Construction of a model for the onset-risk of diabetic kidney disease based on the classification tree method

doi:10.3877/cma.j.issn.2095-3216.2021.05.002

Abstract

Abstract:

Objective

To apply the classification tree method for constructing a model for the onset-risk of diabetic kidney disease (DKD), and to evaluate its value in application.

Methods

285 diabetic patients diagnosed in the Nanjing Hospital of Traditional Chinese Medicine from February 2017 to August 2020 were selected, including 76 patients with DKD (DKD group) and 209 patients with simple diabetes (control group). The correlation between the clinical data and DKD was analyzed for the two groups. Single-factor and multi-factor logisitic regression method was used to analyze the relevant influencing factors of DKD. The chi-squared automatic interaction detector (CHAID) classification tree algorithm was used to establish a predictive risk model for the onset of DKD. The value for application of the model was evaluated with the income graph, index graph, and misclassification probability.

Results

The classification tree model for the onset-risk of DKD included 3 layers with a total of 8 nodes. Four explanatory variables were screened out, including diabetes course, body mass index, systolic blood pressure, and glycosylated hemoglobin (HbA1c), among which HbAlc was the most important predictor. The misclassification probability of the model was 0.149, indicating that the fitting effect of the model was good.

Conclusion

The classification tree model could not only effectively predict the onset-risk of DKD, but also analyze the interaction between the variables. Controlling the weight, blood sugar, and blood pressure of patients with long-term diabetes may help prevent and control the onset-risk of DKD.

Key words: Diabetic kidney disease, Risk factors, Classification tree, Prediction model

Hongjuan Ji, Juan Lin. Construction of a model for the onset-risk of diabetic kidney disease based on the classification tree method[J]. Chinese Journal of Kidney Disease Investigation(Electronic Edition), 2021, 10(05): 246-251.

/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: https://zhsbyjdzzz.cma-cmc.com.cn/EN/10.3877/cma.j.issn.2095-3216.2021.05.002

