Analysis in performance of GM(1, 1) model in predicting blood glucose at different ranges

LU Xiangyue; WANG Yannian; LI Quanzhong

doi:10.7619/jcmp.20210757

Journal of Clinical Medicine in Practice > 2021 > 25(9): 23-28, 36. > DOI: 10.7619/jcmp.20210757

LU Xiangyue, WANG Yannian, LI Quanzhong. Analysis in performance of GM(1, 1) model in predicting blood glucose at different ranges[J]. Journal of Clinical Medicine in Practice, 2021, 25(9): 23-28, 36. DOI: 10.7619/jcmp.20210757

Citation:

PDF (5807 KB)

Analysis in performance of GM(1, 1) model in predicting blood glucose at different ranges

1.
Department of Endocrinology, Zhengzhou University People's Hospital, Henan Provincial People's Hospital, Zhengzhou, Henan, 450003
2.
School of Information Engineering, Zhengzhou University, Zhengzhou, Henan, 450001

More Information

Received Date: February 23, 2021
Available Online: May 20, 2021
Published Date: May 14, 2021

Graphical Abstract

Abstract

Abstract

Objective To evaluate performance of GM (1, 1) model in predicting blood glucose, and the predictive ability of this model for prediction of different blood glucose ranges.
Methods Seventy-two-hour blood glucose sequence of fifty patients with T2DM was selected as study objects. GM (1, 1) model was established based on the metabolic algorithm to predict blood glucose levels after 5, 15 and 30 min. Fifty patients were randomly divided into control group(n=20) and experimental group(n=30). The blood glucose range(ranging from a to b) when the prediction error was low in the control group was obtained. According to the blood glucose range of the control group, the data of the experimental group was divided into group A(< a), group B(a to b), and group C(>b). Analysis was performed by Pearson correlation analysis and nonparametric test.
Results The blood glucose ranges for prediction duration of 5 min, 15 min and 30 min in the control group were 3.4 to 11.5 mmol/L, 3.3 to 11.4 mmol/L and 3.2 to 11.4 mmol/L, respectively. Correlation analysis showed that group B at differed prediction durations had the best predictive fit (P < 0.01). Nonparametric tests indicated that there was a statistical difference in prediction error between groups at the same prediction duration (P < 0.01), and the group A had the minimum error, followed by group B, and group C had the maximum error.
Conclusion GM (1, 1) model has better predictive efficacy at blood glucose range of 3.4 to 11.4 mmol/L.
- GM(1, 1) model,
- type 2 diabetes mellitus,
- prediction of blood glucose,
- range of blood glucose

FullText(HTML)

References (20)

