Search

Fasting blood glucose (FBG) and glycosylated hemoglobin (HbA1c) are key indicators reflecting blood glucose control in type 2 diabetes mellitus (T2DM) patients. The purpose of this study is to establish a predictive model for blood glucose changes in T2DM patients after 3 months of treatment, achieving personalized treatment.A retrospective study was conducted on type 2 diabetes mellitus real-world medical data from 4 cities in Sichuan Province, China from January 2015 to December 2020. After data preprocessing, data inputting, data sampling, and feature screening, 16 kinds of machine learning methods were used to construct prediction models, and 5 prediction models with the best prediction performance were screened respectively. A total of 100,000 cases were included to establish the FBG model, and 2,169 cases were established to establish the HbA1c model. The best prediction model both of FBG and HbA1c finally obtained are realized by ensemble learning and modified random forest inputting, the AUC values are 0.819 and 0.970, respectively. The most important indicators of the FBG and HbA1c prediction model were FBG and HbA1c. Medication compliance, follow-up outcome, dietary habits, BMI, and waist circumference also had a greater impact on FBG levels. The prediction accuracy of the models of the two blood glucose control indicators is high and has certain clinical applicability.HbA1c and FBG are mutually important predictors, and there is a close relationship between them. [ABSTRACT FROM AUTHOR]

Objective: Because acute myocardial infarction (AMI) is a major cause of death, China faces the challenge of improving its quality of care. This study provides context‐specific evidence of association between 30‐day mortality and hospital characteristics in China to extend the understanding of hospitalized AMI patients. Methods: We conducted a retrospective cohort study of 67,619 hospitalized AMI patients at 372 tertiary and secondary hospitals in Sichuan, China, between January 1, 2018 and December 31, 2020. Using a hierarchical logistic regression model to control risk factors, we explored relationships among 30‐day mortality, hospital level, AMI volume, and percutaneous coronary intervention (PCI) timeliness. Locally weighted scatterplot smoothing was used to observe the trends of 30‐day mortality with increased AMI volume and PCI timeliness. Results: After risk factor adjustment, the 30‐day mortality model demonstrated that a lower hospital level and smaller AMI volume were associated with higher 30‐day mortality (medium‐volume: OR = 1.511, 95% CI (1.195, 1.910); small‐volume: OR = 1.636, 95% CI (1.277, 2.096); other tertiary: OR = 1.190, 95% CI (1.037, 1.365); secondary: OR = 1.524, 95% CI (1.289, 1.800)). Similarly, 30‐day mortality was higher for patients at hospitals with a low PCI timeliness (low timeliness: OR = 1.318, 95% CI (1.079, 1.610)). Scatterplot smoothing showed hospital 30‐day mortality first reduced quickly and gradually stabilized with increased AMI volume and PCI timeliness. Conclusion: Patients admitted to tertiary grade A hospitals, large‐volume hospitals, and high‐ or medium‐timeliness hospitals were more likely to survive at 30 days. Policymakers should focus on improving the outcomes at hospitals without these characteristics. [ABSTRACT FROM AUTHOR]