Please wait a minute...
J Zhejiang Univ (Med Sci)  2022, Vol. 51 Issue (1): 1-9    DOI: 10.3724/zdxbyxb-2021-0227
    
Research on prediction of daily admissions of respiratory diseases with comorbid diabetes in Beijing based on long short-term memory recurrent neural network
ZHU Qian1,ZHANG Meng1,HU Yaoyu1,XU Xiaolin2,3,TAO Lixin1,4,ZHANG Jie1,4,LUO Yanxia1,4,GUO Xiuhua1,4,LIU Xiangtong1,4,*()
1. School of Public Health, Capital Medical University, Beijing 100069, China;
2. School of Public Health, Zhejiang University School of Medicine, Hangzhou 310058, China;
3. The University of Queensland, Brisbane 4006, Australia;
4. Beijing Municipal Key Laboratory of Clinical Epidemiology, Beijing 100069, China
Download: HTML( 15 )   PDF(4907KB)
Export: BibTeX | EndNote (RIS)      

Abstract  

Objective: To compare the performance of generalized additive model (GAM) and long short-term memory recurrent neural network (LSTM-RNN) on the prediction of daily admissions of respiratory diseases with comorbid diabetes. Methods: Daily data on air pollutants, meteorological factors and hospital admissions for respiratory diseases from Jan 1st, 2014 to Dec 31st, 2019 in Beijing were collected. LSTM-RNN was used to predict the daily admissions of respiratory diseases with comorbid diabetes, and the results were compared with those of GAM. The evaluation indexes were calculated by five-fold cross validation. Results: Compared with the GAM, the prediction errors of LSTM-RNN were significantly lower [root mean squared error (RMSE): 21.21±3.30 vs. 46.13±7.60, P<0.01; mean absolute error (MAE): 14.64±1.99 vs. 36.08±6.20,P<0.01], and theR2 value was significantly higher (0.79±0.06 vs. 0.57±0.12, P<0.01). In gender stratification, RMSE, MAE andR2 values of LSTM-RNN were better than those of GAM in predicting female admission (all P<0.05), but there were no significant difference in predicting male admission between two models (allP>0.05). In seasonal stratification, RMSE and MAE of LSTM-RNN were lower than those of GAM in predicting warm season admission (allP<0.05), but there was no significant difference inR2 value (P>0.05). There were no significant difference in RMSE, MAE andR2 between the two models in predicting cold season admission (all P>0.05). In the stratification of functional areas, the RMSE, MAE andR2 values of LSTM-RNN were better than those of GAM in predicting core area admission (all P<0.05).Conclusion: LSTM-RNN has lower prediction errors and better fitting than the GAM, which can provide scientific basis for precise allocation of medical resources in polluted weather in advance.



Key wordsLong short-term memory recurrent neural network      Generalized additive model      Respiratory disease      Diabetes mellitus      Daily admission      Prediction     
Received: 06 August 2021      Published: 17 May 2022
CLC:  R197.5  
Corresponding Authors: LIU Xiangtong     E-mail: xiangtongl@ccmu.edu.cn
Cite this article:

ZHU Qian,ZHANG Meng,HU Yaoyu,XU Xiaolin,TAO Lixin,ZHANG Jie,LUO Yanxia,GUO Xiuhua,LIU Xiangtong. Research on prediction of daily admissions of respiratory diseases with comorbid diabetes in Beijing based on long short-term memory recurrent neural network. J Zhejiang Univ (Med Sci), 2022, 51(1): 1-9.

