Developing Deep LSTMs With Later Temporal Attention for Predicting COVID-19 Severity, Clinical Outcome, and Antibody Level by Screening Serological Indicators Over Time.

OBJECTIVE: The clinical course of COVID-19, as well as the immunological reaction, is notable for its extreme variability. Identifying the main associated factors might help understand the disease progression and physiological status of COVID-19 patients. The dynamic changes of the antibody against Spike protein are crucial for understanding the immune response. This work explores a temporal attention (TA) mechanism of deep learning to predict COVID-19 disease severity, clinical outcomes, and Spike antibody levels by screening serological indicators over time. METHODS: We use feature selection techniques to filter feature subsets that are highly correlated with the target. The specific deep Long Short-Term Memory (LSTM) models are employed to capture the dynamic changes of disease severity, clinical outcome, and Spike antibody level. We also propose deep LSTMs with a TA mechanism to emphasize the later blood test records because later records often attract more attention from doctors. RESULTS: Risk factors highly correlated with COVID-19 are revealed. LSTM achieves the highest classification accuracy for disease severity prediction. Temporal Attention Long Short-Term Memory (TA-LSTM) achieves the best performance for clinical outcome prediction. For Spike antibody level prediction, LSTM achieves the best permanence. CONCLUSION: The experimental results demonstrate the effectiveness of the proposed models. The proposed models can provide a computer-aided medical diagnostics system by simply using time series of serological indicators.

[The increased expression of stromal cell-derived factor-1 (SDF-1) alleviates airway inflammation in asthmatic rats by promoting the migration of bone marrow mesenchymal stem cells (BMSCs)].

Objective To observe the correlation of stromal cell-derived factor 1 (SDF-1) with bone marrow mesenchymal stem cell (BMSCs) migration and airway inflammation in asthmatic rats. Methods Twenty-four clean SD rats were randomly divided into normal control (NC) group, model control (MC) group, and BMSCs group. Asthma model was established by OVA. In the BMSCs group, 1×106 BMSCs (1 mL) were transplanted into the tail vein on the day the model was completed. Pathological changes in lung tissues were evaluated by HE staining. The count of inflammatory cells in bronchoalveolar lavage fluid(BALF) was evaluated by Wright-Giemsa staining. The concentrations of IL-4, IL-5, IL-13, IgE, IgG1 and IgG2a in BALF were tested by ELISA. The expression of SDF-1 and STAT6 mRNA in lung tissue was measured by real time quantitative PCR. The expression of SDF-1 protein in bronchial epithelial cells were evaluated by Immunofluorescence staining. The expression of SDF-1 and STAT6 protein in lung tissue were measured by Western blot analysis. Results Compared with the normal group, the number of relative inflammatory cell counts and the concentrations of IL-4, IL-5, IL-13, IgE, IgG1, and IgG2a in BALF of the MC group increased significantly. The mRNA and protein expression of SDF-1 and STAT6 in lung tissue increased significantly. Compared with the MC group, inflammatory cells and inflammatory cytokines of BALF of BMSCs group were decreased in numbers, as was the expression of SDF-1 and STAT6 in lung tissues. Compared with the MC group, the expression of SDF-1 gene in lung tissues was increased, as was the expression of SDF-1 protein in bronchial epithelial cells. Conclusion In the process of asthmatic inflammation, the expression of chemokine SDF-1 in the damaged site increases, and promotes the migration of exogenous BMSCs to the lung tissue of asthmatic rats. BMSCs can regulate immune imbalance of Th1/Th2 cells by homing to damaged lung tissue, thus inhibiting asthmatic airway inflammation.

Authorized Shared Electronic Medical Record System with Proxy Re-Encryption and Blockchain Technology.

With the popularity of the internet 5G network, the network constructions of hospitals have also rapidly developed. Operations management in the healthcare system is becoming paperless, for example, via a shared electronic medical record (EMR) system. A shared electronic medical record system plays an important role in reducing diagnosis costs and improving diagnostic accuracy. In the traditional electronic medical record system, centralized database storage is typically used. Once there is a problem with the data storage, it could cause data privacy disclosure and security risks. Blockchain is tamper-proof and data traceable. It can ensure the security and correctness of data. Proxy re-encryption technology can ensure the safe sharing and transmission of relatively sensitive data. Based on the above situation, we propose an electronic medical record system based on consortium blockchain and proxy re-encryption to solve the problem of EMR security sharing. Electronic equipment in this process is connected to the blockchain network, and the security of data access is ensured through the automatic execution of blockchain chaincodes; the attribute-based access control method ensures fine-grained access to the data and improves the system security. Compared with the existing electronic medical records based on cloud storage, the system not only realizes the sharing of electronic medical records, but it also has advantages in privacy protection, access control, data security, etc.

