基于改进关联规则与Logistic回归算法集成的2型糖尿病中医证型鉴别研究

Corresponding author: Wen Tiancai

DOI: 10.12201/bmr.202404.00034

•  

  Abstract: Objective: To analyze the multidimensional interaction between the characteristics of Chinese and Western medicine in patients with type 2 diabetes mellitus and its influence on TCM(Traditional Chinese Medicine) dialectics. Methods: Based on the real-world electronic medical record data,The traditional association rule algorithm is improved, and the important TCM syndromes are screened out as dependent variables by increasing respect index, and then the Logistic regression algorithm is used to explore the influence of Chinese and Western medicine indexes on TCM syndromes. Results: A total of 688 patients with T2DM were included in this study, including 317 cases of qi and yin deficiency syndrome, 186 cases of middle-earth stagnation syndrome, 111 cases of liver qi stagnation syndrome and 74 cases of intestinal damp-heat syndrome. Finally, 112 association rules are obtained, among which 12 rules contain TCM syndromes. The association rules between middle-earth stagnation syndrome and overweight/obesity has the greatest respect (Respect=0.52), moreover, overweight/obese patients have a higher prevalence rate of middle-earth stagnation syndrome (OR=3.097,P<0.001). There is a strong correlation between middle-earth stagnation syndrome 、peripheral neuropathy or hypertension with overweight/obesity (Respect=0.42). Patients with diabetic nephropathy are more likely to have qi and yin deficiency syndrome (OR=1.475,P=0.019).

  Key words: type 2 diabetes mellitus; Characteristics of Chinese and western medicine; TCM syndrome types; Association rules; Real world research

  Submit time: 26 April 2024

  Copyright: The copyright holder for this preprint is the author/funder, who has granted biomedRxiv a license to display the preprint in perpetuity.
• html

• 图表

• Yu Hong, Wang Congrong, Chen Fang, Yin Shankai, Hu Cheng, Bao Yuqian, Jia Weiping, Zhang Liang, Zhu Lin. Type 2 Diabetes Health Education Knowledge Science Mapping. 2020. doi: 10.12201/bmr.202007.00001

  liruiyao, xujingyi, daihaoyu, sunhuiwen, wutianxing. Deep confidence network-based prediction of microvascular complications in type 2 diabetes mellitus. 2024. doi: 10.12201/bmr.202404.00021

  Analysis of risk factors for hypoglycemia in elderly outpatients with type 2 diabetes. 2024. doi: 10.12201/bmr.202412.00069

  WANG Li, PIAO Chun-li. Efficacy and safety of Yuye decoction with metformin in type 2 diabetes mellitus: A meta-analysis. 2024. doi: 10.12201/bmr.202407.00066

  zhangshipei, chujinshen, xueguohui, wanfang, caojunda, chenkeqi, chenjing, liuxiaofeng, chenxueli. Elevated HE4 levels in type 2 diabetes patients are associated with proteinuria and renal impairment. 2024. doi: 10.12201/bmr.202409.00008

  wangyifan, shichaojun, maanning. Comparison of risk prediction models for atherosclerosis in type 2 diabetes mellitus. 2024. doi: 10.12201/bmr.202404.00007

  Liu Shiwei. The predictive value of neutrophil-to-lymphocyte ratio and platelet-to-lymphocyte ratio in the type 2 diabeticnephropathy. 2024. doi: 10.12201/bmr.202408.00066

  QIU Weiwen, LAN Haiyuan, WANG Huaqiang. Correlating White Matter Hyperintensities Severity with Collateral Disease Syndrome Type Distribution. 2024. doi: 10.12201/bmr.202411.00015

  zhaochengyu. Research Progress on the Relationship between Hyperuricemia and Diabetic Peripheral Neuropathy. 2024. doi: 10.12201/bmr.202408.00019

  HU Xinxin, GAO Chuchu, ZHU Xueme, PAN Yiyi. Analysis of Medication Patterns for Treating Menstrual Disorders with Chong and Ren Disharmony Based on Real-World Data Mining. 2024. doi: 10.12201/bmr.202412.00026

• ID	Submit time	Number	Download
  1	2023-12-28	bmr.202404.00034V1	Download

• Public  Anonymous  To author only Submit Comments