A two-stage prediction filling method with support vector technologies optimized competitively in stages by grey wolf optimizer and particle swarm optimization for missing fasting blood glucose
Restricted accessResearch articleFirst published online December, 2023
A two-stage prediction filling method with support vector technologies optimized competitively in stages by grey wolf optimizer and particle swarm optimization for missing fasting blood glucose
Missing values often affect the data utilization in epidemiological survey. In this study, according to the cut-off point value of the medical diagnostic standard of fasting blood glucose for diabetes, we divide fasting blood glucose test data from the China Health and Nutrition Survey (CHNS) of Shandong province in 2009 into two classes: the normal and the abnormal. Accordingly, for missing fasting blood glucose values, we propose a two-stage prediction filling method with optimized support vector technologies competitively by particle swarm optimization (PSO) or grey wolf optimizer (GWO), which is to first predict the class of the missing data with support vector machine (SVM) in the first stage and then predict the missing value with support vector regression (SVR) within the predicted class in the second stage. In addition, we use the LIBSVM as a gold standard to train both SVM and SVR in different stages. For two kinds of competitive optimizers in stages, in the first stage GWO has the highest classification accuracy (91.1%), and in the second stage PSO has the smallest in-class mean absolute error (0.48). So, GWO-SVM-PSO-SVR is determined as the optimal model and a predicted value with it serves as a fill value. The comparison results of the models in empirical analysis also show that it outdoes any of the other filling models in terms of mean absolute error and mean absolute percentage error. In addition, the sensitivity analysis shows that it presents high tolerance as the sample size changes and has a good stability.
PatricianPA. Multiple imputation for missing data. Res Nurs Health2002; 25: 76–84.
2.
CismondiFFialhoASVieiraSM, et al. Missing data in medical databases: impute, delete or classify?Artif Intell Med2013; 58: 63–72.
3.
VesinAAzoulayERucklyS, et al. Reporting and handling missing values in clinical studies in intensive care units. Intensive Care Med2013; 39: 1396–1404.
4.
WangYWangLYangD, et al. Imputing missing values for genetic interaction data. Methods2014; 67: 269–277.
5.
JerezJMMolinaIGarcía-LaencinaPJ, et al. Missing data imputation using statistical and machine learning methods in a real breast cancer problem. Artif Intell Med2010; 50: 105–115.
6.
ZhaoY. Statistical inference for missing data mechanisms. Stat Med2020; 39: 4325–4333.
7.
RubinDB. Inference and Missing Data. ETS Res Bull Ser1975; 1975: i–19.
8.
JadhavAPramodDRamanathanK. Comparison of performance of data imputation methods for numeric dataset. Appl Artif Intell2019; 33: 913–933.
9.
MiaoWDingPGengZ. Identifiability of normal and normal mixture models with nonignorable missing data. J Am Stat Assoc2016; 111: 1673–1683.
10.
PedersenABMikkelsenEMCronin-FentonD, et al. Missing data and multiple imputation in clinical epidemiological research. Clin Epidemiol2017; 9: 157–166.
11.
MostafaTNarayananMPongiglioneB, et al. Missing at random assumption made more plausible: evidence from the 1958 British birth cohort. J Clin Epidemiol2021; 136: 44–54.
12.
GabrioAHunterRMasonAJ, et al. Joint longitudinal models for dealing with missing at random data in trial-based economic evaluations. Value Health2021; 24: 699–706.
13.
DingXXieJYanX. Model averaging for multiple quantile regression with covariates missing at random. J Stat Comput Simul2021; 91: 2249–2275.
14.
PennyKIAtkinsonI. Approaches for dealing with missing data in health care studies. J Clin Nurs2012; 21: 2722–2729.
15.
van der HeijdenGJDondersARStijnenT, et al. Imputation of missing values is superior to complete case analysis and the missing-indicator method in multivariable diagnostic research: a clinical example. J Clin Epidemiol2006; 59: 1102–1109.
16.
AydilekIBArslanA. A hybrid method for imputation of missing values using optimized fuzzy c-means with support vector regression and a genetic algorithm. Inf Sci2013; 233: 25–35.
17.
ZhangYLiuYC. Data imputation using least squares support vector machines in urban arterial streets. IEEE Signal Process Lett2009; 16: 414–417.
18.
GaoSTangYGQuX. Particle swarm optimization least square support machine based missing data imputation algorithm in wireless sensor network for nuclear power plant’s environmental radiation monitor. In: 2nd International conference on materials and products manufacturing technology (ICMPMT 2012), Guangzhou, China, 22–23 September 2012, Advanced designs and researches for manufacturing, pts 1-3, pp.2137–2144.
19.
FengHHChenGSYinC, et al. A SVM regression based approach to filling in missing values. In: KhoslaRHowlettRJJainLC (eds) Knowledge-based intelligent information and engineering systems, Pt 3, Proceedings. Berlin, Heidelberg: Springer, 2005, pp.581–587.
20.
DoreswamyHGadIManjunathaBR, et al. Performance evaluation of predictive models for missing data imputation in weather data. In: International conference on advances in computing, communications and informatics (ICACCI)Manipal, India, 13–16 September 2017, pp.1327–1334. New York, NY: IEEE.
