基于大数据老年多重慢性病风险预测模型构建探究

罗瑶; 邓学学; 徐晓茹; 方荣华

doi:10.16766/j.cnki.issn.1674-4152.002216

基于大数据老年多重慢性病风险预测模型构建探究

doi: 10.16766/j.cnki.issn.1674-4152.002216

罗瑶^{1, 2},
邓学学^{1, 2},
徐晓茹^{1, 2},
方荣华^{1, 2, ,}

1.
四川大学华西医院特需医疗中心, 四川成都 610041
2.
四川大学华西护理学院, 四川成都 610041

基金项目:

四川省科学技术厅重点研发项目 2020YFS0151

四川大学护理发展专项基金一般项目 HXHL19021

详细信息

通讯作者:
方荣华，E-mail：fangronghua@wchscu.cn

中图分类号: R592
计量
- 文章访问数: 897
- HTML全文浏览量: 169
- PDF下载量: 199
- 被引次数: 0
出版历程
- 收稿日期: 2020-08-24
- 网络出版日期: 2022-03-02

Research on the establishment of a risk prediction model for multiple chronic diseases in the elderly based on big data

LUO Yao^{1, 2},
DENG Xue-xue^{1, 2},
XU Xiao-ru^{1, 2},
FANG Rong-hua^{1, 2
, ,}

1.
International Medical Center, West China Hospital/West China School of Nursing, Sichuan University, Chengdu, Sichuan 610041, China

摘要

摘要: 人口老龄化已成为一个重大的世界性社会问题。我国65岁以上老年人口超过2.54亿，老年慢性病患病率及共病率高，导致其生活质量下降，致残率、死亡率增高和医疗费用支出的明显增长，给家庭和社会带来沉重的负担。目前基于物联网、大数据、人工智能等新技术已在医疗行业应用，传统的慢性病管理受到挑战。发展智慧医疗是医疗卫生改革的战略需要，也是行业革新的必然趋势，正逐渐成为疾病诊断和风险预测的源动力。开发准确有效的早期诊断及筛检技术，建立完善的疾病普查制度和风险评估、预警体系等是慢性病防治的关键点。国外已开发了乳腺癌、肺癌、糖尿病等疾病风险评估模型，但这些模型并不完全适合中国人群开展疾病风险评估及测量，因此有必要构建符合中国人群自身特点的疾病风险评估模型。如何突破传统的慢性病管理模式，构建精准医疗决策的解决方案成为医疗界共同关注的科学问题。在慢性病管理的实践中，多重慢性病危险因素分级及分层是核心难题。基于大数据云平台，利用机器学习技术进行医疗数据挖掘，形成老年慢性病干预评估的指标评价体系，从而实现创新性的老年慢性病管理模式。该模式将突破老年慢性病管理的难点和瓶颈，促使慢性病的预防/干预关口前移，实现精准管理。
- 慢性病管理 /
- 大数据 /
- 机器学习 /
- 老年人 /
- 风险预测
Abstract: The aging of population has become a major worldwide social problem. The elderly population in China had exceeded 254 million. High morbidity and co-morbidity of chronic diseases in the elder have led to reduce quality of their life, the increase of disability rate, mortality rate and obviously increased medical expenditures, which bring heavy burden to family and society. At present, based on the application of new technologies, such as internet of things, big data and artificial intelligence in the medical industry, traditional chronic disease management will be challenged. The development of smart medicine is the strategic need of medical health reform, as well as the inevitable trend of industry innovation, and gradually becomes the source power of disease diagnosis and risk prediction. Developing accurate and effective early diagnosis and screening technology, establishing perfect disease general survey system, risk assessment and early warning system are the key points to prevent and treat chronic diseases. Foreign countries have developed disease risk assessment models for breast cancer, lung cancer, diabetes and other diseases, but these models are not fully suitable for Chinese population to carry out disease risk assessment and measurement, so it is necessary to build disease risk assessment models that are in line with the characteristics of Chinese population. How to go beyond the traditional chronic disease management system and construct the solution of precision medical decision has become a scientific problem concerned by the medical community. In the process of practicing of chronic disease management, the classification and stratification of multiple chronic disease risk factors are the core problems. Based on a large amount of collected medical data, using machine learning technology to build a prediction model for risk assessment of multiple chronic diseases in the elderly and conducts medical data mining, and to form an index evaluation system for intervention evaluation of chronic diseases in the elderly. This model will break through the difficulties and choke point of chronic disease management, and promote the prevention/intervention of chronic diseases to move forward, and achieve accurate management in the elderly.
- Chronic disease management /
- Big data /
- Machine learning /
- Elderly /
- Disease risk prediction

