To explore the application effect of the deep learning (DL) network model in the Internet of Things (IoT) database query and optimization. This study first analyzes the architecture of IoT database queries, then explores the DL network model, and finally optimizes the DL network model through optimization strategies. The advantages of the optimized model in this study are verified through experiments. Experimental results show that the optimized model has higher efficiency than other models in the model training and parameter optimization stages. Especially when the data volume is 2000, the model training time and parameter optimization time of the optimized model are remarkably lower than that of the traditional model. In terms of resource consumption, the Central Processing Unit and Graphics Processing Unit usage and memory usage of all models have increased as the data volume rises. However, the optimized model exhibits better performance on energy consumption. In throughput analysis, the optimized model can maintain high transaction numbers and data volumes per second when handling large data requests, especially at 4000 data volumes, and its peak time processing capacity exceeds that of other models. Regarding latency, although the latency of all models increases with data volume, the optimized model performs better in database query response time and data processing latency. The results of this study not only reveal the optimized model\'s superior performance in processing IoT database queries and their optimization but also provide a valuable reference for IoT data processing and DL model optimization. These findings help to promote the application of DL technology in the IoT field, especially in the need to deal with large-scale data and require efficient processing scenarios, and offer a vital reference for the research and practice in related fields.

OBJECTIVE: To report the cost of hospitalization and the associated risk factors for rheumatic diseases in middle-aged and elderly patients in China.
METHODS: The study participants included inpatients from hospitals of various levels in the Jiangsu Province Health Account database in 2016. Participants were selected by using a multistage sampling method. Patients <45 years of age were excluded, and patients hospitalized for rheumatic diseases were identified according to the 10th edition of the International Classification of Diseases. Generalized linear models were used to analyze the sociodemographic characteristics related to the hospitalization costs of patients with rheumatic diseases.
RESULTS: The study included 3696 patients. The average cost of hospitalization for patients with rheumatic diseases was USD 4038.63. Female sex, a long length of stay, age between 65 and 74 years, free medical care, not being covered by the Urban-Rural Residents Basic Medical Insurance, and a high hospital level were associated with high hospitalization costs.
CONCLUSIONS: This study examined hospitalization costs and relevant influencing factors in middle-aged and elderly patients with rheumatic disease in China. Our findings are useful for further research on costs of disease and the economic evaluation of strategies to prevent rheumatic disease.

UNASSIGNED: Pesticides are widely used in agricultural activities. Although pesticide use is known to cause damage to the human body, its relationship with thyroid function remains unclear. Therefore, this study aimed to investigate the association between pesticide exposure and thyroid function.
UNASSIGNED: The Chinese database used included 60 patients with pyrethroid poisoning and 60 participants who underwent health checkups between June 2022 and June 2023. The NHANES database included 1,315 adults enrolled from 2007 to 2012. The assessed pesticide and their metabolites included 2,4-dichlorophenoxyacetic acid (2,4-D), 4-fluoro-3-phenoxybenzoic acid (4F3PB), para-nitrophenol (PN), 3-phenoxybenzoic acid (3P), and trans-dichlorovinyl-dimethylcyclopropane carboxylic acid (TDDC). The evaluated indicators of thyroid function were measured by the blood from the included population. The relationship between pesticide exposure and thyroid function indexes was investigated using linear regression, Bayesian kernel machine regression (BKMR), restricted cubic spline (RCS), and weighted quantile sum (WQS) models.
UNASSIGNED: The Chinese data showed that pesticide exposure was negatively correlated with the thyroid function indicators FT4, TT4, TgAb, and TPOAb (all p < 0.05). The BKMR model analysis of the NHANES data showed that the metabolic mixture of multiple pesticides was negatively associated with FT4, TSH, and Tg, similar to the Chinese database findings. Additionally, linear regression analysis demonstrated positive correlations between 2,4-D and FT3 (p = 0.041) and 4F3PB and FT4 (p = 0.003), whereas negative associations were observed between 4F3PB and Tg (p = 0.001), 4F3PB and TgAb (p = 0.006), 3P and TgAB (p = 0.006), 3P and TPOAb (p = 0.03), PN and TSH (p = 0.003), PN and TT4 (p = 0.031), and TDDC and TPOAb (p < 0.001). RCS curves highlighted that most pesticide metabolites were negatively correlated with thyroid function indicators. Finally, WQS model analysis revealed significant differences in the weights of different pesticide metabolites on the thyroid function indexes.
UNASSIGNED: There is a significant negative correlation between pesticide metabolites and thyroid function indicators, and the influence weights of different pesticide metabolites on thyroid function indicators are significantly different. More research is needed to further validate the association between different pesticide metabolites and thyroid disease.

