基于聚类分析和主成分分析的伤员受伤程度评估*

doi:10.16265/j.cnki.issn1003-3033.2021.08.026

摘要/Abstract

摘要： 为探究人体4大生命体征(呼吸、体温、脉搏、血压)与伤员生命状态之间的对应关系,首先,采用描述性统计分析收集50例伤员样本;然后,结合聚类分析和主成分分析(PCA),提出一种快速评估伤员受伤严重程度的方法(RAIS),并据此对50位伤员的受伤严重程度作分级;最后,对比分析英国早期预警评分(NEWS)与提出的RAIS法在评估结果方面的差异。研究结果表明:通过伤员的4大生命体征数据分析得到的主成分得分线性函数可以用来表征伤员的受伤严重程度,主成分得分越大,受伤程度越重;由于第一主成分(PC1)的贡献率较大,实际进行伤重程度评估时应以PC1得分作为主要依据。

关键词: 聚类分析, 主成分分析(PCA), 受伤严重程度, 生命体征, 评估方法

Abstract: In order to explore correspondence between four vital signs of human body (respiratory, temperature, pulse, blood pressure) and life status of the wounded, firstly, collected data of 50 samples of the wounded were analyzed using descriptive statistics. Then, a method for rapid assessment of injury severity (RAIS) was proposed based on cluster analysis and PCA, and severity of 50 samples was graded accordingly. Finally, difference in assessment results between National Early Warning Score (NEWS) and RAIS was compared and analyzed. The results show that linear function of principal component score obtained through analysis of four vital signs can be used to assess injury severity of the wounded. The greater this score is, the more severe the injury would be. And since contribution rate of first principal component (PC1) is relatively large, PC1 score should be taken as main basis for actual injury severity assessment.

Key words: cluster analysis, principal component analysis (PCA), severity of injury, vital signs, condition assessment method

中图分类号:

X913.4

陈长坤, 王小勇, 雷鹏. 基于聚类分析和主成分分析的伤员受伤程度评估^*[J]. 中国安全科学学报, 2021, 31(8): 189-196.

CHEN Changkun, WANG Xiaoyong, LEI Peng. Injury severity assessment of wounded based on cluster analysis and PCA[J]. China Safety Science Journal, 2021, 31(8): 189-196.