HTML全文

图 1 老年慢病健康管理大数据云平台架构

下载: 全尺寸图片幻灯片

图 2 模型构建流程

下载: 全尺寸图片幻灯片

参考文献(48)

[1]	张兴文, 祝益民, 刘智玲, 等. 老年慢性病人群健康服务的困境与应对[J]. 中国全科医学, 2016, 19(36): 4434-4437. doi: 10.3969/j.issn.1007-9572.2016.36.006
[2]	World Health Organization. World report on ageing and health. Geneva: World Health Organization (WHO)[M]. https://www.who.int/publications/i/item/9789241565042.2015-9-29/2019-10-15.
[3]	The Lancet. GBD 2017: A fragile world[J]. Lancet, 2018, 392(10159): 1683. doi: 10.1016/S0140-6736(18)32858-7
[4]	史弘毅. 中国人口老龄化带来的健康问题及其相关策略[J]. 临床医药文献电子杂志, 2018, 5(84): 174-175. doi: 10.3877/j.issn.2095-8242.2018.84.147
[5]	武留信, 朱玲, 陈志恒, 等. 中国健康管理与健康产业发展报告(2018)[M]. 北京: 社会科学文献出版社, 2019.
[6]	屈健宁, 王浩, 梅浙川, 等. 互联网+慢性病管理创新模式探索[J]. 重庆医学, 2017, 46(7): 988-989. doi: 10.3969/j.issn.1671-8348.2017.07.040
[7]	吕兰婷, 林筑, 张延. 我国慢性病防控与管理研究的十年综述[J]. 中国卫生事业管理, 2020, 37(1): 32-34, 37. https://www.cnki.com.cn/Article/CJFDTOTAL-ZWSG202001012.htm
[8]	李文玲. 慢性病管理模式现状分析[J]. 医学理论与实践, 2018, 31(22): 3353-3354. https://www.cnki.com.cn/Article/CJFDTOTAL-YXLL201822014.htm
[9]	张延, 田雯, 徐梦霞, 等. 基于ICCC模型的北京市朝阳区慢性病管理模型剖析和启示[J]. 中国初级卫生保健, 2018, 32(6): 27-31. doi: 10.3969/j.issn.1001-568X.2018.06.0011
[10]	唐星月, 张清. 国内外慢性病管理模式的比较研究[J]. 中国全科医学, 2017, 20(9): 1025-1030. doi: 10.3969/j.issn.1007-9572.2017.09.002
[11]	Government account ability office. Health information technology: HHS should assess the effectiveness of its efforts to enhance patient access to, use of electronic health information[N]. US Fed News Service, Including US State News[Washington, D.C. ]. 2017-03-15.
[12]	孟群, 尹新, 陈禹. 互联网+慢病管理的研究与实践[J]. 中国卫生信息管理杂志, 2016, 13(2): 119-123. https://www.cnki.com.cn/Article/CJFDTOTAL-WSGL201602007.htm
[13]	邵红霞, 武俊平, 吴琦. 重视慢病防控与传染病的防治关联[J]. 中国慢性病预防与控制, 2020, 28(8): 561-562. https://www.cnki.com.cn/Article/CJFDTOTAL-ZMXB202008001.htm
[14]	MARTINI N, PICCINNI C, PEDRINI A, et al. COVID-19 and chronic diseases: Current knowledge, future steps and the MaCroScopio project[J]. Recenti Prog Med, 2020, 111(4): 198-201.
[15]	TAL-SINGER R, CRAPO J D. COPD at the time of COVID-19: A COPD foundation perspective[J]. Chronic Obstr Pulm Dis, 2020, 7(2): 73-75.
[16]	KWONG E W, WU H, PANG G K, et al. A prediction model of blood pressure for telemedicine[J]. Health Informatics J, 2018, 24(3): 227-244. doi: 10.1177/1460458216663025
[17]	张宝露, 孙子科技木, 鞠梅, 等. 基于物联网云计算技术的远程医疗在老年慢性病管理中的研究进展[J]. 中国老年学杂志, 2017, 37(11): 2835-2838. doi: 10.3969/j.issn.1005-9202.2017.11.105