URL:

https://www.zjujournals.com/med/10.3724/zdxbyxb-2021-0227     OR     https://www.zjujournals.com/med/Y2022/V51/I1/1


基于长短时记忆循环神经网络的北京市糖尿病合并呼吸系统疾病患者入院预测研究

目的:比较广义相加模型(GAM)和长短时记忆循环神经网络(LSTM-RNN)对糖尿病合并呼吸系统疾病患者入院频数的预测效果。方法:收集2014年1月1日至2019年12月31日北京市大气污染物、气象因素和呼吸系统疾病入院数据,基于LSTM-RNN预测糖尿病合并呼吸系统疾病患者入院频数并与GAM对比,模型评价采用五折交叉验证法。结果:与GAM相比,LSTM-RNN具有较低的预测误差[均方根误差(RMSE)分别为21.21±3.30和46.13±7.60,P<0.01;平均绝对误差(MAE)分别为14.64±1.99和36.08±6.20,P<0.01]和较高的拟合优度(R2值分别为0.79±0.06和0.57±0.12,P<0.01)。在性别分层中,预测女性入院频数时,LSTM-RNN三项指标均优于GAM(均P<0.05);预测男性入院频数时,两模型误差评价指标差异无统计学意义(均P>0.05)。在季节分层中,预测温暖季节的入院频数时,LSTM-RNN的RMSE和MAE均低于GAM(均P<0.05),R2值差异无统计学意义(P>0.05);预测寒冷季节入院频数时,两种模型的RMSE、MAE和R2值差异均无统计学意义(均P>0.05)。在功能区分层中,预测首都功能核心区入院频数时,LSTM-RNN的RMSE、MAE和R2值均优于GAM(均P<0.05)。结论:LSTM-RNN预测误差较小,拟合程度优,可作为污染天气提前精准配置医疗资源的预测手段。


关键词: 长短时记忆循环神经网络,  广义相加模型,  呼吸系统疾病,  糖尿病,  日入院频数,  预测 

序号

变量名称

变量种类

单位

赋值

1

月份

特征变量

2

日期

特征变量

3

节假日

特征变量

d

0∶非节假日

1∶节假日

4

星期

特征变量

d

5

既往入院频数

特征变量

例次/d

6

PM2.5

特征变量

μg/m3

7

PM10

特征变量

μg/m3

8

二氧化硫

特征变量

μg/m3

9

二氧化氮

特征变量

μg/m3

10

臭氧

特征变量

μg/m3

11

一氧化碳

特征变量

mg/m3

12

空气质量指数

特征变量

13

温度

特征变量

14

比湿

特征变量

g/kg

15

气压

特征变量

hPa

16

风速

特征变量

m/s

17

预测入院频数

目标变量

例次/d

Table 1 Input and output data in long short-term memory recurrent neural network model
Figure 1 Spatial distribution of air pollutants in 16 administrative regions of Beijing during 2014 and 2019

类别

总入院频数

每日入院频数

患者性别男性

146? 958(58.40)

71(37,89)

女性

104? 697(41.60)

48(29,63)

患者年龄≤60岁

34? 281(13.62)

16(9,21)

>60岁

217 ?374(86.38)

104(57,132)

季节寒冷

134 ?665(53.51)

131(69,164)

温暖

116 ?990(46.49)

114(62,141)

功能区首都功能核心区

36 ?795(14.62)

18(7,24)

城市功能拓展区

114? 049(45.32)

55(26,71)

城市发展新区

67 ?393(26.78)

30(21,39)

生态涵养区

33? 418(13.28)

14(10,20)

合计

251? 655(100.00)

121(65,151)

Table 2 Distribution characteristics of total and daily hospital admission for respiratory diseases with comorbid diabetes in Beijing during 2014 and 2019

变量

中位数

最小值

Q1

Q3

最大值

四分位数间距

污染物PM2.5(μg/m3

47.34

8.32

30.64

73.01

301.08

42.38

PM10(μg/m3

82.67

22.23

59.36

116.79

689.27

57.42

二氧化硫(μg/m3

9.56

3.86

6.10

15.77

109.24

9.67

二氧化氮(μg/m3

36.42

12.01

29.32

48.63

113.34

19.30

臭氧(μg/m3

87.09

10.85

56.50

128.65

246.85

72.15

一氧化碳(mg/m3

0.85

0.31

0.67

1.14

6.04

0.47

空气质量指数

74.69

15.16

49.64

111.68

431.69

62.04

气象因素温度(℃)

