Please wait a minute...
Data Analysis and Knowledge Discovery  2019, Vol. 3 Issue (12): 101-112    DOI: 10.11925/infotech.2096-3467.2019.0776
Current Issue | Archive | Adv Search |
Screening Critical Patients with Optimized Classifier Based on Multi Objective Quantum
Jing Li1,Shuxiao Pan1,Xueyan Li2(),Lijing Jia3,Yuzhuo Zhao3
1 School of Economics and Management, Beijing Jiaotong University, Beijing100044, China
2 Management College, Beijing Union University, Beijing100101, China
3 The General Hospital of the People’s Liberation Army, Beijing100853, China
Download: PDF(935 KB)   HTML ( 9
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This study tries to improve the identification of emergency patients’ critical indicators. [Methods] First, we selected a swarm algorithm with multi-objective particle and quantum behaviors. Then, we combined this algorithm with machine learning classifier to propose a new method for screening the needed indicators. Finally, we compared the new method with two existing ones. [Results] The proposed method increased search scope and reduced data dimensionality, which help us obtain indicators of clinical significance. [Limitations] The calculation of indicators’ importance needs to be optimized with recursive method. [Conclusions] The proposed method could improve the recognition rates of critical patients.

Key wordsIndicators Screening      Multi-objective Optimization      Quantum Behavior      Machine Learning     
Received: 01 July 2019      Published: 25 January 2020
ZTFLH:  TP181  
Corresponding Authors: Xueyan Li     E-mail: gongye1632006@163.com

Cite this article:

Jing Li,Shuxiao Pan,Xueyan Li,Lijing Jia,Yuzhuo Zhao. Screening Critical Patients with Optimized Classifier Based on Multi Objective Quantum. Data Analysis and Knowledge Discovery, 2019, 3(12): 101-112.

URL:

http://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2019.0776     OR     http://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2019/V3/I12/101