https://zhsbyjdzzz.cma-cmc.com.cn/EN/Y2021/V10/I05/246

Figures/Tables 9

References 29

[1]	曾富元，史晓腾. 吡格列酮联合替米沙坦对糖尿病肾病患者血清TGF-β-1、MMP-9、TIMP-1水平及肾功能的影响[J]. 临床合理用药杂志，2021, 14(4): 20-22.
[2]	徐庆东，郭焕开，陈洁欣，等. 血清SFRP-4水平与2型糖尿病肾病患者胰岛素抵抗、肾功能及肾纤维化指标的相关性[J]. 疑难病杂志，2021, 20(2): 158-162.
[3]	吴修红，刘静，朴成玉，等. 当归补血汤治疗糖尿病肾病作用机制研究进展[J]. 中医药学报，2021, 49(2): 79-82.
[4]	石妍妍. 2型糖尿病患者的糖尿病肾病影响因素分析[D]. 郑州：郑州大学，2020.
[5]	李东哲，王丹丹，蔡明，等. 糖尿病肾病影响因素及相关信号通路研究进展[J]. 承德医学院学报，2020, 37(4): 333-337.
[6]	张丽敏，高燕，李鸿燕，等. 影响糖尿病肾病患者发病的相关因素分析[J]. 重庆医学，2014, 43(27): 3649-3651.
[7]	王金塔，孙丽. 2014-2017年常州市学生男男性行为者血浆硒水平及影响因素[J]. 卫生研究，2019, 48(4): 567-572.
[8]	余方琳，叶莺，严延生. 福建省居民膳食模式及基于分类树模型的糖尿病影响因素分析[J]. 中华流行病学杂志，2017, 38(5): 602-610.
[9]	何纲，张志侨，叶一农，等. 慢加急性肝衰竭患者发生肝性脑病高危人群的分类树模型和简易风险评估[J]. 中国热带医学，2020, 20(3): 275-280.
[10]	王雪莹，李楠，郭佳桐，等. 基于分类树模型对高尿酸血症的影响因素分析[J]. 中华疾病控制杂志，2019, 23(11): 1364-1369.
[11]	肖傲霜. 基于分类树模型的妊娠期不良症状与围产期抑郁症状相关性及交互作用探究[D]. 武汉：武汉轻工大学，2019.
[12]	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.
[13]	赵文波，李明，唐骅，等. 应用分类树模型构建糖尿病肾病蛋白尿进展的风险预测模型[J]. 第三军医大学学报，2013, 35(11): 1144-1147.
[14]	廖志波，刘迅，成彩联，等. 慢性肾脏病3-4期糖尿病肾脏疾病患者进展到终末期肾病的危险因素分类树模型分析[J]. 中山大学学报(医学科学版), 2019, 40(5): 767-773.
[15]	魏颖，毛宝宏，王剑，等. 应用分类树模型分析女性性功能障碍的影响因素[J]. 中国性科学，2019, 28(12): 83-89.
[16]	董俊，杨莉，杨蓓，等. 2型糖尿病患者合并糖尿病肾病的临床特征及相关危险因素分析[J]. 中国医学创新，2020, 17(21): 43-46.
[17]	石妍妍. 2型糖尿病患者的糖尿病肾病影响因素分析[D]. 郑州：郑州大学，2020.
[18]	高赛赛，张爱鸣，杨宏，等. 糖尿病肾病的危险因素分析[J]. 中国基层医药，2020, 27(18): 2257-2260.
[19]	张波，丁文谦. 托拉塞米治疗伴利尿剂抵抗糖尿病肾病患者的临床效果[J]. 中国当代医药，2019, 26(26): 36-38, 43.
[20]	Hu J, Du Y. Managing chronic kidney disease in diabetes patients with the latest chemical therapies [J]. Expert Rev Clin Pharmacol, 2019, 12(1): 53-60.
[21]	白倩，陈琰，代闪，等. 2型糖尿病患者血糖波动指标与MAU的相关性[J]. 临床与病理杂志，2019, 39(8): 1698-1704.
[22]	Scott SN, Christiansen MP, Fontana FY, et al. Evaluation of factors related to glycemic management in professional cyclists with type 1 diabetes over a 7-day stage race [J]. Diabetes Care, 2020, 43(5): 1142-1145.
[23]	Radcliffe NJ, Seah JM, Clarke M, et al. Clinical predictive factors in diabetic kidney disease progression [J]. J Diabetes Investig, 2017, 8(1): 6-18.
[24]	马剑侠. 2型糖尿病肾脏疾病临床危险因素分析及FoxO1与2型糖尿病肾脏疾病风险关系研究[D]. 石家庄：河北医科大学，2020.
[25]	韩金良. 同型半胱氨酸、血清胱抑素C、超敏C反应蛋白联合检测在糖尿病肾病早期诊断中的应用[J]. 中国现代医生，2019, 57(19): 132-134.
[26]	Ravindran R, Kalaivalli S, Srinivasagalu S, et al. A study on prevalence and risk factors of diabetic nephropathy in newly detected type 2 diabetic patients [J]. J Diabetol, 2020, 11(2): 109-114.
[27]	中国高血压防治指南修订委员会. 中国高血压防治指南(2018修订版)[J]. 中国心血管杂志，2019, 24(1): 24-56.
[28]	Hu F, Zhang TT. Study on risk factors of diabetic nephropathy in obese patients with type 2 diabetes mellitus [J]. Int J Gen Med, 2020, 13: 351-360.
[29]	Okada S, Samejima K, Matsui M, et al. Microscopic hematuria is a risk factor for end-stage kidney disease in patients with biopsy-proven diabetic nephropathy [J]. BMJ Open Diabetes Res Care, 2020, 8(2): e001863.

