Aim: Patients with type 2 diabetes mellitus (T2DM) exhibit an elevated prevalence of metabolic dysfunction‐associated steatotic liver disease (MASLD) and are at greater risk of liver‐related adverse events. Existing non‐invasive tools show limited diagnostic performance in this population. This study aims to develop a predictive model that accurately identifies the risk of MASLD among T2DM patients. Materials and methods: Clinical data were collected from T2DM patients hospitalised at Nanjing Drum Tower Hospital between January 2018 and May 2025. Eight machine learning methods were developed to predict the risk of MASLD in T2DM patients. The discriminatory ability of the models was evaluated using area under the receiver operating characteristic curve (AUROC), area under the precision‐recall curve (AUPRC), accuracy, recall, negative predictive value, positive predictive value, and F1 score. Calibration curves and decision analysis curves were employed to evaluate the calibration and clinical utility. The models were interpreted using the Shapley additive explanations method, and unsupervised clustering was performed to identify potential high‐risk subgroups. Results: A total of 3836 T2DM patients constituted the complete dataset, with a MASLD incidence rate of 55.9%. Thirteen feature variables were selected for model construction, and the XGB model achieved optimal overall performance, with an AUROC of 0.873 and an AUPRC of 0.904. Unsupervised clustering identified several high‐risk subgroups with distinct metabolic characteristics. Conclusion: The model developed enables reliable and interpretable MASLD risk prediction in T2DM patients based on selected commonly available clinical data, providing a practical tool for routine identification and stratified management.

Objective. To explore the incidence and influencing factors of postoperative hypoglycemia in diabetic patients during the perioperative period and to construct a risk prediction model for postoperative hypoglycemia. Methods. Patients with T2DM admitted to the nonendocrinology department of Nanjing Drum Tower Hospital from December 2019 to January 2022 were included as research subjects. Basic information, hospital blood glucose management methods, laboratory indicators, and surgery-related indicators were collected. A risk prediction model and scoring table for postoperative hypoglycemia in patients with perioperative diabetes mellitus were established. Results. A total of 440 patients were included, of which 109 had hypoglycemia, resulting in an incidence of postoperative hypoglycemia of 24.78. The results show that preoperative C-peptide and operation duration were risk factors for postoperative hypoglycemia, while BMI and preoperative fasting blood glucose were protective factors. Conclusion. The model constructed in this study is a good method for evaluating the risk of postoperative hypoglycemia. The scoring table intuitively quantifies the risk of risk factors for outcome variables and has strong clinical practicability.

Background: Effective glycemic control is crucial for hospitalized patients, leading to benefits such as shorter hospital stays and reduced postoperative infection rates. While previous studies have emphasized the effectiveness of multidisciplinary collaborative stewardship for hospital‐wide hyperglycemia management, patient perspectives and preferences have not been adequately considered.Objective: To identify factors influencing treatment preferences of Chinese hospitalized diabetes patients using discrete choice experiments (DCEs) and provide practical insights for the construction of a hospital‐wide glycemic control programme.Methods: A face‐to‐face survey was conducted among diabetes patients admitted to nonendocrine departments in a tertiary hospital in Nanjing, China. The attributes and levels were determined based on DCE principles, and a conditional logit model was used to quantify patients’ preferences.Results: A total of 157 respondents were analyzed. Antihyperglycemic effectiveness, healthcare providers, treatment regimen, monitoring frequency, and adverse reactions were the five attributes that significantly influenced patient preference (p < 0.05). Notably, an 80% glycemic control rate (β = 2.009) and a multidisciplinary management team involving clinical pharmacists (β = 1.346) had the greatest impact. Negative effects were observed for hypoglycemia (β = −1.008), insulin pump use (β = −0.746), and frequent glucose monitoring (β = −0.523). Female patients exhibited higher concern for healthcare providers (β = 1.172) compared to males. Younger and shorter‐course patients prioritized antihyperglycemic effectiveness (β = 3.330, β = 1.510), while older patients preferred multidisciplinary management (β = 1.186) and opposed increased monitoring frequency (β = −0.703). Patients with higher educational backgrounds showed greater acceptance of continuous glucose monitoring (β = 1.983), and those with higher annual income placed more emphasis on glycemic control rate.Conclusion: Treatment preferences of hospitalized diabetes patients are mainly influenced by antihyperglycemic effectiveness, adverse reactions, healthcare providers, and individual characteristics. Comprehensive consideration and an individualized therapy strategy should be given when constructing a hospital‐wide glycemic control programme.

Objective: This study constructed a tertiary hospital-community health service center diabetes linkage management model with the participation of clinical pharmacists, assessed the changes in clinical indicators and medication treatment of patients with type 2 diabetes before and after the implementation of the model, and evaluated the model, with a view to providing a model reference in the participation of clinical pharmacists in the management of type 2 diabetes and other chronic diseases. Given the current situation that diabetes management at the community level in China is still unsatisfactory, with an HbA1c control rate of less than 10% compared to about 50% in tertiary hospitals, there is an urgent need to explore innovative, pharmacist-involved models to bridge this gap.Methods: Using the principle of randomization, patients who met the enrollment criteria were divided into the experimental group and the control group. A total of 210 patients were enrolled from three community health service centers in Nanjing in collaboration with Drum Tower Hospital, and were followed up for 12 months. Clinical indicators and medication adherence were used as evaluation endpoints to compare the differences in management effects between the two groups. This study was registered with the Chinese Clinical Trial Registry (ChiCTR2300074444).Results: Under the diabetes linkage management model, patients in the intervention group showed improvement in blood glucose, glycated hemoglobin and other indicators compared with the control group; the medication adherence score of patients in the intervention group was significantly higher than that of the control group.Conclusion: The clinical efficacy and medication level of diabetic patients were significantly improved after management by this management model, which provides a reference for clinical pharmacists to carry out pharmacy services in the context of hierarchical diagnosis and treatment. This model may contribute to narrowing the quality gap between tertiary hospitals and community health service centers in diabetes care.

Objective: This study aims to assess the compliance with anti-hypoglycemic drugs among postpartum patients with gestational diabetes mellitus (GDM) through a questionnaire survey, and to examine the factors that may influence this adherence. The goal is to enhance pharmacists’ medication practices and improve glycemic control.Method: Based on the theory of risk perception attitude framework, the study selected pregnant women who delivered at Nanjing DrumTower Hospital’s obstetrics department from 2020 to 2022 and were diagnosed with GDM as the research subjects. The Morisky Medication Adherence Scale was used to evaluate their medication adherence. The correlation matrix was used to express whether there is a correlation between risk perception, self-efficacy, and medication adherence. Finally, a linear hierarchical regression model was used to present the moderating effect of self-efficacy on the relationship between risk perception and medication adherence.Results: A total of 80 postpartum GDM patients receiving medication intervention were included in the study to assess medication adherence. The median score on the MMAS-8 scale was 3.75 (3.50, 5.50). The results of the Spearman test showed a positive correlation between GDM patients’ perception of future diabetes risk and postpartum medication adherence (r= 0.778, P<0.001). Additionally, self-efficacy was also positively correlated with medication adherence (r= 0.631, P<0.001). The results of the linear stratified regression model indicated that self-efficacy moderates the relationship between risk perception and medication adherence.Conclusion: The results of the MMAS-8 scale survey indicate poor medication adherence among postpartum GDM patients, with a significantly lower rate of good medication adherence compared to general T2DM patients. The stratified regression analysis demonstrates that risk perception and self-efficacy jointly influence postpartum medication adherence, and the risk perception attitude model can predict medication adherence among GDM patients postpartum.