${{x}_{ik}}$ ${{\mu }_{ik}}$ $F(x_{i}^{R})\succ F(x_{i}^{R*})$ $s({{\alpha }_{ik}},{{\beta }_{ik}})$
${{\alpha }_{ik}}\cdot {{\beta }_{ik}}>0$ ${{\alpha }_{ik}}\cdot {{\beta }_{ik}}<0$ ${{\alpha }_{ik}}=0$ ${{\beta }_{ik}}=0$
0 1 False 1 -1 0 ±1
0 1 True -1 1 ±1 0
1 0 False -1 1 ±1 0
1 0 True 1 -1 0 ±1
编号 名称 编号 名称 编号 名称
1 C-反应蛋白测定 23 45 脂肪酶
2 D-二聚体测定 24 脑利钠肽前体 46 直接胆红素
3 γ-谷氨酰基转移酶 25 尿素 47 中性粒细胞
4 白细胞计数 26 凝血酶时间测定 48 总胆红素
5 丙氨酸氨基转移酶 27 平均红细胞体积 49 总蛋白
6 单核细胞 28 平均红细胞血红蛋白量 50 BEecf
7 淀粉酶 29 平均红细胞血红蛋白浓度 51 Glu
8 二氧化碳 30 平均血小板体积测定 52 HCO3-
9 31 葡萄糖 53 HCO3std
10 国际标准化比值 32 乳酸脱氢酶 54 呼吸
11 红细胞比积测定 33 嗜碱性粒细胞 55 K+
12 红细胞计数 34 嗜酸性粒细胞 56 Lac
13 红细胞体积分布宽度测定CV 35 天冬氨酸氨基转移酶 57 pCO2
14 肌钙蛋白T 36 无机磷 58 pH
15 肌酐 37 血红蛋白测定 59 pO2
16 肌红蛋白定量 38 血浆活化部分凝血活酶时间测定 60 收缩压
17 肌酸激酶 39 血浆凝血酶原活动度测定 61 舒张压
18 40 血浆凝血酶原时间测定 62 SO2c
19 碱性磷酸酶 41 血浆纤维蛋白原测定 63 TCO2
20 淋巴细胞 42 血清白蛋白 64 temp
21 氯化物 43 血清尿酸 65 心率
22 44 血小板计数
参数 符号 取值
粒子群规模 N 20
指标筛选算法迭代次数 - 20
个体非支配解集NDi存储容量 - 50
全局非支配解集NDg存储容量 - 200
粒子更新方式选择概率 ps 0.7
交叉概率 pc 0.7
变异概率 pm 0.05
优化算法 MLP RF KNN
SCMOPSO 33% 13% 25%
SCQBBMOPSO 80% 83% 67%
关键指标 重要性 关键指标 重要性
1.000 肌酐 0.300
肌钙蛋白T 0.847 平均红细胞体积 0.287
HCO3std 0.840 心率 0.287
平均血小板体积测定 0.600 国际标准化比值 0.267
红细胞比积测定 0.500 γ-谷氨酰基转移酶 0.167
BEecf 0.447 pO2 0.153
血浆凝血酶原时间测定 0.440 血小板计数 0.073
淋巴细胞 0.373 直接胆红素 0.047
血清尿酸 0.307 平均红细胞血红蛋白量 0.000
关键指标 临床意义
肌钙蛋白T 肌钙蛋白是心肌损伤坏死的标志物, 对急性心肌梗死的诊断和危险分层有重要的临床意义。肌钙蛋白值升高提示心肌损伤, 可见于急性心肌梗死, 是急救中医生重点关注的指标
BEecf 组织间液的剩余碱含量过低, 表现为酸中毒, 常见于死亡病例
HCO3std 水解大于电离, 呈碱性, 值过低, 表现为酸中毒, 常见于死亡病例
pO2 反映病人呼吸状况, 取值低常见于死亡病例
心率 重要生命体征, 心率极低即与生命危险密切相关
肌酐 表现肾功能的重要指标, 肌酐过高说明肾脏受到严重损伤, 与生命危险密切相关
血清尿酸 诊断肾重度受损的重要指标, 与生命危险密切相关
红细胞比积 临床上红细胞比积过高或过低都常见于死亡病例
血浆凝血酶原时间测定 临床上该指标值过低说明发生了血栓; 过高说明发生严重出血; 均与生命危险密切相关
国际标准比值 临床上该指标是衡量凝血功能的重要指标, 值过高时, 说明出现严重出血, 与生命危险密切相关
关键指标 重要性 关键指标 重要性
心率 0.0515 脂肪酶 0.0258
肌钙蛋白T 0.0414 收缩压 0.0252
舒张压 0.0412 平均红细胞体积 0.0245
Glu 0.0360 肌红蛋白定量 0.0237
呼吸 0.0304 红细胞比积测定 0.0222
氯化物 0.0286 血清尿酸 0.0218
平均血小板体积测定 0.0284 血浆凝血酶原时间测定 0.0213
肌酸激酶 0.0284 红细胞计数 0.0193
γ-谷氨酰基转移酶 0.0262 单核细胞 0.0184
关键指标 重要性 关键指标 重要性
Glu 0.0685 血浆凝血酶原时间测定 0.0047
平均血小板体积测定 0.0477 血浆纤维蛋白原测定 0.0044
Lac 0.0392 脑利钠肽前体 0.0041
肌钙蛋白T 0.0304 中性粒细胞 0.0038
红细胞比积测定 0.0260 红细胞体积分布宽度
测定CV
0.0036
国际标准化比值 0.0244 收缩压 0.0033
乳酸脱氢酶 0.0162 肌红蛋白定量 0.0030
尿素 0.0159 血浆活化部分凝血活酶
时间测定
0.0030
淀粉酶 0.0145 平均红细胞血红蛋白浓度 0.0027
0.0134 0.0027
淋巴细胞 0.0115 血红蛋白测定 0.0025
肌酐 0.0099 pO2 0.0025
HCO3- 0.0099 TCO2 0.0022
心率 0.0079 血清尿酸 0.0019
丙氨酸氨基转移酶 0.0066 嗜酸性粒细胞 0.0019
C-反应蛋白测定 0.0063 单核细胞 0.0016
BEecf 0.0060 血浆凝血酶原活动度测定 0.0005
凝血酶时间测定 0.0060
方法性能 QBBMOPSO-RF 基于Gini系数 递归式特征消除(文献[14])
指标数量 18 18 35


