019,39(03):77-83+89.

[113]廖华龙,曾小茜,李华凤,等.机器学习在疾病预测中的应用[J].生物医学工程研究,2021,40(02):203-209.

[114]黄晓霞,严玉洁,尉敏琦,等.logistic回归、决策树和神经网络在脑卒中高危筛查中的性能比较[J].中国慢性病预防与控制,2016,24(06):412-415.

[115]蒋杏丽,王剑辉.基于决策树算法的疾病分类预测[J].信息与电脑(理论版),2021,33(11):51-53.

[116]Young F A, Singer R M, Foster D. The psychological differentiation of male myopes and nonmyopes[J].Am J Optom Physiol Opt,1975,52(10):679-686.

[117]Cheng D, Schmid K L, Woo G C. Myopia prevalence in Chinese-Canadian children in an optometric practice[J].Optom Vis Sci,2007,84(01):21-32.

[118]Smith E R, Hung L F, Huang J. Protective effects of high ambient lighting on the development of form-deprivation myopia in rhesus monkeys[J].Invest Ophthalmol Vis Sci,2012,53(01):421-428.

[119]Ashby R, Ohlendorf A, Schaeffel F. The effect of ambient illuminance on the development of deprivation myopia in chicks[J].Invest Ophthalmol Vis Sci,2009,50(11):5348-5354.

[120]Rose K A, Morgan I G, Ip J, et al. Outdoor activity reduces the prevalence of myopia in children[J].Ophthalmology,2008,115(08):1279-1285.

[121]陆建明,马云宝,高雷华.缺血性脑卒中患者血浆ET、CGRP和血清MDA、SOD的测定及其意义[J].标记免疫分析与临床.2005,12(01):7-9.

[122]Moldes 0, Sobrino T, Millan M, et al. High serum levels of endothelin-l predict severe cerebral edema in patients with acute ischemic stroke treated with t-PA[J].Stroke,2008,39(07):2006-10.

[123]Ying Z, M J G, K T W, et al. Incidence and risk factors for stroke in American Indians: the Strong Heart Study[J].Circulation,2008,118(15):1577-84.

[124]刘子秀,吕蒙,高丽,等.石化企业职业人群高血压危险因素分析及其患病风险预测[J].工业卫生与职业病,2023,49(02):130-134.

[125]姜田园,张莉,田恬,等.2015-2019年某铁路局职工常见慢性病动态观察分析[J].工业卫生与职业病,2022,48(03):215-218.

[126]齐娜娜,马庆华,张增利,等.苏州市职业人群高血压、糖尿病筛查分析及健康教育策略[J].实用糖尿病杂志,2019,15(04):39-41.

[127]徐振兴,陈晓,吴伟君,等.苏中地区儿童青少年高血压发病情况及相关风险因素分析[J].中西医结合心脑血管病杂志,2023,21(24):4483-4489.

[128]俞美艳,赵雅宁,刘瑶,等.基于贝叶斯网络模型的中老年发生H型高血压的影响因素研究[J].现代预防医学,2024,51(02):335-342.

[129]A G N, B J B. Validating the Framingham Offspring Study equations for predicting incident diabetes mellitus[J].The American journal of managed care,2008,14(09):574-80.