参考文献

[1] BOUZAT P,BROUX C,AGERON F X,et al. Trauma network for severely injured patients [J]. Annales Francaises Danesthesie Et De Reanimation, 2013, 32(7/8):531-534.
[2] SASSER S M,HUNT R C,FAUL M,et al. Guidelines for field triage of injured patients recommendations of the national expert panel on field triage, 2011 [J]. Morbidity and Mortality Weekly Report, 2012, 61:1-20.
[3] CANNON C M,BRAXTON C C,KLING-SMITH M,et al. Utility of the shock index in predicting mortality in traumatically injured patients [J]. The Journal of Trauma: Injury, Infection, and Critical Care, 2009, 67(6):1 426-1 430.
[4] SARTORIUS D,LE MANACH Y,DAVID,et al. Mechanism, glasgow coma scale, age, and arterial pressure (MGAP): a new simple prehospital triage score to predict mortality in trauma patients [J]. Critical Care Medicine, 2010, 38(3):831-837.
[5] 谢吐秀,吕菁君,魏捷,等. 不同评分系统对急诊自发性非创伤性脑出血患者病情及预后判断的影响[J]. 中国医药导报, 2019, 16(14):109-112.
XIE Tuxiu,LYU Jingjun,WEI Jie,et al. Effects of different scoring systems on condition and prognosis of patients with emergency spontaneous nontraumatic cerebral hemorrhage [J]. China Medical Herald, 2019, 16(14):109-112.
[6] 赵威,黄杨,王玉同,等. 损伤严重程度评分对重度创伤病情评估的意义与预后相关性研究[J]. 临床误诊误治, 2014, 27(1):7-10.
ZHAO Wei,HUANG Yang,WANG Yutong,et al. Correlation study on evaluation significance and prognosis of injury severity score in patients with severe trauma [J]. Clinical Misdiagnosis & Mistherapy, 2014, 27(1):7-10.
[7] 苏永刚. 老年创伤患者身体状况评分法附55例病例应用分析[D]. 北京:北京大学医学部, 2000.
[8] 傅爱凤,郑志惠,王爱琴,等. 疼痛对创伤骨科术后患者生命体征的影响[J].护理学杂志, 2005, 20(20):3-5.
FU Aifeng,ZHENG Zhihui,WANG Aiqin,et al. Effect of pain on the vital signs of postoperative patients with osteopathic trauma [J]. Journal of Nursing Science, 2005, 20(20):3-5.
[9] 邓小明,孙振朕,朱科明. 体温调节的新进展[C]. 2008年中华医学会全国麻醉学术年会论文集, 2008:608-613.
[10] 许云华. 体温调节机制研究进展[J]. 连云港师范高等专科学校学报, 2010, 27(2):96-98.
XU Yunhua. Research progress of thermoregulation mechanisms [J]. Journal of Lianyungang Teachers College, 2010, 27(2):96-98.
[11] 田程涛. 大数据审计下统计分析方法研究[J]. 会计之友, 2018(1):140-145.
[12] 魏娜,刘迪,陈滋顶. 基于系统聚类的普速铁路运营安全分析[J].中国安全科学学报, 2018, 28(增1):88-92.
WEI Na,LIU Di,CHEN Ziding. Safety analysis of general speed railway operation based on system clustering [J]. China Safety Science Journal, 2018, 28(S1):88-92.
[13] 牛志鹏,祁首铭,吴东玲,等. 考虑系统聚类的公路交通事故多发点鉴别研究[J]. 中国安全科学学报, 2018, 28(11):104-109.
NIU Zhipeng,QI Shouming,WU Dongling,et al. Research on identification of black spots for highway based on system clustering method [J]. China Safety Science Journal, 2018, 28(11):104-109.
[14] 林海明,杜子芳. 主成分分析综合评价应该注意的问题[J]. 统计研究, 2013, 30(8):25-31.
LIN Haiming,DU Zifang. Some problems in comprehensive evaluation in the principal component analysis [J]. Statistical Research, 2013, 30(8):25-31.
[15] 赵琳琳,温国锋,邵良杉. 不均衡数据下的采空区煤自燃PCA-AdaBoost预测模型[J]. 中国安全科学学报, 2018, 28(3):74-78.
ZHAO Linlin,WEN Guofeng,SHAO Liangshan. PCA-AdaBoost model for predicting coal spontaneous combustion in caving zone with imbalanced data [J]. China Safety Science Journal, 2018, 28(3):74-78.
[16] 王静宇,李翠平,李仲学. 基于主成分聚类分析的煤层底板突水危险性预测[J]. 中国安全科学学报, 2013, 23(8):120-125.
WANG Jingyu,LI Cuiping,LI Zhongxue. Risk prediction of water inrush from coal floor based on principal component clustering analysis [J]. China Safety Science Journal, 2013, 23(8):120-125.
[17] 阿基业,何骏,孙润彬. 代谢组学数据处理:主成分分析十个要点问题[J]. 药学学报, 2018, 53(6):929-937.
A Jiye,HE Jun,SUN Runbin. Multivariate statistical analysis for metabolomic data: the key points in principal component analysis [J]. Acta Pharmaceutica Sinica, 2018, 53(6):929-937.
[18] 付逸超,黄萍. 五种院前创伤评分方法在急危重症创伤患者识别中的应用效果[J]. 解放军护理杂志, 2015, 32(22):57-58.
FU Yichao,HUANG Ping. Application effect of five pre-hospital trauma scoring methods in emergency triage system [J]. Nursing Journal of Chinese People's Liberation Army, 2015, 32(22):57-58.
[19] 周继红. 创伤评分学简介[J]. 伤害医学:电子版, 2018, 7(4):4-9.
ZHOU Jihong. Introduction of trauma scoreology [J]. Injury Medicine:Electronic Edition, 2018, 7(4):4-9.
[20] 王长远,曹涛,汤辉,等. NEWS评分MEWS评分和APACHEⅡ评分对急诊内科抢救室患者的评估价值[J]. 中国急救医学, 2017, 37(2):123-126.
WANG Changyuan,CAO Tao,TANG Hui,et al. Use of NEWS, MEWS and APACHE Ⅱ score in predicting outcomes in patients of internal emergency room[J]. Chinese Journal of Critical Care Medicine, 2017, 37(2):123-126.
[21] 陈夏,闫莉. 广义线性模型的大样本理论及其研究进展[J]. 陕西师范大学学报:自然科学版, 2016, 44(3):1-6.
CHEN Xia,YAN Li. Progress and large sample theory of generalized linear models [J]. Journal of Shaanxi Normal University :Natural Science Edition, 2016, 44(3):1-6.
[22] 吴卢荣. 基于模糊聚类的马氏链模型在交通事故预测中的应用[J]. 中国安全科学学报, 2007, 17(12):31-36.
WU Lurong. Application of markov chain model to the prediction of traffic accidents based on fuzzy clustering analysis [J]. China Safety Science Journal, 2007, 17(12):31-36.
[23] 张敏,于剑. 基于划分的模糊聚类算法[J]. 软件学报, 2004, 15(6):70-80.
ZHANG Min,YU Jian. Fuzzy partitional clustering algorithms [J]. Journal of Software, 2004, 15(6):70-80.