最大值 0.932 0.932 0.945
最小值 0.685 0.644 0.671
平均值 0.820 0.805 0.815
F值 最大值 0.874 0.879 0.912
最小值 0.493 0.477 0.485
平均值 0.718 0.703 0.712
[1] 吴婷婷, 李红 . 院内心搏骤停早期预警评分系统的研究进展[J]. 中华护理杂志, 2016,51(9):1118-1123.
[1] ( Wu Tingting, Li Hong . Research Progress of Early Warning Score Models for In-hospital Cardiac Arrest[J]. Chinese Journal of Nursing, 2016,51(9):1118-1123.)
[2] Jones P, Le Fevre J, Harper A , et al. Effect of the Shorter Stays in Emergency Departments Time Target Policy on Key Indicators of Quality of Care[J]. The New Zealand Medical Journal, 2017,130(1455):35-44.
[3] Coster J, Jacques R, Turner J , et al. PP12 New Indicators for Measuring Patient Survival following Ambulance Service Care[J]. Emergency Medicine Journal, 2017,34(10):e4.
[4] McCoy A, Das R . Reducing Patient Mortality, Length of Stay and Readmissions Through Machine Learning-based Sepsis Prediction in the Emergency Department, Intensive Care Unit and Hospital Floor Unit[J]. BMJ Open Quality, 2017,6(2):e000158.
[5] Gupta A, Liu T, Shepherd S , et al. Using Statistical and Machine Learning Methods to Evaluate the Prognostic Accuracy of SIRS and qSOFA[J]. Healthcare Informatics Research, 2018,24(2):139-147.
[6] Levin S, Toerper M, Hamrock E , et al. Machine-Learning- Based Electronic Triage More Accurately Differentiates Patients with Respect to Clinical Outcomes Compared with the Emergency Severity Index[J]. Annals of Emergency Medicine, 2018,71(5):565-574.
[7] Hohl C M, Badke K, Zhao A , et al. Prospective Validation of Clinical Criteria to Identify Emergency Department Patients at High Risk for Adverse Drug Events[J]. Academic Emergency Medicine, 2018,25(9):1015-1026.
[8] 周志华 . 机器学习[M]. 北京: 清华大学出版社, 2016.
[8] ( Zhou Zhihua. Machine Learning [M]. Beijing: Tsinghua University Press, 2016.)
[9] Palma-Mendoza R J, Rodriguez D, De-Marcos L . Distributed Relief F-based Feature Selection in Spark[J]. Knowledge & Information Systems, 2018,57(1):1-20.
[10] Zhu X Z, Zhu W, Fan X N . Rough Set Methods in Feature Selection via Submodular Function[J]. Soft Computing, 2017,21(13):3699-3711.
[11] Guo S, Guo D, Chen L , et al. A L1-regularized Feature Selection Method for Local Dimension Reduction on Microarray Data[J]. Computational Biology & Chemistry, 2017,67:92-101.
[12] Sylvester E V A, Bentzen P, Bradbury I R , et al. Applications of Random Forest Feature Selection for Fine-scale Genetic Population Assignment[J]. Evolutionary Applications, 2017,11(2):153-165.
[13] 王力波, 王耀力, 常青 . 生物信息学中的特征选择[J]. 太原理工大学学报, 2017,48(3):458-468.
[13] ( Wang Libo, Wang Yaoli, Chang Qing . A Review on Feature Selection for Bioinformatics[J]. Journal of Taiyuan University of Technology, 2017,48(3):458-468.)
[14] 周成, 魏红芹 . 基于随机森林属性约简的众包竞赛参与者识别体系研究[J]. 数据分析与知识发现, 2018,2(7):46-54.
[14] ( Zhou Cheng, Wei Hongqin . Identifying Crowd Participants with Modified Random Forests Algorithm[J]. Data Analysis and Knowledge Discovery, 2018,2(7):46-54.)
[15] Huang X, Zhang Li, Wang B , et al. Feature Clustering Based Support Vector Machine Recursive Feature Elimination for Gene Selection[J]. Applied Intelligence, 2018,48(3):594-607.
[16] Alijla B O, Lim C P, Wong L P , et al. An Ensemble of Intelligent Water Drop Algorithm for Feature Selection Optimization Problem[J]. Applied Soft Computing, 2018,65:531-541.