References

[1]	AKBAS E M, DEMIRTAS L, OZCICEK A, et al. Association of epicardial adipose tissue, neutrophil-to-lymphocyte ratio and platelet-to-lymphocyte ratio with diabetic nephropathy[J]. Int J Clin Exp Med, 2014, 7(7): 1794-1801. http://europepmc.org/abstract/MED/25126182
[2]	中华医学会糖尿病学分会. 中国2型糖尿病防治指南(2017年版)[J]. 中国实用内科杂志, 2018, 38(4): 292-344. https://www.cnki.com.cn/Article/CJFDTOTAL-SYNK201804009.htm
[3]	Seuring T, Archangelidi O, Suhrcke M. The economic costs of type 2 diabetes: a global systematic review[J]. Pharmacoeconomics, 2015, 33(8): 811-831. doi: 10.1007/s40273-015-0268-9
[4]	SAITI K, MACAŠ M, LHOTSKÁ L, et al. Ensemble methods in combination with compartment models for blood glucose level prediction in type 1 diabetes mellitus[J]. Comput Methods Programs Biomed, 2020, 196: 105628. doi: 10.1016/j.cmpb.2020.105628
[5]	HE J, WANG Y. Blood glucose concentration prediction based on kernel canonical correlation analysis with particle swarm optimization and error compensation[J]. Comput Methods Programs Biomed, 2020, 196: 105574. doi: 10.1016/j.cmpb.2020.105574
[6]	都承华, 龚谊承. 基于支持向量回归和核岭回归对血糖值预测的对比分析[J]. 数学的实践与认识, 2020, 50(6): 132-139. https://www.cnki.com.cn/Article/CJFDTOTAL-SSJS202006013.htm
[7]	王延年, 郭占丽, 袁进磊, 等. 基于自适应噪声完整聚合经验模态分解-极限学习机的短期血糖预测[J]. 中国生物医学工程学报, 2017, 36(6): 702-710. doi: 10.3969/j.issn.0258-8021.2017.06.010
[8]	邓聚龙. 灰色系统理论教程[M]. 武汉: 华中理工大学出版社, 1990: 122-123.
[9]	覃伟, 高敏, 沈莹, 等. 基于机器学习算法的2型糖尿病患者3个月血糖预测[J]. 中华疾病控制杂志, 2019, 23(11): 1313-1317. https://www.cnki.com.cn/Article/CJFDTOTAL-JBKZ201911003.htm
[10]	WANG Y, WEI F, SUN C, et al. The Research of Improved Grey GM(1, 1) Model to Predict the Postprandial Glucose in Type 2 Diabetes[J]. Biomed Res Int, 2016, 2016: 6837052. http://europepmc.org/articles/PMC4893588/
[11]	龚谊承, 都承华, 张艳娜, 等. 基于主成分和GBDT对血糖值的预测[J]. 数学的实践与认识, 2019, 49(14): 116-122. https://www.cnki.com.cn/Article/CJFDTOTAL-SSJS201914013.htm
[12]	VOELKER R. "artificial pancreas" is approved[J]. JAMA, 2016, 316(19): 1957. http://www.ncbi.nlm.nih.gov/pubmed/27838705
[13]	KOVATCHEV B, CHENG P, ANDERSON S M, et al. Feasibility of long-term closed-loop control: a multicenter 6-month trial of 24/7 automated insulin delivery[J]. Diabetes Technol Ther, 2017, 19(1): 18-24. doi: 10.1089/dia.2016.0333
[14]	SCHVTZ-FUHRMANN I, SCHVTZ A K, EICHNER M, et al. Two subsequent pregnancies in a woman with type 1 diabetes: artificial pancreas was a gamechanger[J]. J Diabetes Sci Technol, 2020, 14(5): 972-973. doi: 10.1177/1932296820906219
[15]	THABIT H, HARTNELL S, ALLEN J M, et al. Closed-loop insulin delivery in inpatients with type 2 diabetes: a randomised, parallel-group trial[J]. Lancet Diabetes Endocrinol, 2017, 5(2): 117-124. doi: 10.1016/S2213-8587(16)30280-7
[16]	QUINTAL A, MESSIER V, RABASA-LHORET R, et al. A critical review and analysis of ethical issues associated with the artificial pancreas[J]. Diabetes Metab, 2019, 45(1): 1-10. doi: 10.1016/j.diabet.2018.04.003
[17]	RAMLI R, REDDY M, OLIVER N. Artificial pancreas: current progress and future outlook in the treatment of type 1 diabetes[J]. Drugs, 2019, 79(10): 1089-1101. doi: 10.1007/s40265-019-01149-2
[18]	BLAUW H, KEITH-HYNES P, KOOPS R, et al. A review of safety and design requirements of the artificial pancreas[J]. Ann Biomed Eng, 2016, 44(11): 3158-3172. doi: 10.1007/s10439-016-1679-2
[19]	QIN Y F, XIAO J, CHEN X D. Physiological model and chemical modeling strategy for blood glucose prediction[J]. Chemical Industry and Engineering Progress, 2019, 38(1): 545-555.
[20]	OVIEDO S, VEHÍ J, CALM R, et al. A review of personalized blood glucose prediction strategies for T1DM patients[J]. Int J Numer Meth Biomed Engng, 2017, 33(6): e2833. doi: 10.1002/cnm.2833