BACKGROUND: Coronavirus disease 2019 (COVID-19) has resulted in substantial morbidity and mortality globally. The National Database of Health Insurance Claims and Specific Health Checkups of Japan (NDB) covers 99.9% of health insurance claim receipts by general practitioners. The purpose of this study is to investigate the nationwide number of inpatient orthopedic surgeries in Japan during the effect of state of emergency (SoE) due to COVID-19.
METHODS: The NDB has been publicly available since 2014. We retrospectively reviewed the NDB from April 2019 to March 2022. We gathered the monthly number of all inpatient orthopedic surgeries. We also classified orthopedic surgeries into the following 11 categories by using K-codes, Japanese original surgery classification: fracture, arthroplasty, spine, arthroscopy, hardware removal, hand, infection/amputation, ligament/tendon, tumor, joint, and others. By using the average number from April to December 2019 as the reference period, we investigated the increase or decrease orthopedic surgeries during the pandemic period.
RESULTS: The NDB showed that the average number of total inpatient orthopedic surgeries during the reference period was 115,343 per month. In May 2020, monthly inpatient orthopedic surgeries decreased by 29.6% to 81,169 surgeries, accounting for 70.3% of the reference period. The second SoE in 2021 saw no change, while the third and fourth SoEs showed slight decreases compared to the reference period. Hardware removal and tumor surgeries in May 2020 decreased to 45.3% and 45.5%, respectively, while fracture surgeries had relatively small decreases.
CONCLUSIONS: According to NDB, approximately 1.3 million orthopedic inpatient surgeries were performed or claimed in a year in Japan. In May 2020, the first SoE period of the COVID-19 pandemic, the number of inpatient orthopedic surgeries in Japan decreased by 30%. Meanwhile, the decrease was relatively small during the SoE periods in 2021.

To examine the prevalence of comorbidities in Chinese urticaria patients and assess medication use patterns across different ages (6-11 years, 12-17 years, above 18 years), a retrospective cohort study was performed in 192,647 urticaria patients within the Health Database. After 1:1 propensity score matching, 166,921 people were divided into the urticaria group and the control group, and the follow-up data were collected within 2 years. During the 12-month and 24-month follow-up period, significant comorbidities identified included allergic rhinitis and asthma, with distinct patterns observed across age groups. Chronic urticaria patients often have complications, such as allergic rhinitis, upper respiratory infection, oropharyngeal infection, and dental caries. The study underscores the need for age-specific treatment strategies in urticaria management.

Heart rate variability (HRV) is related to cardiac vagal control and emotional regulation and an index for cardiac vagal control and cardiac autonomic activity. This study aimed to develop the Taiwan HRV normative database covering individuals aged 20 to 70 years and to assess its diagnosing validity in patients with major depressive disorder (MDD). A total of 311 healthy participants were in the HRV normative database and divided into five groups in 10-year age groups, and then the means and standard deviations of the HRV indices were calculated. We recruited 272 patients with MDD for cross-validation, compared their HRV indices with the normative database, and then converted them to Z-scores to explore the deviation of HRV in MDD patients from healthy groups. The results found a gradual decline in HRV indices with advancing age in the HC group, and females in the HC group exhibit higher cardiac vagal control and parasympathetic activity than males. Conversely, patients in the MDD group demonstrate lower HRV indices than those in the HC group, with their symptoms of depression and anxiety showing a negative correlation with HRV indices. The Taiwan HRV normative database has good psychometric characteristics of cross-validation.