[17] Sayed G I, Khoriba G, Haggag M H . A Novel Chaotic Salp Swarm Algorithm for Global Optimization and Feature Selection[J]. Applied Intelligence, 2018,48(10):3462-3481.
[18] Zouache D, Ben Abdelaziz F . A Cooperative Swarm Intelligence Algorithm Based on Quantum-inspired and Rough Sets for Feature Selection[J]. Computers & Industrial Engineering, 2018,115:26-36.
[19] 马莹, 王怀晓, 刘贺 , 等. 一种新的自适应量子遗传算法研究[J]. 计算机工程与应用, 2018,54(20):99-103.
[19] ( Ma Ying, Wang Huaixiao, Liu He , et al. Research on Self-adaptive Quantum Genetic Algorithm[J]. Computer Engineering and Applications, 2018,54(20):99-103.)
[20] Rumelhart D E, McClelland J L . The PDP Research Group. Parallel Distributed Processing: Explorations in the Microstructures of Cognition[J]. Language, 1987,63(4):871-886.
[21] Breiman L . Random Forest[J]. Machine Learning, 2001,45(1):5-32.
[22] Cover T M, Hart P E . Nearest Neighbor Pattern Classification[J]. IEEE Transactions on Information Theory, 1967,13(1):21-27.
[23] Zhang Y, Gong D W, Ding Z . A Bare-bones Multi-objective Particle Swarm Optimization Algorithm for Environmental/ Economic Dispatch[J]. Information Sciences, 2012,192(6):213-227.
[1] Ruojia Wang,Lu Zhang,Jimin Wang. Automatic Triage of Online Doctor Services Based on Machine Learning[J]. 数据分析与知识发现, 2019, 3(9): 88-97.
[2] Gang Li,Huayang Zhou,Jin Mao,Sijing Chen. Classifying Social Media Users with Machine Learning[J]. 数据分析与知识发现, 2019, 3(8): 1-9.
[3] Jiahui Hu,An Fang,Wanqing Zhao,Chenliu Yang,Huiling Ren. Annotating Chinese E-Medical Record for Knowledge Discovery[J]. 数据分析与知识发现, 2019, 3(7): 123-132.
[4] Jinzhu Zhang,Yiming Hu. Extracting Titles from Scientific References in Patents with Fusion of Representation Learning and Machine Learning[J]. 数据分析与知识发现, 2019, 3(5): 68-76.
[5] Zhiqiang Liu,Yuncheng Du,Shuicai Shi. Extraction of Key Information in Web News Based on Improved Hidden Markov Model[J]. 数据分析与知识发现, 2019, 3(3): 120-128.
[6] Hongxia Xu,Chunwang Li. Review of Knowledge Extraction of Scientific Literature[J]. 数据分析与知识发现, 2019, 3(3): 14-24.
[7] Zixuan Zhang,Hao Wang,Liping Zhu,Sanhong eng. Identifying Risks of HS Codes by China Customs[J]. 数据分析与知识发现, 2019, 3(1): 72-84.
[8] Lina Liu,Jiayin Qi,Zhenping Zhang,Dan Zeng. Analyzing Impacts of Brand Reputation on Online Sales Based on Massive Commodity Reviews and Brand[J]. 数据分析与知识发现, 2018, 2(9): 10-21.
[9] Longjia Jia,Bangzuo Zhang. Classifying Topics of Internet Public Opinion from College Students: Case Study of Sina Weibo[J]. 数据分析与知识发现, 2018, 2(7): 55-62.
[10] Wei Lu,Mengqi Luo,Heng Ding,Xin Li. Image Annotation Tags by Deep Learning and Real Users: A Comparative Study[J]. 数据分析与知识发现, 2018, 2(5): 1-10.
[11] Li Wang,Lixue Zou,Xiwen Liu. Visualizing Document Correlation Based on LDA Model[J]. 数据分析与知识发现, 2018, 2(3): 98-106.
[12] Xinyue Fan,Lei Cui. Predicting Antineoplastic Drug Targets Based on Network Properties[J]. 数据分析与知识发现, 2018, 2(12): 98-108.
[13] Yang Zhao,Xini Yuan,Yawen Chen,Liqiang Wu. Predicting Conversion Rate of APP Advertising with Machine Learning[J]. 数据分析与知识发现, 2018, 2(11): 2-9.
[14] Xin Wang,Wen’gang Feng. Review of Techniques Detecting Online Extremism and Radicalization[J]. 数据分析与知识发现, 2018, 2(10): 2-8.
[15] Zhongyi Hu,Chaoqun Wang,Jiang Wu. Identifying Phishing Websites with Multiple Online Data Sources[J]. 数据分析与知识发现, 2017, 1(6): 47-55.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938   E-mail:jishu@mail.las.ac.cn