指标	DKD组(n＝76)	对照组(n＝209)	t/χ²值	P值
年龄(岁)	56.28±11.83	55.24±12.35	0.636	0.526
性别	45/31	115/94	0.397	0.529
BMI(kg/m²)	26.43±2.87	24.32±2.44	6.151	<0.001
糖尿病病程(年)	12.85±3.46	9.86±2.75	7.554	<0.001
SBP(mm Hg)	159.43±23.12	138.47±21.46	7.141	<0.001
DBP(mm Hg)	84.56±14.27	81.23±13.56	1.808	0.072
吸烟史	26(34.21)	61(29.19)	0.663	0.415
饮酒史	24(31.58)	50(23.92)	1.699	0.192
DR	28(36.84)	56(26.79)	2.707	0.100
FBG(mmol/L)	9.46±2.58	8.49±2.16	3.178	0.002
HbA1c(%)	8.59±2.47	7.49±1.96	3.897	<0.001
TG(mmol/L)	1.54±0.46	1.45±0.38	1.668	0.096
TC(mmol/L)	4.16±0.76	4.11±0.71	0.516	0.606

指标	DKD组(n＝76)	对照组(n＝209)	t/χ²值	P值
年龄(岁)	56.28±11.83	55.24±12.35	0.636	0.526
性别	45/31	115/94	0.397	0.529
BMI(kg/m²)	26.43±2.87	24.32±2.44	6.151	<0.001
糖尿病病程(年)	12.85±3.46	9.86±2.75	7.554	<0.001
SBP(mm Hg)	159.43±23.12	138.47±21.46	7.141	<0.001
DBP(mm Hg)	84.56±14.27	81.23±13.56	1.808	0.072
吸烟史	26(34.21)	61(29.19)	0.663	0.415
饮酒史	24(31.58)	50(23.92)	1.699	0.192
DR	28(36.84)	56(26.79)	2.707	0.100
FBG(mmol/L)	9.46±2.58	8.49±2.16	3.178	0.002
HbA1c(%)	8.59±2.47	7.49±1.96	3.897	<0.001
TG(mmol/L)	1.54±0.46	1.45±0.38	1.668	0.096
TC(mmol/L)	4.16±0.76	4.11±0.71	0.516	0.606

指标	OR值	OR的95%CI	P值
年龄(岁)	1.136	0.943~1.329	0.162
性别	1.256	1.121~1.391	0.487
BMI(kg/m²)	1.604	1.426~1.782	0.021
糖尿病病程(年)	2.426	1.745~3.107	0.029
SBP(mm Hg)	1.432	1.187~1.677	<0.001
DBP(mm Hg)	2.264	2.034~2.494	0.157
吸烟史	1.873	1.437~2.309	0.714
饮酒史	1.342	1.312~1.372	0.098
DR	1.534	1.274~1.794	0.087
FBG(mmol/L)	2.103	1.856~2.894	0.026
HbA1c(%)	2.463	2.124~2.802	0.018
TG(mmol/L)	1.621	1.132~2.110	0.093
TC(mmol/L)	1.341	1.141~1.541	0.124
HDL-C(mmol/L)	1.342	1.115~1.569	0.147
LDL-C(mmol/L)	1.442	1.345~1.539	0.564
UA(μmol/L)	2.721	2.463~2.979	0.011

指标	OR值	OR的95%CI	P值
年龄(岁)	1.136	0.943~1.329	0.162
性别	1.256	1.121~1.391	0.487
BMI(kg/m²)	1.604	1.426~1.782	0.021
糖尿病病程(年)	2.426	1.745~3.107	0.029
SBP(mm Hg)	1.432	1.187~1.677	<0.001
DBP(mm Hg)	2.264	2.034~2.494	0.157
吸烟史	1.873	1.437~2.309	0.714
饮酒史	1.342	1.312~1.372	0.098
DR	1.534	1.274~1.794	0.087
FBG(mmol/L)	2.103	1.856~2.894	0.026
HbA1c(%)	2.463	2.124~2.802	0.018
TG(mmol/L)	1.621	1.132~2.110	0.093
TC(mmol/L)	1.341	1.141~1.541	0.124
HDL-C(mmol/L)	1.342	1.115~1.569	0.147
LDL-C(mmol/L)	1.442	1.345~1.539	0.564
UA(μmol/L)	2.721	2.463~2.979	0.011

指标	VIF
BMI(kg/m²)	1.532
糖尿病病程(年)	1.214
SBP(mm Hg)	1.047
FBG(mmol/L)	2.542
HbA1c(%)	1.149
UA(μmol/L)	1.231

Please choose a citation manager

Content to export