[18]	应志野, 李春漾, 曾筱茜, 等. 物联网在慢性肾脏病管理中的应用[J]. 华西医学, 2019, 34(7): 827-831. https://www.cnki.com.cn/Article/CJFDTOTAL-HXYX201907019.htm
[19]	YANG C, KONG G, WANG L, et al. Big data in nephrology: Are we ready for the change?[J]. Nephrology, 2019, 24(11): 1097-1102. doi: 10.1111/nep.13636
[20]	BHARDWAJ N, WODAJO B, SPANO A, et al. The impact of big data on chronic disease management[J]. Health Care Manag, 2018, 37(1): 90-98. doi: 10.1097/HCM.0000000000000194
[21]	WILLEMS S M, ABELN S, FEENSTRA K A, et al. The potential use of big data in oncology[J]. Oral Oncol, 2019, 98: 8-12. doi: 10.1016/j.oraloncology.2019.09.003
[22]	王琛琛, 洪忻, 秦真真, 等. 南京市社区高血压患者自我管理项目效果评估[J]. 中华疾病控制杂志, 2016, 20(10): 975-978. https://www.cnki.com.cn/Article/CJFDTOTAL-JBKZ201610002.htm
[23]	王睆琳, 李景宇, 谭明英. 我国互联网+慢性病管理模式应用前景分析[J]. 中国卫生信息管理杂志, 2020, 17(2): 168-171, 187. https://www.cnki.com.cn/Article/CJFDTOTAL-WSGL202002010.htm
[24]	国务院办公厅. 国务院办公厅关于制定和实施老年人照顾服务项目的意见(国办发〔2017〕52号)[EB/OL]. (2017-06-16)[2020-06-15]. http://www.gov.cn/zhengce/content/2017-06/16/content_5203088.htm.
[25]	国务院. 国务院印发《"十三五"深化医药卫生体制改革规划》[J]. 中国医院院长, 2017(Z1): 10. https://www.cnki.com.cn/Article/CJFDTOTAL-YYYZ2017Z1002.htm
[26]	孙娟, 乔平安. 基于物联网的老年人健康管理系统的设计与应用[J]. 中国新通信, 2018, 20(2): 124-125. doi: 10.3969/j.issn.1673-4866.2018.02.103
[27]	ORNES S. Core Concept: The Internet of Things and the explosion of interconnectivity[J]. Proc Nati Acad of Sci U S A, 2016, 113(40): 11059-11060. doi: 10.1073/pnas.1613921113
[28]	王红. 基于大数据社区养老模式研究与探索[J]. 电脑知识与技术: 学术交流, 2018, 14(9): 249-250. https://www.cnki.com.cn/Article/CJFDTOTAL-DNZS201825108.htm
[29]	李涵, 李慧嘉, 张林姿, 等. 大数据环境下老年人失能失智因素关联[J]. 计算机科学, 2018, 45(S1): 497-501. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJA2018S1107.htm
[30]	National Comprehensive Cancer Network. Clinical Practice Guidelines in Oncology: Lung Cancer Screening(Version 1.2020). https://www.nccn.org/professionals/physician_gls/default.aspx.
[31]	UEMATSU T, NAKASHIMA K, KIKUCHI M, et al. The Japanese breast cancer society clinical practice guidelines for breast cancer screening and diagnosis, 2018 edition[J]. Breast Cancer, 2020, 27(1): 17-24. doi: 10.1007/s12282-019-01025-7
[32]	PENA A S, CURRAN J A, FUERY M, et al. Screening, assessment and management of type 2 diabetes mellitus in children and adolescents: Australasian Paediatric Endocrine Group guidelines[J]. Med J Aust, 2020, 213(1): 30-43. doi: 10.5694/mja2.50666