9.70

–16.33

–1.87

18.92

28.01

20.79

比湿(g/kg)

4.71

0.22

1.80

10.44

22.08

8.64

气压(hPa)

997.85

972.97

990.25

1005.84

1023.25

15.59

风速(m/s)

0.72

0.27

0.57

0.99

5.25

0.41

Table 3 Descriptive statistical analysis of air pollutants and meteorological factors in Beijing during 2014 and 2019
Figure 2 Long short-term memory recurrent neural network loss curve
Figure 3 Root mean square error of the model under different epochs

训练超参数

设置

训练超参数

设置

原始数据集/条

2191

随机断开连接比例

0.2

记录时间间隔/d

1

预测时长

7

训练集大小/d

1753

参数优化方式

AdaMax

测试集大小/d

438

模型损失评价

MSE

LSTM-RNN层数

1

训练迭代次数

50

连接的神经元个数

90

每次批次大小

40

输出层层数

1

?

Table 4 Parameters of long short-term memory recurrent neural network (LSTM-RNN)
Figure 4 Comparison of long short-term memory recurrent neural network (LSTM-RNN) and generalized additive model (GAM) for predicting daily admissions of respiratory diseases with comorbid diabetes

类别

RMSE

MAE

调整后R2

GAM

LSTM-RNN

GAM

LSTM-RNN

GAM

LSTM-RNN

患者性别 男性

40.28 ± 24.63

13.36 ± 2.03

30.95 ± 18.89

9.68 ± 1.40

0.52 ± 0.08

0.75 ± 0.06**

女性

34.30 ± 16.85

10.95 ± 1.27*

26.69 ± 13.13

8.12 ± 0.83*

0.31 ± 0.05

0.73 ± 0.06**

季节温暖

30.26 ± 8.38

19.62 ± 4.84*

24.88 ± 7.72

13.87 ± 3.19*

0.77 ± 0.06

0.76 ± 0.07

寒冷

38.26 ± 19.18

22.60 ± 4.50

29.51 ± 16.09

16.11 ± 3.36

0.67 ± 0.15

0.78 ± 0.11

功能区首都功能核心区

9.25 ± 2.72

5.58 ± 0.62*

6.99 ± 2.24

4.13 ± 0.47*

0.54 ± 0.02

0.65 ± 0.09*

城市功能拓展区

38.09 ± 22.52

11.96 ± 2.01

29.01 ± 16.88

8.56 ± 1.12

0.48 ± 0.08

0.74 ± 0.07**

城市发展新区

8.23 ± 1.50

6.80 ± 0.88

6.31 ± 1.16

5.26 ± 0.69

0.58 ± 0.05

0.66 ±0.03*

生态涵养区

5.51 ± 0.81

4.58 ± 0.69

4.25 ± 0.43

3.59 ± 0.48

0.32 ± 0.12

0.41 ± 0.11

合计

46.13 ± 7.60

21.21 ± 3.30**

36.08 ± 6.20

14.64 ± 1.99**

0.57 ± 0.12

0.79 ± 0.06**

Table 5 The prediction performance of long short-term memory recurrent neural network (LSTM-RNN) and generalized addictive model (GAM)
[1]   SAEEDIP, PETERSOHNI, SALPEAP, et al.Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: results from the International Diabetes Federation Diabetes Atlas, 9th edition[J]Diabetes Res Clin Pract, 2019, 107843.
doi: 10.1016/j.diabres.2019.107843
[2]   KYUH H, ABATED, ABATEK H, et al.Global, regional, and national disability-adjusted life-years (DALYs) for 359 diseases and injuries and healthy life expectancy (HALE) for 195 countries and territories, 1990—2017: a systematic analysis for the Global Burden of Disease Study 2017[J]Lancet, 2018, 392( 10159): 1859-1922.
doi: 10.1016/S0140-6736(18)32335-3
[3]   GUANW J, LIANGW H, ZHAOY, et al.Comorbidity and its impact on 1590 patients with COVID-19 in China: a nationwide analysis[J]Eur Respir J, 2020, 55( 5): 2000547.
doi: 10.1183/13993003.00547-2020
