Rui Zhang

Rui Zhang

Auto-generated profile, based on publicly available information

Rui Zhang

Engineering Research Center of Medical Information Technology, Ministry of Education, West China Hospital of Sichuan University, Chengdu, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 June 2022 in BMC Bioinformatics
Verified
Journal Article
Open access
PDF file
RLRan Liu
Ran Liu
MWMiye Wang
Miye Wang
TZTao Zheng
Tao Zheng
RZRui Zhang
Rui Zhang
NLNan Li
Nan Li
QSQingke Shi
Qingke Shi
Background: Myocardial infarction can lead to malignant arrhythmia, heart failure, and sudden death. Clinical studies have shown that early identification of and timely intervention for acute MI can significantly reduce mortality. The traditional MI risk assessment models are subjective, and the data that go into them are difficult to obtain. Generally, the assessment is only conducted among high-risk patient groups.Objective: To construct an artificial intelligence–based risk prediction model of myocardial infarction (MI) for continuous and active monitoring of inpatients, especially those in noncardiovascular departments, and early warning of MI.Methods: The imbalanced data contain 59 features, which were constructed into a specific dataset through proportional division, upsampling, downsampling, easy ensemble, and w-easy ensemble. Then, the dataset was traversed using supervised machine learning, with recursive feature elimination as the top-layer algorithm and random forest, gradient boosting decision tree (GBDT), logistic regression, and support vector machine as the bottom-layer algorithms, to select the best model out of many through a variety of evaluation indices.Results: GBDT was the best bottom-layer algorithm, and downsampling was the best dataset construction method. In the validation set, the F1 score and accuracy of the 24-feature downsampling GBDT model were both 0.84. In the test set, the F1 score and accuracy of the 24-feature downsampling GBDT model were both 0.83, and the area under the curve was 0.91.Conclusion: Compared with traditional models, artificial intelligence–based machine learning models have better accuracy and real-time performance and can reduce the occurrence of in-hospital MI from a data-driven perspective, thereby increasing the cure rate of patients and improving their prognosis.

12 January 2019 in Lipids in Health and Disease
Verified
Journal Article
Open access
PDF file
QHQingtao Hou
Qingtao Hou
CYchuan yu
chuan yu
Sheyu LiSheyu Li
Sheyu Li
YLYun Li
Yun Li
RZRui Zhang
Rui Zhang
HTHaoming Tian
Haoming Tian
Diabetes is often accompanied by dyslipidemia. Lipid control is very important in the management of diabetes. There are limited real world data on the lipid control in diabetic inpatients in southwest China. An observational study was conducted to assess the characteristics of lipid profiles and lipid control. Diabetic patients from February 2009 to December 2013 at West China Hospital of Sichuan University were identified. A total of 56,784 inpatients were included and 85.9% of them had at least one lipid panel. The proportions of inpatients with optimal low-density lipoprotein cholesterol (LDL-C) level (< 2.59 mmol/L), optimal triglyceride (TG) level (< 1.70 mmol/L), optimal high-density lipoprotein cholesterol (HDL-C) level (men ≥1.04 mmol/L; women ≥1.30 mmol/L) and optimal non-high-density lipoprotein cholesterol (non-HDL-C) level (< 3.37 mmol/L) were 61.1, 64.6, 49.9 and 64.5%, respectively. Only 23.1% of inpatients obtained optimal levels for all the above four lipid parameters. Of diabetic inpatients with ischemic heart disease, the proportions of inpatients with optimal LDL-C level (< 1.81 mmol/L), optimal TG level (< 1.70 mmol/L), optimal HDL-C level (men ≥1.04 mmol/L; women ≥1.30 mmol/L) and optimal non-HDL-C level (< 2.59 mmol/L) were 38.0, 66.3, 48.1 and 48.7%, respectively. Of diabetic inpatients with cerebrovascular disease, the proportions were 28.3, 64.8, 49.9 and 38.1%, respectively. Older people and men were more likely to obtain optimal lipid levels. However, inpatients between 46 and 64 years were least likely to obtain optimal LDL-C levels. The lipid control of diabetic inpatients in southwest China is worrisome. Individualized strategies of lipid management should be taken to bridge the gap between the recommendations of clinical guidelines and the real situation of clinical practice.