Background and Objectives: Lung cancer remains a leading cause of cancer mortality worldwide. Accurately classifying benign pulmonary nodules and malignant ones is crucial for early diagnosis and improved patient outcomes. The purpose of this study is to explore the deep-learning model of ResNet combined with a convolutional block attention module (CBAM) for the differentiation between benign and malignant lung cancer, based on computed tomography (CT) images, morphological features, and clinical information. Methods and materials: In this study, 8241 CT slices containing pulmonary nodules were retrospectively included. A random sample comprising 20% (n = 1647) of the images was used as the test set, and the remaining data were used as the training set. ResNet combined CBAM (ResNet-CBAM) was used to establish classifiers on the basis of images, morphological features, and clinical information. Nonsubsampled dual-tree complex contourlet transform (NSDTCT) combined with SVM classifier (NSDTCT-SVM) was used as a comparative model. Results: The AUC and the accuracy of the CBAM-ResNet model were 0.940 and 0.867, respectively, in test set when there were only images as inputs. By combining the morphological features and clinical information, CBAM-ResNet shows better performance (AUC: 0.957, accuracy: 0.898). In comparison, a radiomic analysis using NSDTCT-SVM achieved AUC and accuracy values of 0.807 and 0.779, respectively. Conclusions: Our findings demonstrate that deep-learning models, combined with additional information, can enhance the classification performance of pulmonary nodules. This model can assist clinicians in accurately diagnosing pulmonary nodules in clinical practice.

Premixed insulin is the most commonly used insulin in China. This trial compared the efficacy and safety of once-daily insulin glargine 100 U/mL (Gla-100) + oral antihyperglycemic drugs (OADs) and twice-daily insulin aspart 70/30 (Asp 30) + OAD in T2D patients. Chinese adults with T2D receiving stable doses of metformin and 1-2 OADs with HbA1c 7.5%-11.0% were enrolled and entered a 7-10 day SIT period in which they were treated with basal-bolus to achieve a fasting blood glucose (FBG) <7 mmol/L and 2-hour postprandial glucose (2hPG) <10 mmol/L. Patients were then randomized 1:1 to receive Gla-100 + OADs (n=192) or Asp 30 + OAD (n=192) for 24 weeks. Baseline characteristics were balanced across groups. Mean (SD) age was 54.2 (8.8) years, BMI was 26.0 (3.1) kg/m², and duration of diabetes was 6.8 (3.0) years. At week 24, the least square mean (SE) change from baseline in HbA1c was -1.72% (0.07) and -1.70% (0.07) in the Gla-100 and Asp 30 groups, respectively (Table); group difference (-0.01%; 95% CI -0.20, 0.17) met the pre-specified non-inferiority criteria (upper bound 95% CI <0.4%). All hypoglycemia events were significantly lower in the Gla-100 group. In conclusion, compared with Asp 30 + OAD, Gla-100 + OAD showed similar efficacy but lower hypoglycemia risk in Chinese T2D patients. Disclosure Y. Mu: Speaker’s Bureau; Self; Abbott, Boehringer Ingelheim Pharmaceuticals, Inc., Lilly Diabetes, Novo Nordisk Inc., Sanofi-Aventis. J. Liu: Employee; Self; Sanofi China. X. Zhang: None. N. Cui: Employee; Self; Sanofi China. H. Yin: None. L. Guo: Consultant; Self; AstraZeneca, Bayer Healthcare Pharmaceuticals Inc., BD, Eli Lilly and Company, Merck & Co., Inc., Merck Sharp & Dohme Corp., Novartis AG, Novo Nordisk, Sanofi China. H. Wan: None. J. Wang: None. B. Xu: None. G. Wang: None. C. Jiang: None. L. Liang: None. W. Feng: Employee; Self; Sanofi China. Funding Sanofi China (NCT03359837)

Trace element is essential for the proper growth, development, and physiology of the organism and the primary source of trace element is dietary intake. Among trace elements, the role of copper (Cu), selenium (Se), and zinc (Zn) in the pathogenesis of diabetes have been widely recognized. However, there is little information available about these 3 trace elements across the different states of glucose tolerance. We examined associations between serum levels of trace elements - Cu, Zn, and Se with various stages of glucose tolerance in a representative, cross-sectional sample of US adults. Our sample included 5,087 adults (≥20 years) with available serum concentrations of Cu, Zn and Se as well as states of glucose tolerance, defined by history, HbA1c, fasting, and 2-hour plasma glucose concentrations. Serum concentrations of trace elements were compared with glucose tolerance status with the consideration of covariates. Regression analyses was used to examine the relationship of trace elements with HOMA-IR, HOMA-B, and BMI in non-diabetic subjects with the consideration of appropriate covariates. Serum Se (P<0.0001) and Zn (P<0.0001) concentrations differed significantly among 3 groups based on the states of glucose tolerance, while no difference was noted in serum Cu concentration. In non-diabetic subjects, serum Cu concentration was positively correlated with BMI (P<0.0001) with a possible compensatory increased beta cell function (P=0.018). Serum Se concentration was negatively correlated with insulin resistance (P=0.016) but not with beta cell function or BMI. Serum Zn concertation was negatively correlated with beta cell function (P=0.0023) and BMI (P=0.018), but not with insulin resistance. We found that a higher serum concentration of trace elements was associated with negative glucose and fuel homeostasis in a non-deficiency population possibly through different mechanisms. Although the casual relationship remains to be elucidated, we recommend against trace element supplementation in a non-deficiency population.