Construction and Analysis of a Prediction Model for Hypertension Combined with Left Ventricular Diastolic Dysfunction Based on Random Forest AlgorithmWANG Tingting1 ,ZHOU Wei1*

Corresponding author: zhou wei, zhouweishmily@163.com

DOI: 10.12201/bmr.202503.00046

•  

  Abstract: Background The occurrence and development of left ventricular diastolic dysfunction is an important and critical transitional stage in the damage process of hypertension to the heart. Left ventricular diastolic dysfunction often occurs earlier than systolic dysfunction. Analyzing and exploring the risk factors of hypertension combined with left ventricular diastolic dysfunction is of great significance for early prevention and intervention of further heart damage. Objective To construct a random forest model for risk factor prediction and validation, explore the influencing factors of EH combined with LVDD, and provide a basis for clinical prevention and treatment. Method 300 patients with primary hypertension who were hospitalized in our hospital from October 2023 to July 2024 were selected as the research subjects. Collect basic information and laboratory test results of patients upon admission, and divide them into a simple EH group (n=60) and a combined LVDD group (LVDD, n=240) based on whether LVDD is present or not. Compare the general information and biochemical indicators of the two groups, perform logistic regression analysis on the influencing factors of EH combined with LVDD, and construct a random forest model. Results Compared with the EH group, the LVDD group showed an increase in age, hypertension grading, hypertension risk stratification, disease duration, proportion of concomitant coronary heart disease, WBC, PLT, IL-6, TC, LDL-C, ALP, CK, and Pro BNP (p<0.05); HDL-C and ALB decreased (p<0.05). Logistic regression analysis showed that hypertension grading, hypertension risk stratification, disease duration, proportion of concomitant coronary heart disease WBC、IL-6、TC、LDL-C、ALB、ALT、Pro-BNP, It is the influencing factor of EH merging with LVDD, among which ALB is the protective factor. The random forest model shows that when the number of decision trees is 300, the out of bag data (OOB) error rate of the model reaches its lowest point, which is 2.86%. According to the ranking of importance, the factors that affect the merging of EH and LVDD, from high to low, are as follows: IL-6、ALB、ALP、LDL-C、Pro-BNP、TC、 Hypertension classification, hypertension risk stratification WBC。Conclusion IL-6 ALB、ALP、LDL-C、Pro-BNP、TC、Hypertension grading, hypertension risk stratification, and WBC are influencing factors of EH combined with LVDD, which are helpful for early clinical prevention and treatment.

  Key words: [keywords missed]

  Submit time: 15 March 2025

  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

• ruanxuling, liuqi, guo zhiheng, yanjunfeng. Research on prediction model of breast cancer based on LDA and XGBoost algorithm. 2022. doi: 10.12201/bmr.202106.00007

  Mo Wei, Xiang Ya, Liao Qiujiao, He Liu, Ling Chaoling, Lu Qixiang, Liu Fangyin. Research progress on risk prediction model of postoperative delirium in elderly patients with hip fractureWEI Yunshi1? MO Wei1? XIANG YA1? LIAO Qiujiao1? HE Liu2? LING Chaoling2? LU Qixiang2? LIU Fangyin3▲. 2024. doi: 10.12201/bmr.202409.00029

  LIU Rui, LIU Xiao-li, JIN Ze-hong. Analysis of application value and related factors for left ventricular? global longitudinal strain in early cardiac function injury in patients with diabetes mellitus. 2024. doi: 10.12201/bmr.202411.00042

  zhouyibo, wangxidan, chenjingwan, chenfuhua, taoxiaoying. YANG Daoling, ZHOU Yibo, WANG Xidan, CHEN Jingwan, CHEN Fuhua, TAO XiaoyingFirst-author’s address: Department of Ultrasound Medicine, Affiliated Jinhua Hospital, Zhejiang University School of Medicine, Jinhua, 321000, China. 2024. doi: 10.12201/bmr.202410.00076

  XIANG Hongying, LING Yingchun. Analysis of the predictive value of quantitative parameters of electroencephalogram and serum miR-146a-5p for cognitive impairment in Alzheimers disease patients. 2024. doi: 10.12201/bmr.202412.00027

  YUE xiaobo, ZHAO Xingsheng. The correlation between serum MHR, NLR, and PLR with essential hypertension. 2024. doi: 10.12201/bmr.202411.00052

  pangzhen, GuJiYu, WuYuFei, YanSshiXing, LiWangYang, SunYue. A study on the solution of the problem of extracting essential substance of TCM diagnosis and treatment of hypertension based on triple extraction strategy. 2021. doi: 10.12201/bmr.202107.00015

  fengli. A Comparative Study on the Accuracy of Nine Combined Machine Learning Algorithms in Early Diagnosis of Tumors Based on High-dimensional dataFeng Li 1,*, Yue Xiaofei 2. 2021. doi: 10.12201/bmr.202108.00016

  liuhe. Hospital Library Reading Promotion Model Building Based on 5W1H Analysis. 2022. doi: 10.12201/bmr.202208.00003

  Construction and application evaluation of risk prediction model and nomogram for shivering during cesarean sectio. 2025. doi: 10.12201/bmr.202501.00053

• ID	Submit time	Number	Download
  1	2025-02-20	bmr.202503.00046V1	Download

• Public  Anonymous  To author only Submit Comments