[1]	SHAO Zhongxin, LI Shiying. Effect of propofol regulating macrophage polarization on airway inflammatory response and Toll-like receptor 4-NOD-like receptor protein 3 pathway in mice with bronchial asthma[J]. Journal of Clinical Medicine in Practice, 2025, 29(6): 13-19. DOI: 10.7619/jcmp.20245587
[2]	YU Jingjing, HU Meng, Xierenguli ALIMU, ZHANG Man, QU Jianhua. Experimental study on treatment of relapsed and refractory acute myeloid leukemia with DNA methyltransferase 1 inhibitor combined with extracellular signal-regulated kinase 1, homeodomain-interacting protein kinase 2, and glycogen synthase kinase 3β inhibitors[J]. Journal of Clinical Medicine in Practice, 2025, 29(5): 26-30, 35. DOI: 10.7619/jcmp.20242914
[3]	LIU Xinyan, DONG Liyun, ZHOU Peipei, CHEN Yongxue, WANG Xinbo, SUN Yan. Esketamine improves hypoxic-ischemic myocardial injury in neonatal rats by glycogen synthase kinase-3β/NOD-like receptor thermal protein domain-containing protein 3 pathway[J]. Journal of Clinical Medicine in Practice, 2024, 28(15): 19-25. DOI: 10.7619/jcmp.20240407
[4]	LAN Youling, LI Tianfa, ZHAN Yatong, CHEN Yan'e, GUAN Fuqing, YANG Yang. Effect of adjuvant therapy of Shenfu Injection on NOD-like receptor protein 3/cysteine-aspartic acid-specific protease 1 mediated pyroptosis signaling pathway and inflammatory factor levels in rats with acute myocardial infarction[J]. Journal of Clinical Medicine in Practice, 2024, 28(15): 3-8, 13. DOI: 10.7619/jcmp.20240909
[5]	WU Nan, ZHENG Miaomiao, WANG Xinzhe, ZHU Xiang, TANG Hao. Research progress of protein arginine methyltransferase regulating bone formation and bone healing[J]. Journal of Clinical Medicine in Practice, 2024, 28(5): 126-129, 134. DOI: 10.7619/jcmp.20233520
[6]	Qilimuge, LI Xuelian, JI Qiang. Research progress on relationship between receptor tyrosine kinase-like orphan receptor 1 and signaling pathway of tumor cells[J]. Journal of Clinical Medicine in Practice, 2023, 27(17): 133-139. DOI: 10.7619/jcmp.20231087
[7]	NI Ming, LIU Tingting, WANG Jun, ZOU Xuehong, ZHOU Hongyu, WANG Yan, YU Guimei. Detection of methylation status of death-related protein kinase 1, KLF4 and O⁶-methylguanine-DNA methyltransferase and their relationships with humanpapillomavirus type 16[J]. Journal of Clinical Medicine in Practice, 2022, 26(8): 117-121. DOI: 10.7619/jcmp.20214540
[8]	XU Dongrui, WANG Xiaolong, MA Wenchao, LIU Tongxiang, DONG Yuanbao, YIN Lijuan. Effect of nucleotide binding oligomerization domain-like receptor protein 3 inflammasome on in-stent restenosis after coronary stent implantation[J]. Journal of Clinical Medicine in Practice, 2021, 25(19): 16-19. DOI: 10.7619/jcmp.20211930
[9]	ZHANG Qi, WANG Zhiqiang, CAI Huarong, JIANG Yuequan. Role of protein arginine methyltransferase 5 in methylthioadenosine phosphorylase deficient malignant pleural mesothelioma[J]. Journal of Clinical Medicine in Practice, 2021, 25(17): 82-87. DOI: 10.7619/jcmp.20212725
[10]	XU Weidong, GU Xiao. Correlation between protein arginine methyltransferase 5 and occurrence, development of bladder cancer[J]. Journal of Clinical Medicine in Practice, 2019, (4): 23-29,33. DOI: 10.7619/jcmp.201904008

Cited By

Cited by

Periodical cited type(7)

1.	郭振，胡晓萌，曹海玮，时玉春，黄旭，张冲. 超声联合螺旋CT对小儿髋关节发育异常的诊断价值. 临床医学. 2024(01): 90-92 .
2.	李凯，夏伊明，单新平，吴鹏，阿尔帕提·努力买买提，石岩. 伊犁地区婴幼儿发育性髋关节发育不良的危险因素分析. 公共卫生与预防医学. 2024(03): 157-160 .
3.	杨茜，石影，张永花，郑华，张婧洁，刘艳敏. 婴儿发育性髋关节发育不良超声筛查情况及影响因素分析. 兰州大学学报(医学版). 2024(07): 37-42 .
4.	蔡如意，陈敏. 早产儿髋关节发育不良的临床特征、超声表现及相关因素分析. 转化医学杂志. 2024(05): 696-701 .
5.	何花，王鑫，林海庆，桂冬冬，孙泉，许子旻. 高频超声在婴幼儿髋关节发育异常早期诊断中的价值分析. 现代诊断与治疗. 2023(08): 1231-1232+1238 .
6.	弓建志. 临夏0～2岁婴幼儿发育性髋关节发育不良筛查暨影响因素分析. 智慧健康. 2023(26): 52-55 .
7.	陈浩，孟晓涛，李晓婷，李敏，李洪涛，任超，刘春燕. 包头地区婴幼儿发育性髋关节发育不良的超声动静态法筛查结果分析. 航空航天医学杂志. 2022(11): 1308-1311 .

Other cited types(1)

Get Citation

PDF

XML

Article views (395) PDF downloads (30) Cited by(8)

Turn off MathJax

Article Contents

Abstract

References

Analysis in performance of GM(1, 1) model in predicting blood glucose at different ranges