[4]   SHIQ, ZHANGX, JIANGF, et al.Diabetic patients with COVID-19, characteristics and outcome: a two-centre, retrospective, case control study[J]SSRN J, 2020. DOI: 10.2139/SSN.3551369,
doi: 10.2139/ssrn.3551369
[5]   SILVERD, HUANGA, MADDISONC J, et al.Mastering the game of Go with deep neural networks and tree search[J]Nature, 2016, 529( 7587): 484-489.
doi: 10.1038/nature16961
[6]   张军阳, 王慧丽, 郭 阳, 等. 深度学习相关研究综述[J]. 计算机应用研究, 2018, 35(7): 1921-1928, 1936
ZHANG Junyang, WANG Huili, GUO Yang, et al. Review of deep learning[J]. Application Reasearch of Computer, 2018, 35(7): 1921-1928, 1936. (in Chinese)
[7]   王志远, 王守相, 陈海文, 等. 考虑空间相关性采用LSTM神经网络的光伏出力短期预测方法[J]. 电力系统及其自动化学报, 2020, 32(5): 78-85
WANG Zhiyuan, WANG Shouxiang, CHEN Haiwen, et al. Short-term photovoltaic output forecasting method using LSTM neural network with consideration of spatial correlation[J]. Proceedings of the CSU-EPSA, 2020, 32(5): 78-85. (in Chinese)
[8]   黄钰姝, 宋和佳, 张 睿, 等. ARIMAX与多变量LSTM模型在盐城市总死亡人数预测中的比较研究[J]. 公共卫生与预防医学, 2021, 32(5): 6-10
HUANG Yushu, SONG Hejia, ZHANG Rui, et al. Comparison of ARIMAX and multivariate LSTM model in predicting daily death toll in Yancheng city[J]. Journal of Public Health and Preventive Medicine, 2021, 32(5): 6-10. (in Chinese)
[9]   PENGR D, DOMINICIF, LOUIST A. Model choice in time series studies of air pollution and mortality[J]J R Statistical Soc A, 2006, 169( 2): 179-203.
doi: 10.1111/j.1467-985X.2006.00410.x
[10]   ZEGERS L, IRIZARRYR, PENGR D. On time series analysis of public health and biomedical data[J]Annu Rev Public Health, 2006, 27( 1): 57-79.
doi: 10.1146/annurev.publhealth.26.021304.144517
[11]   DOMINICIF, MCDERMOTTA, ZEGERS L, et al.On the use of generalized additive models in time-series studies of air pollution and health[J]Am J Epidemiol, 2002, 156( 3): 193-203.
doi: 10.1093/aje/kwf062
[12]   PENGZ, WANGQ, KANH, et al.Effects of ambient temperature on daily hospital admissions for mental disorders in Shanghai, China: a time-series analysis[J]Sci Total Environ, 2017, 281-286.
doi: 10.1016/j.scitotenv.2017.02.237
[13]   孙锦峰, 耿云亮, 郭奕瑞, 等. Elman神经网络与ARIMA模型对流感发病率预测效果的比较[J]. 郑州大学学报(医学版), 2013, 48(5): 584-587
SUN Jinfeng, GENG Yunliang, GUO Yirui, et al. Application and comparison of Elman neural network model and ARIMA model to predict the incidence of influenza[J]. Journal of Zhengzhou University (Medical Sciences), 2013, 48(5): 584-587. (in Chinese)
[14]   侯伟涛, 姬东鸿. 基于Bi-LSTM的医疗事件识别研究[J]. 计算机应用研究, 2018, 35(7): 1974-1977
HOU Weitao, JI Donghong. Research on clinic event recognition based Bi-LSTM[J]. Application Reasearch of Computer, 2018, 35(7): 1974-1977. (in Chinese)
[15]   李艳芳, 王 钰, 李济洪. 几种交叉验证检验的可重复性[J]. 太原师范学院学报(自然科学版), 2013, 12(4): 46-49
LI Yanfang, WANG Yu, LI Jihong. The replicability of several cross-validated tests[J]. Journal of Taiyuan Normal University (Natural Science Edition), 2013, 12(4): 46-49. (in Chinese)
