Building Childhood Asthma Prediction Model with Artificial Neural Network and BRFSS Database
Ma Xiaoyu1,2, Zhang Han1, Zhao Yuhong1,2()
1Department of Medical Informatics, China Medical University, Shenyang 110122, China 2Department of Clinical Epidemiology, Shengjing Hospital of China Medical University, Shenyang 110004, China
[Objective] This study tries to identify high-correlated variables with significant impacts on childhood asthma, aiming to establish predictive model without invasive clinical indicators. [Methods] First, we used statistical methods to identify the needed variables from the BRFSS database. Second, we employed the back propagation artificial neural network to build the prediction model. Finally, we compared the performance of the new model with three other methods: the traditional logistic regression, decision tree and support vector machine. [Results] The identified variables included history of asthma, correct use of inhaler, age of diagnosis, and family income. The proposed model has an accuracy of 0.723, a sensitivity of 0.697 and a specificity of 0.680. [Limitations] The BRFSS database has lots of missing data, which may influence the prediction accuracy. [Conclusions] The self-adaptable BP artificial neural network, could help us establish better prediction models for childhood asthma.
马晓宇, 张晗, 赵玉虹. 基于BRFSS数据库应用人工神经网络构建儿童哮喘预测模型*[J]. 数据分析与知识发现, 2018, 2(8): 10-15.
Ma Xiaoyu,Zhang Han,Zhao Yuhong. Building Childhood Asthma Prediction Model with Artificial Neural Network and BRFSS Database. Data Analysis and Knowledge Discovery, 2018, 2(8): 10-15.
Valet R S, Gebretsadik T, Carroll K N, et al.High Asthma Prevalence and Increased Morbidity Among Rural Children in a Medicaid Cohort[J]. Annals of Allergy Asthma & Immunology, 2011, 106(6): 467-473.
[2]
GINA Global Strategy for Asthma Management and Prevention updated 2017[R/OL]. [2017-12-25]. .
[3]
Caudri D, Wijga A, Schipper C M A, et al. Predicting the Long-Term Prognosis of Children with Symptoms Suggestive of Asthma at Preschool Age[J]. The Journal of Allergy Clinical Immunology, 2009, 124(5): 903-910.
doi: 10.1016/j.jaci.2009.06.045
[4]
Smit H A, Pinart M, Antó J M, et al.Childhood Asthma Prediction Models: A Systematic Review[J]. Lancet Respiratory Medicine, 2015, 3(12): 973-984.
doi: 10.1016/S2213-2600(15)00428-2
pmid: 26597131
[5]
Behavioral Risk Factor Surveillance System [DB/OL]. [2017-11-28]..
[6]
Castro-Rodríguez J A, Holberg C J, Wright A L, et al. A Clinical Index to Define Risk of Asthma in Young Children with Recurrent Wheezing[J]. American Journal of Respiratory and Critical Care Medicine, 2000, 162(4): 1403-1406.
doi: 10.1164/ajrccm.162.4.9912111
pmid: 11029352
[7]
Brand P L.The Asthma Predictive Index: Not a Useful Tool in Clinical Practice[J]. The Journal of Allergy Clinical Immunology, 2011, 127(1): 293-294.
doi: 10.1016/j.jaci.2010.10.012
pmid: 21075441
[8]
Van Der Mark L B, Van Wonderen K E, Mohrs J, et al. Predicting Asthma in Preschool Children at High Risk Presenting in Primary Care: Development of a Clinical Asthma Prediction Score[J]. Primary Care Respiratory Journal, 2014, 23(1): 52-59.
doi: 10.4104/pcrj.2014.00003
[9]
Chatzimichail E, Paraskakis E, Rigas A.An Evolutionary Two-Objective Genetic Algorithm for Asthma Prediction[C]// Proceedings of 2013 UKSim 15th International Conference on Computer Modelling and Simulation, Cambridge, United Kingdom. US: IEEE, 2013.
(Liu Miaomiao, Wang Da, Ren Wanhui, et al.Relationship Between Pet Keeping and Childhood Asthma in Shenyang City[J]. Chinese Journal of Public Health, 2012, 28(11): 1420-1430.)
doi: 10.11847/zgggws2012-28-11-11
(Zhou Yanfeng.Risk Factors of Bronchial Asthma and Related Nursing Strategies[J]. Contemporary Medicine, 2011, 17(27): 133-134.)
doi: 10.3969/j.issn.1009-4393.2011.27.094
[12]
Finkelstein J, Jeong I C.Machine Learning Approaches to Personalize Early Prediction of Asthma Exacerbations[J]. Annals of the New York Academy of Sciences, 2017, 1387(1): 153-165.
doi: 10.1111/nyas.13218
pmid: 27627195
[13]
Kim W, Kim K S, Lee J E, et al.Development of Novel Breast Cancer Recurrence Prediction Model Using Support Vector Machine[J]. Journal of Breast Cancer, 2012, 15(2): 230-238.
doi: 10.4048/jbc.2012.15.2.230
pmid: 22807942
(Mu Dongmei, Ren Ke.Discovering Knowledge from Electronic Medical Records with Three Data Mining Algorithms[J]. New Technology of Library and Information Service, 2016(6): 102-109.)
(Li Lixia, Zhang Min, Gao Yanhui, et al.Application of Artificial Neural Network in Medical Research[J]. Journal of Mathematical Medicine, 2009, 22(1): 80-82.)
[16]
Bisgaard H, Szefler S.Prevalence of Asthma-Like Symptoms in Young Children[J]. Pediatric Pulmonology, 2007, 42(8): 723-728.
doi: 10.1002/ppul.v42:8
[17]
Savenije O E, Granell R, Caudri D, et al.Comparison of Childhood Wheezing Phenotypes in 2 Birth Cohorts: ALSPAC and PIAMA[J]. The Journal of Allergy Clinical Immunology, 2011, 127(6): 1505-1512.
doi: 10.1016/j.jaci.2011.02.002
pmid: 21411131
[18]
Caudri D, Wijga A, Maarten C, et al.Predicting the Long-Term Prognosis of Children with Symptoms Suggestive of Asthma at Preschool Age[J]. The Journal of Allergy Clinical Immunology, 2009, 124(5): 903-910.
doi: 10.1016/j.jaci.2009.06.045
[19]
袁梅宇. 数据挖掘与机器学习—WEKA应用技术与实践[M]. 北京: 清华大学出版社, 2014.
[19]
(Yuan Meiyu.Data Mining and Machine Learning — WEKA Application Technology and Practice[M]. Beijing: Tsinghua University Press, 2014.)
[20]
Kumar Y, Sahoo G.Prediction of Different Types of Liver Diseases Using Rule Based Classification Model[J]. Technology & Health Care, 2013, 21(5): 417-432.
doi: 10.3233/THC-130742
pmid: 23963359
[21]
方积乾. 现代医学统计学[M]. 北京: 人民卫生出版社, 2002: 708-718.
[21]
(Fang Jiqian.Advanced Medical Statistics[M]. Beijing: People’s Medical Publishing House, 2002: 708-718.)
[22]
Rumelhart D E, Hinton G E, Williams G J, et al.Learning Internal Representation by Back-Propagation Errors[J]. Nature, 1986, 323: 533-536.
doi: 10.1038/323533a0