Fractures affect nearly 9.45% of the South Korean population, with radiography being the primary diagnostic tool. This research employs a machine-learning methodology that integrates HyperColumn techniques with the convolutional block attention module (CBAM) to enhance fracture detection in X-ray radiographs. Utilizing the EfficientNet-B0 and DenseNet169 models bolstered by the HyperColumn and the CBAM, distinct improvements in fracture site prediction emerge. Significantly, when HyperColumn and CBAM integration is applied, both DenseNet169 and EfficientNet-B0 showed noteworthy accuracy improvements, with increases of approximately 0.69% and 0.70%, respectively. The HyperColumn-CBAM-DenseNet169 model particularly stood out, registering an uplift in the AUC score from 0.8778 to 0.9145. The incorporation of Grad-CAM technology refined the heatmap’s focus, achieving alignment with expert-recognized fracture sites and alleviating the deep-learning challenge of heavy reliance on bounding box annotations. This innovative approach signifies potential strides in streamlining training processes and augmenting diagnostic precision in fracture detection.

Introduction: The association between microalbuminuria and cardiovascular disease (CVD) is accumulating in various patient populations. However, when stratified by sex, the relationship between microalbuminuria and CVD remains unclear. Method: We obtained data from the 2011–2014 and 2019–2020 Korea National Health and Nutrition Examination Survey (KNHANES). Microalbuminuria was measured based on spot urine albumin-creatinine ratio (UACR). The Framingham risk score (FRS) model was implemented to evaluate the CVD risk. Linear and logistic regression models were used to identify the associations of microalbuminuria status with cardiometabolic predictors and CVD status determined by the FRS score. Results: Among 19,340 representative Korean participants, the (UACR) in Korean women and men with history of CVD was higher than in those without history of CVD. Among patients without history of CVD, multivariate regression analysis showed that a high UACR was related to older age, lower high-density lipoprotein cholesterol level, higher total cholesterol level, higher systolic blood pressure, higher prevalence of current smoking, higher prevalence of diabetes, and higher anti-hypertensive medication use in both women and men. The UACR showed a positive linear correlation with the Framingham risk score in both women and men. Conclusion: The presence of microalbuminuria was significantly associated with the cardiometabolic risk factors and the increased risk of CVD evaluated by FRS model in both women and men in a nationally representative sample of Korea.

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Previously, we constructedWe applied the LDL-DNN model to an electronic health record (EHR) system in real time (deep LDL-EHR). a deep neural network (DNN) model for estimating low-density lipoprotein (LDL) cholesterol (LDL-DNN). Objective: We applied the LDL-DNN model to an electronic health record (EHR) system in real time (deep LDL-EHR). Methods: The Korea National Health and Nutrition Examination Survey and the Wonju Severance Christian Hospital (WSCH) datasets were used as training and testing datasets, respectively. We measured the model’s performance by using four indices, including bias, root mean square error, P10 to P30, and concordance. For transfer learning (TL), we pre-trained the DNN model using a training dataset, and fine-tuned it using 30% of the testing datasets. Results: Based on the four accuracy criteria, the DNN-EHR model generated inaccurate results compared to other methods for LDL-C estimation. By comparing the training and testing datasets, we found there to be an overfitting problem. We revised the LDL-DNN model using the TL algorithms and randomly selected sub-data from the WSCH dataset. As a result, the LDL-DNN-TL model exhibited the best performance among the other methods. Conclusions: The LDL-DNN-TL model is expected to be suitable for routine real-time clinical application for LDL-C estimation in a clinical laboratory.

Lee KH, et al. Yonsei Med J. 2022 Jan;63(Suppl):S84-S92. https://doi.org/10.3349/ymj.2022.63.S84

(1) Background: The health implications associated with the metabolically healthy obese (MHO) phenotype, in particular related to symptoms of depression, are still not clear. the purpose of this study is to check whether depression and metabolic status are relevant by classifying them into four groups in accordance with the MHO diagnostic standard. Other impressions seen were the differences between sexes and the effects of the MHO on the occurrence of depression. (2) Methods: A sample of 3,586,492 adult individuals from the National Health Insurance Database of Korea was classified into four categories by their metabolic status and body mass index: (1) metabolically healthy non-obese (MHN); (2) metabolically healthy obese (MHO); (3) metabolically unhealthy non-obese (MUN); and (4) metabolically unhealthy obese (MUO). Participants were followed for six to eight years for new incidences of depression. The statistical significance of the general characteristics of the four groups, as well as the mean differences in metabolic syndrome risk factors, was assessed with the use of a one-way analysis of variance (ANOVA). (3) Results: The MHN ratio in women was higher than in men (men 39.3%, women 55.2%). In both men and women, depression incidence was the highest among MUO participants (odds ratio (OR) = 1.01 in men; OR = 1.09 in women). It was concluded as well that, among the risk factors of metabolic syndrome, waist circumference was the most related to depression. Among the four groups, the MUO phenotype was the most related to depression. Furthermore, in women participants, MHO is also related to a higher risk of depressive symptoms. These findings indicate that MHO is not a totally benign condition in relation to depression in women. (4) Conclusion: Therefore, reducing metabolic syndrome and obesity patients in Korea will likely reduce the incidence of depression.

Inference of co-expression network and identification of disease-related modules and gene sets can help us understand disease-related molecular pathophysiology. We aimed to identify a cardiovascular disease (CVD)-related transcriptomic signature, specifically, in peripheral blood tissue, based on differential expression (DE) and differential co-expression (DcoE) analyses. Publicly available blood sample datasets for coronary artery disease (CAD) and acute coronary syndrome (ACS) statuses were integrated to establish a co-expression network. A weighted gene co-expression network analysis was used to construct modules that include genes with highly correlated expression values. The DE criterion is a linear regression with module eigengenes for module-specific genes calculated from principal component analysis and disease status as the dependent and independent variables, respectively. The DcoE criterion is a paired t-test for intramodular connectivity between disease and matched control statuses. A total of 21 and 23 modules were established from CAD status- and ACS-related datasets, respectively, of which six modules per disease status (i.e., obstructive CAD and ACS) were selected based on the DE and DcoE criteria. For each module, gene–gene interactions with extremely high correlation coefficients were individually selected under the two conditions. Genes displaying a significant change in the number of edges (gene–gene interaction) were selected. A total of 6, 10, and 7 genes in each of the three modules were identified as potential CAD status-related genes, and 14 and 8 genes in each of the two modules were selected as ACS-related genes. Our study identified gene sets and genes that were dysregulated in CVD blood samples. These findings may contribute to the understanding of CVD pathophysiology.