[16]   刘相佟, 伍梦秋, 孙 玥, 等. 2013—2014年北京市脑卒中日入院人数的两种预测模型比较研究[J]. 健康体检与管理, 2021, 2(4): 295-301
LIU Xiangtong, WU Mengqiu, SUN Yue, et al. Comparison of two prediction models for daily admission of stroke in Beijing from 2013 to 2014[J]. Journal of Health Examination and Management, 2021, 2(4): 295-301. (in Chinese)
[17]   欧阳红兵, 黄 亢, 闫洪举. 基于LSTM神经网络的金融时间序列预测[J]. 中国管理科学, 2020, 28(4): 27-35
OUYANG Hongbing, HUANG Kang, YAN Hongju. Prediction of financial time series based on LSTM neural network[J]. Chinese Journal of Management Science, 2020, 28(4): 27-35. (in Chinese)
[18]   李 冰, 张 妍, 刘 石. 基于LSTM的短期风速预测研究[J]. 计算机仿真, 2018, 35(11): 456-461
LI Bing, ZHANG Yan, LIU Shi. Wind speed short term prediction study based on LSTM[J]. Computer Simulation, 2018, 35(11): 456-461. (in Chinese)
[19]   TAJT, MALMQVISTE, STROHE, et al.Short-term associations between air pollution concentrations and respiratory health——comparing primary health care visits, hospital admissions, and emergency department visits in a multi-municipality study[J]Int J Environ Res Public Health, 2017, 14( 6): 587.
doi: 10.3390/ijerph14060587
[20]   LAIH K, TSANGH, WONGC M. Meta-analysis of adverse health effects due to air pollution in Chinese populations[J]BMC Public Health, 2013, 13( 1): 360.
doi: 10.1186/1471-2458-13-360
[21]   THIERINGE, HEINRICHJ. Epidemiology of air pollution and diabetes[J]Trends Endocrinol Metab, 2015, 26( 7): 384-394.
doi: 10.1016/j.tem.2015.05.002
[22]   PAULL A, BURNETTR T, KWONGJ C, et al.The impact of air pollution on the incidence of diabetes and survival among prevalent diabetes cases[J]Environ Int, 2020, 105333.
doi: 10.1016/j.envint.2019.105333
[23]   GURUNGA, SONJ Y, BELLM L. Particulate matter and risk of hospital admission in the kathmandu valley, nepal: a case-crossover study[J]Am J Epidemiol, 2017, 186( 5): 573-580.
doi: 10.1093/aje/kwx135
[24]   YAOC, WANGY, WILLIAMSC, et al.The association between high particulate matter pollution and daily cause-specific hospital admissions: a time-series study in Yichang, China[J]Environ Sci Pollut Res, 2020, 27( 5): 5240-5250.
doi: 10.1007/s11356-019-06734-2
[25]   YANGB Y, GUOY, MARKEVYCHI, et al.Association of long-term exposure to ambient air pollutants with risk factors for cardiovascular disease in China[J/OL]JAMA Netw Open, 2019, 2( 3): e190318.
doi: 10.1001/jamanetworkopen.2019.0318
[26]   SONGX, WANGS, LIT, et al.The impact of heat waves and cold spells on respiratory emergency department visits in Beijing, China[J]Sci Total Environ, 2018, 1499-1505.
doi: 10.1016/j.scitotenv.2017.09.108
[27]   BLAUWL L, AZIZN A, TANNEMAATM R, et al.Diabetes incidence and glucose intolerance prevalence increase with higher outdoor temperature[J/OL]BMJ Open Diab Res Care, 2017, 5( 1): e000317.