21.
JiangLYangJQHongXW, et al. Interpolation of missing data of magnetic flux leakage in oil pipeline based on improved supporting vector machine. In: International conference on computer systems, electronics and control (ICCSEC), Dalian, China, 25–27 December 2017, pp.125–127. New York, NY: IEEE.
22.
NagarajanGDhinesh BabuLD. A hybrid of whale optimization and late acceptance hill climbing based imputation to enhance classification performance in electronic health records. J Biomed Inform2019; 94: 103190.
23.
BernardiniMMorettiniMRomeoL, et al. TyG-er: an ensemble regression forest approach for identification of clinical factors related to insulin resistance condition using electronic health records. Comput Biol Med2019; 112: 103358.
24.
WangGDengZChoiKS. Tackling missing data in community health studies using additive LS-SVM classifier. IEEE J Biomed heal2018; 22: 579–587.
25.
SenanEMAl-AdhailehMHAlsaadeFW, et al. Diagnosis of chronic kidney disease using effective classification algorithms and recursive feature elimination techniques. J Healthc Eng2021; 2021: 1004767.
26.
Vapnik VladimirN. The nature of statistical learning theory. New York, NY: Springer, 1995.
27.
ChenKY. Forecasting systems reliability based on support vector regression with genetic algorithms. Reliab Eng Syst Saf2007; 92: 423–432.
28.
MirjaliliSMirjaliliSMLewisA. Grey wolf optimizer. Adv Eng Softw2014; 69: 46–61.
29.
EmaryEZawbaaHMGrosanC, et al. Feature subset selection approach by Gray-Wolf optimization. In: 1st International Afro-European conference for industrial advancement (AECIA) Addis Ababa University, Addis Ababa, Ethiopia, 17–19 November 2014, pp.1–13. Cham: Springer.
30.
BianXQZhangQZhangL, et al. A grey wolf optimizer-based support vector machine for the solubility of aromatic compounds in supercritical carbon dioxide. Chem Eng Res Des2017; 123: 284–294.
31.
ZhouJHuangSWangM, et al. Performance evaluation of hybrid GA–SVM and GWO–SVM models to predict earthquake-induced liquefaction potential of soil: a multi-dataset investigation. Eng Comput2022; 38: 4197–4215.
32.
KennedyJEberhartR. Particle swarm optimization. In: Proceedings of ICNN’95 - International conference on neural networks, 1995.
33.
WangLXWangLNLiGF, et al. Application research of support vector machine based on particle swarm optimization in runoff forecasting. In: International conference on vibration, structural engineering and measurement (ICVSEM2012), Shanghai, China, 19–21 October 2012, pts 1–3, p.2303.
34.
LinSWYingKCChenSC, et al. Particle swarm optimization for parameter determination and feature selection of support vector machines. Expert Syst Appl2008; 35: 1817–1824.
35.
FengYZhangWHanG, et al. A newborn particle swarm optimization algorithm for charging-scheduling algorithm in industrial rechargeable sensor networks. IEEE Sens J2020; 20: 11014–11027.
36.
LiYTengDShiX, et al. Prevalence of diabetes recorded in mainland China using 2018 diagnostic criteria from the American Diabetes Association: national cross sectional study. BMJ2020; 369: m997.
37.
MalikSKhadgawatRAnandS, et al. Non-invasive detection of fasting blood glucose level via electrochemical measurement of saliva. Springerplus2016; 5: 701.
38.
ShenJChenJZhengZ, et al. An innovative artificial intelligence-based app for the diagnosis of gestational diabetes mellitus (GDM-AI): development Study. J Med Internet Res2020; 22: e21573.
39.
KaltehAM. Monthly river flow forecasting using artificial neural network and support vector regression models coupled with wavelet transform. Comput Geosci2013; 54: 1–8.
40.
LeeZJLeeCYYuanXJ, et al. Rainfall forecasting of landslides using support vector regression. In: 2020 3rd IEEE International conference on knowledge innovation and invention (ICKII)2020. New York, NY: IEEE.
41.
JiangTTWangYLiZY, et al. Fault diagnosis of three-phase inverter based on CEEMDAN and GWO-SVM. In: Chinese Automation Congress (CAC), Shanghai, China, 6 August 2020, pp.2362–2368. New York, NY: IEEE.
42.
XiaoJZhuoR. Research on motor rolling bearing fault classification method based on CEEMDAN and GWO-SVM. In: IEEE Advanced information management, communicates, electronic and automation control conference (IMCEC), 2018.
43.
LiaoXZhouGZhangZ, et al. Tool wear state recognition based on GWO–SVM with feature selection of genetic algorithm. Int J Adv Manuf Technol2019; 104: 1051–1063.
44.
FadhillahMFLeeSLeeCW, et al. Application of support vector regression and metaheuristic optimization algorithms for groundwater potential mapping in Gangneung-si, South Korea. Remote Sens2021; 13: 1196.
45.
BehravanIRazaviSM. A novel machine learning method for estimating football players' value in the transfer market. Soft Comput2021; 25: 2499–2511.