[33]	王逸, 殷安康, 赵翔宇. 基于互联网平台的慢性病管理研究[J]. 中国农村卫生, 2019, 11(20): 17. doi: 10.3969/j.issn.1674-361X.2019.20.020
[34]	LEBLANC E L, PATNODE C D, WEBBER E M, et al. Behavioral and pharmacotherapy weight loss interventions to prevent obesity-related morbidity and mortality in adults: An updated systematic review for the U.S. preventive services task force[J]. JAMA, 2018, 320(11): 1172-1191. doi: 10.1001/jama.2018.7777
[35]	LEE W, HWANG S H, CHOI H, et al. The association between smoking or passive smoking and cardiovascular diseases using a Bayesian hierarchical model: Based on the 2008-2013 Korea Community Health Survey[J]. Epidemiol Health, 2017, 22;39: e2017026.
[36]	CHARTRANG G, CHENG P M, VORONSOV E, et al. Deep learning: A primer for radiologists[J]. Radio graphics, 2017, 37(7): 2113-2131.
[37]	赵梦蝶, 孙九爱. 机器学习在心血管疾病诊断中的研究进展[J]. 北京生物医学工程, 2020, 39(2): 208-214. doi: 10.3969/j.issn.1002-3208.2020.02.015
[38]	ESTEVA A, KUPREL B, NOVOA R A, et al. Dermatologist-level classification of skin cancer with deep neural networks[J]. Nature, 2017, 542(7639): 115-118. doi: 10.1038/nature21056
[39]	LIU Y, KOHLERGER T, NOROUZI M, et al. Artificial intelligence-based breast cancer nodal metastasis detection: Insights into the black box for pathologists[J]. Arch Pathol Lab Med, 2019, 143(7): 859-868. doi: 10.5858/arpa.2018-0147-OA
[40]	SINGH G, AL'AREF SJ, VAN ASSEN M, et al. Machine learning in cardiac CT: Basic concepts and contemporary data[J]. J Cardiovasc Comput Tomogr, 2018, 12(3): 192-201. doi: 10.1016/j.jcct.2018.04.010
[41]	CHEN M, HAO Y, HWANG K, et al. Disease prediction by machine learning over big data from healthcare communities[J]. IEEE Access, 2017, 5: 8869-8879. doi: 10.1109/ACCESS.2017.2694446
[42]	彭苏元. 基于机器学习方法的CKD4期中医慢病管理疾病预测模型的建立与验证[D]. 广州: 广州中医药大学, 2019.
[43]	帅仁俊, 陈平, 马力, 等. 基于AI的慢病高危管理系统研究与设计[J]. 中国数字医学, 2019, 14(1): 21-23. doi: 10.3969/j.issn.1673-7571.2019.01.006
[44]	赵笑颜, 王嘉阳, 王昀, 等. 大数据在慢病管理中的应用[J]. 解放军医院管理杂志, 2019, 6(1): 1-4. https://www.cnki.com.cn/Article/CJFDTOTAL-JFYG201901005.htm
[45]	黄焯. 基于云计算与医疗大数据的FP-Growth算法的优化研究[D]. 泉州: 华侨大学, 2018.
[46]	朱甜甜. 基于医疗大数据的肿瘤疾病模式分析与研究[D]. 青岛: 青岛科技大学, 2018.
[47]	王伟娜, 杨丹, 童庆. 基于大数据的慢病管理平台的研究[J]. 电脑知识与技术, 2018, 14(5): 27-29. https://www.cnki.com.cn/Article/CJFDTOTAL-DNZS201805011.htm
[48]	姜媛媛, 王晶晶, 张伟宏, 等. "互联网+"在慢性病管理中的应用研究进展[J]. 现代医药卫生, 2019, 35(5): 692-695. doi: 10.3969/j.issn.1009-5519.2019.05.017