doi: 10.1136/bmjdrc-2016-000317
[28]   SONGW M, LIUY, LIUJ Y, et al.The burden of air pollution and weather condition on daily respiratory deaths among older adults in China, Jinan from 2011 to 2017[J/OL]Medicine, 2019, 98( 10): e14694.
doi: 10.1097/MD.0000000000014694
[29]   顾 晨, 王佳欣, 吕沛诚, 等. 兰州市3种主要污染物大气环境容量季节差异及排放总量控制[J]. 兰州大学学报(自然科学版), 2021, 57(3): 302-310, 317
GU Chen, WANG Jiaxin, LYU Peicheng, et al. Seasonal variations in atmospheric environmental capacity and total quantity control for three criteria pollutants in Lanzhou[J]. Journal of Lanzhou University (Natural Sciences), 2021, 57(3): 302-310, 317. (in Chinese)
[30]   张 玉, 兰 剑, 乔利平, 等. 气象参数和节假日对上海市区大气污染物浓度的影响[J]. 广州化工, 2021, 49(18): 85-87, 108
ZHANG Yu, LAN Jian, QIAO Liping, et al. Influence of meteorological parameters and holidays on air pollutant concentration in Shanghai[J]. Guangzhou Chemical Industry, 2021, 49(18): 85-87, 108. (in Chinese)
[31]   臧星华, 鲁垠涛, 姚 宏, 等. 中国主要大气污染物的时空分布特征研究[J]. 生态环境学报, 2015, 24(8): 1322-1329
ZANG Xinghua, LU Yintao, YAO Hong, et al. The temporal and spatial distribution characteristics of main air pollutants in China[J]. Ecology and Environment Sciences, 2015, 24(8): 1322-1329. (in Chinese)
[32]   王嫣然, 张学霞, 赵静瑶, 等. 2013—2014年北京地区PM2.5时空分布规律及其与植被覆盖度关系的研究[J]. 生态环境学报, 2016, 25: 103-111
WANG Yanran, ZHANG Xuexia, ZHAO Jingyao, et al. Temporal and spatial distribution of PM2.5 and its relationship with vegetation coverage in Beijing during the period of 2013—2014[J]. Ecology and Environment Sciences, 2016, 25: 103-111. (in Chinese)
[33]   朱晓娟. 基于机器学习的健康风险评估与预测[D]. 成都: 电子科技大学, 2020
ZHU Xiaojuan. Health risk assessment and prediction based on machine learning[D]. Chengdu: University of Electronic Science and Technology of China, 2020. (in Chinese)
[34]   洪 也, 张 莹, 马雁军, 等. 沈阳大气污染物与气象因素对呼吸疾病门诊数的影响[J]. 中国环境科学, 2020, 40: 4077-4090
HONG Ye, ZHANG Ying, MA Yanjun, et al. Effects of air pollutants and meteorological factors on outpatient visitors for respiratory diseases in Shenyang[J]. China Environmental Science, 2020, 40: 4077-4090. (in Chinese)
[1] CHEN Yunyan,WU Qi,ZHANG Lixia,CHEN Danqing,LIANG Zhaoxia. Relationship of abnormal mid-term oral glucose tolerance test and maternal weight gain with adverse pregnancy outcomes in women with gestational diabetes mellitus[J]. J Zhejiang Univ (Med Sci), 2021, 50(3): 313-319.
[2] XU Heng,MA Yan,ZHANG Lixia,LIANG Zhaoxia,CHEN Danqing. Impact of pre-pregnancy body mass index, weight gain and blood lipid level during pregnancy on pregnancy outcome in patients with gestational diabetes mellitus[J]. J Zhejiang Univ (Med Sci), 2021, 50(3): 320-328.
[3] ZHOU Yumei,XIE Ni,ZHANG Lixia,CHEN Danqing. Impact of family history of diabetes on blood glucose, lipid levels and perinatal outcomes in pregnant women with gestational diabetes mellitus[J]. J Zhejiang Univ (Med Sci), 2021, 50(3): 329-334.