BACKGROUND: Previous studies have shown that an elevated triglyceride-glucose (TyG) index was associated with all-cause mortality in both general adult individuals and critically ill adult patients. However, the relationship between the TyG index and clinical prognosis in pediatric patients admitted to the intensive care unit (ICU) remains unknown. We aimed to investigate the association of the TyG index with in-hospital all-cause mortality in critically ill pediatric patients.
METHODS: A total of 5706 patients in the Pediatric Intensive Care database were enrolled in this study. The primary outcome was 30-day in-hospital all-cause mortality, and secondary outcome was 30-day in-ICU all-cause mortality. The restricted cubic spline (RCS) curves and two-piecewise multivariate Cox hazard regression models were performed to explore the relationship between the TyG index and outcomes.
RESULTS: The median age of the study population was 20.5 [interquartile range (IQR): 4.8, 63.0] months, and 3269 (57.3%) of the patients were male. The mean TyG index level was 8.6 ± 0.7. A total of 244 (4.3%) patients died within 30 days of hospitalization during a median follow-up of 11 [7, 18] days, and 236 (4.1%) patients died in ICU within 30 days of hospitalization during a median follow-up of 6 [3, 11] days. The RCS curves indicated a U-shape association between the TyG index and 30-day in-hospital and in-ICU all-cause mortality (both P values for non-linear < 0.001). The risk of 30-day in-hospital all-cause mortality was negatively correlated with the TyG index until it bottoms out at 8.6 (adjusted hazard ratio [HR], 0.72, 95% confidence interval [CI] 0.55-0.93). However, when the TyG index was higher than 8.6, the risk of primary outcome increased significantly (adjusted HR, 1.51, 95% CI 1.16-1.96]). For 30-day in-ICU all-cause mortality, we also found a similar relationship (TyG < 8.6: adjusted HR, 0.75, 95% CI 0.57-0.98; TyG ≥ 8.6: adjusted HR, 1.42, 95% CI 1.08-1.85). Those results were consistent in subgroups and various sensitivity analysis.
CONCLUSIONS: Our study showed that the association between the TyG index and 30-day in-hospital and in-ICU all-cause mortality was nonlinear U-shaped, with a cutoff point at the TyG index of 8.6 in critically ill pediatric patients. Our findings suggest that the TyG index may be a novel and important factor for the short-term clinical prognosis in pediatric patients.

BACKGROUND: This study aims to construct a model predicting the probability of RF in AECOPD patients upon hospital admission.
METHODS: This study retrospectively extracted data from MIMIC-IV database, ultimately including 3776 AECOPD patients. The patients were randomly divided into a training set (n = 2643) and a validation set (n = 1133) in a 7:3 ratio. First, LASSO regression analysis was used to optimize variable selection by running a tenfold k-cyclic coordinate descent. Subsequently, a multifactorial Cox regression analysis was employed to establish a predictive model. Thirdly, the model was validated using ROC curves, Harrell\'s C-index, calibration plots, DCA, and K-M curve.
RESULTS: Eight predictive indicators were selected, including blood urea nitrogen, prothrombin time, white blood cell count, heart rate, the presence of comorbid interstitial lung disease, heart failure, and the use of antibiotics and bronchodilators. The model constructed with these 8 predictors demonstrated good predictive capabilities, with ROC curve areas under the curve (AUC) of 0.858 (0.836-0.881), 0.773 (0.746-0.799), 0.736 (0.701-0.771) within 3, 7, and 14 days in the training set, respectively and the C-index was 0.743 (0.723-0.763). Additionally, calibration plots indicated strong consistency between predicted and observed values. DCA analysis demonstrated favorable clinical utility. The K-M curve indicated the model\'s good reliability, revealed a significantly higher RF occurrence probability in the high-risk group than that in the low-risk group (P < 0.0001).
CONCLUSIONS: The nomogram can provide valuable guidance for clinical practitioners to early predict the probability of RF occurrence in AECOPD patients, take relevant measures, prevent RF, and improve patient outcomes.

Heart disease is the world\'s leading cause of death. Diagnostic models based on electrocardiograms (ECGs) are often limited by the scarcity of high-quality data and issues of data imbalance. To address these challenges, we propose a conditional generative adversarial network (CECG-GAN). This strategy enables the generation of samples that closely approximate the distribution of ECG data. Additionally, CECG-GAN addresses waveform jitter, slow processing speeds, and dataset imbalance issues through the integration of a transformer architecture. We evaluated this approach using two datasets: MIT-BIH and CSPC2020. The experimental results demonstrate that CECG-GAN achieves outstanding performance metrics. Notably, the percentage root mean square difference (PRD) reached 55.048, indicating a high degree of similarity between generated and actual ECG waveforms. Additionally, the Fréchet distance (FD) was approximately 1.139, the root mean square error (RMSE) registered at 0.232, and the mean absolute error (MAE) was recorded at 0.166.

暂无摘要。