基于聚类分析和主成分分析的伤员受伤程度评估^*

Injury severity assessment of wounded based on cluster analysis and PCA

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	于光玉, 李慧民. 旧工业建筑改造施工安全影响机制研究[J]. 中国安全科学学报, 2021, 31(7): 120-129.
[2]	张志宇, 朱能. 16个高温高湿环境工况等级划分[J]. 中国安全科学学报, 2020, 30(5): 184-190.
[3]	周华, 张巧玉, 母尧尧, 谭正平, 孙庆, 张道文. 十字路口乘用车与二轮车典型危险场景聚类及推演[J]. 中国安全科学学报, 2020, 30(4): 100-107.
[4]	戴健非, 杨鹏, 诸利一, 郭攀, 贯怀光. 集成PCA和LSTM神经网络的浸润线预测方法[J]. 中国安全科学学报, 2020, 30(3): 94-101.
[5]	温廷新, 靳露露. 基于预处理的IFOA-ELM煤与瓦斯突出预测模型[J]. 中国安全科学学报, 2020, 30(1): 35-41.
[6]	沈书乾, 李伟. 面向储罐声发射检测的信号分析技术研究[J]. 中国安全科学学报, 2019, 29(6): 158-164.
[7]	柴超君, 凌永生, 岳琪, 贾文宝. 维数约简用于BPNN的核事故源项估算方法[J]. 中国安全科学学报, 2018, 28(9): 122-127.
[8]	李红霞, 田辰宁. 基于Cite Space V的煤矿安全管理可视化分析[J]. 中国安全科学学报, 2018, 28(9): 148-153.
[9]	赵琳琳, 温国锋, 邵良杉. 不均衡数据下的采空区煤自燃PCA-AdaBoost预测模型[J]. 中国安全科学学报, 2018, 28(3): 74-78.
[10]	赵琳琳, 温国锋, 邵良杉. 煤层底板突水危险性GSPCA-LSSVM评价模型[J]. 中国安全科学学报, 2018, 28(2): 128-133.
[11]	李书全, 冯雅清, 胡松鹤, 冯领香. 基于社会网络的建筑施工不安全行为关系研究[J]. 中国安全科学学报, 2017, 27(6): 7-12.
[12]	李敬强, 王蓓, 赵宁, 李灏, 王勇. 基于k-means聚类的管制员注意品质特征研究[J]. 中国安全科学学报, 2017, 27(6): 13-18.
[13]	谢晓锋, 李夕兵, 尚雪义, 翁磊, 邓青林. PCA-BP神经网络模型预测导水裂隙带高度[J]. 中国安全科学学报, 2017, 27(3): 100-105.
[14]	张智, 何雨, 黄茜, 何汉平, 鲍洪志. 含硫气井完整性风险等级预测研究^*[J]. 中国安全科学学报, 2017, 27(10): 155-161.
[15]	朱连滨，吴宪，陈辉. 特种设备安全风险评估与控制对策研究[J]. 中国安全科学学报, 2014, 24(1): 149-.