[4] GE Yingzhou,LIU Xinmei,HUANG Hefeng. Advances in the role of silence information regulator family in pathological pregnancy[J]. J Zhejiang Univ (Med Sci), 2021, 50(3): 335-344.
[5] ZHANG Zhuangwei,LI Junqin,HU Tiantian,XU Chunjing,XIE Ni,CHEN Danqing. Interventional effect of dietary fiber on blood glucose and pregnancy outcomes in patients with gestational diabetes mellitus[J]. J Zhejiang Univ (Med Sci), 2021, 50(3): 305-312.
[6] WU Yi,JIANG Weiliang,YANG Xiaojun,LI Wenhua,WAN Rong,LU Lungen,FAN Junwei,LU Zhanjun. Postoperative serum triglyceride levels in predicting risk of new-onset diabetes mellitus in patients following liver transplantation[J]. J Zhejiang Univ (Med Sci), 2021, 50(2): 239-244.
[7] YE Yuanqing,LEI Hao,CHEN Chen,HU Kejia,XU Xiaolin,YUAN Changzheng,CAO Shuyin,WANG Sisi,WANG Sicong,LI Shu,YING Zhijun,JIA Junlin,WANG Qinchuan,Sten H. VERMUND,XU Zhengping,WU Xifeng. Predicting COVID-19 epidemiological trend by applying population mobility data in two-stage modeling[J]. J Zhejiang Univ (Med Sci), 2021, 50(1): 68-73.
[8] FU Yuanyuan,JIANG Jingxin,CHEN Shuzheng,QIU Fuming. Establishment of risk prediction nomogram for ipsilateral axillary lymph node metastasis in T1 breast cancer[J]. J Zhejiang Univ (Med Sci), 2021, 50(1): 81-89.
[9] ZHU Huiqi,YING Kejing. Tissue factors and venous thromboembolism in cancer patients[J]. J Zhejiang Univ (Med Sci), 2020, 49(6): 772-778.
[10] HAN Xue,JIANG Guojun,SHI Qiaojuan. Effects of antihyperglycemics on endothelial progenitor cells[J]. J Zhejiang Univ (Med Sci), 2020, 49(5): 629-636.
[11] HONG Pingping,GUO Bingjie,LIN Li,LIN Xihua,ZHOU Jiaqiang. A novel mutation W257R in GCK gene discovered from a Chinese patient with maturity onset diabetes of the young[J]. J Zhejiang Univ (Med Sci), 2019, 48(2): 200-203.
[12] LI Xiaoyong,SHEN Peng,LIN Hongbo,YU Zhebin,CHEN Kun,WANG Jianbing. A community-based survey on risk factors of type 2 diabetic kidney disease in Ningbo, China[J]. J Zhejiang Univ (Med Sci), 2018, 47(2): 163-168.
[13] LIU Tingting,WANG Lingxiao,YANG Xiaohui,YAO Zhiqing,CAI Huizhen. TLR/NF-κB independent signaling pathway in TNF-α suppression of diabetic MyD88-knockout mice after Lycium barbarum polysaccharides administration[J]. J Zhejiang Univ (Med Sci), 2018, 47(1): 35-40.
[14] WANG Jiesheng, DAI Guanhai, LI Weijia. Berberine regulates glycemia via local inhibition of intestinal dipeptidyl peptidase-Ⅳ[J]. J Zhejiang Univ (Med Sci), 2016, 45(5): 486-492.
[15] YAO Meifang, SUN Xue, HAN Jue, TU Yina, HE Jie, ZHAO Yiming, LOU Hanyu, PANG Xiaohong, ZENG Wenheng, ZHANG Songzhao, SHAN Pengfei. Metabolic syndrome increases Framingham risk score of patients with type 2 diabetes mellitus[J]. J Zhejiang Univ (Med Sci), 2016, 45(3): 268-274.