Exploring Misclassification Information for Fine-Grained Image Classification.

Fine-grained image classification is a hot topic that has been widely studied recently. Many fine-grained image classification methods ignore misclassification information, which is important to improve classification accuracy. To make use of misclassification information, in this paper, we propose a novel fine-grained image classification method by exploring the misclassification information (FGMI) of prelearned models. For each class, we harvest the confusion information from several prelearned fine-grained image classification models. For one particular class, we select a number of classes which are likely to be misclassified with this class. The images of selected classes are then used to train classifiers. In this way, we can reduce the influence of irrelevant images to some extent. We use the misclassification information for all the classes by training a number of confusion classifiers. The outputs of these trained classifiers are combined to represent images and produce classifications. To evaluate the effectiveness of the proposed FGMI method, we conduct fine-grained classification experiments on several public image datasets. Experimental results prove the usefulness of the proposed method.

A novel biopolymer device fabricated by 3D printing for simplifying procedures of pancreaticojejunostomy.

The purpose of our research was to verify the feasibility and effectiveness of a novel three-dimensional printed biopolymer device (3DP-BPD) for duct-to-mucosa pancreaticojejunostomy (PJ) in minipigs. Polylactic acid (PLA) was selected as the raw materials for 3DP-BPD. Three components of a 3DP-BPD were designed and manufactured: hollow stent, supporting disk, and nut. A pancreatic duct dilation model was developed in six minipigs. After 4 weeks, minipigs underwent operations with duct-to-mucosa PJ using 3DP-BPD. The operation time and postoperative complications were analyzed. The anastomotic sites were evaluated grossly 4 weeks and 24 weeks after PJ, and the histological evaluation of anastomotic sites was performed 24 weeks after PJ. The operation time of six stitches duct-to-mucosa PJ was 9.1 ±â€¯1.7 min. All minipigs survived without any adverse events like postoperative pancreatic fistula (POPF). Serum C reactive protein (CRP) and procalcitonin (PCT) levels were normal, and the anastomotic sites were connected tightly on gross observation and touch at 4 weeks and 24 weeks. Histological examinations indicated that the tissues were continuous between the pancreas and the jejunum. The use of 3DP-BPD did not increase the risk of severe local inflammation and POPF. 3DP-BPD used for duct-to-mucosa PJ is more convenient and clinically feasible for pancreatoenteric reconstruction.

Epidemiology of appendicitis and appendectomy for the low-income population in Taiwan, 2003-2011.

BACKGROUND: Although numerous epidemiological studies on appendicitis have been conducted worldwide, only a few studies have paid attention to the effect of socioeconomic status on appendicitis, particularly studies focusing on the low-income population (LIP). METHODS: We analyzed the epidemiological features of appendicitis in Taiwan using data from the National Health Insurance Research Database from 2003 to 2011. All cases diagnosed as appendicitis were enrolled. RESULTS: Between 2003 and 2011, 2,916 patients from the LIP and 209,206 patients from the normal population (NP) were diagnosed with appendicitis. Our finding revealed that the ratios of comorbidities, complicated appendicitis, and readmissions in LIP patients were slightly higher than those of NP patients. LIP patients were more likely to live in suburban and rural areas, and hence a higher proportion of them were hospitalized in a district or regional hospital compared with NP patients. The crucially finding was that the overall incidence ratios of appendicitis, acute appendicitis, and perforated appendicitis in the LIP were substantially higher than those in the NP (36.25%, 35.33%, and 37.28%, respectively). The mean LOS in LIP patients was longer than that of NP patients. The overall case-fatality ratio of appendectomy in the LIP was higher when compared with the NP (0.41% versus 0.12%, p < 0.05). We also observed that appendicitis was occurred frequently in male patients, with a higher incidence for those aged 15-29 years in both the LIP and NP. The incidences of incidental appendectomy showed a decreasing trend in both the LIP and NP. Finally, a valuable discovery was that the total hospital cost was comparable between the laparoscopic appendectomy (LA) and open appendectomy (OA) (1,178 ± 13 USD versus 1,191 ± 19 USD, p < 0.05) in LIP patients because they saved more hospitalization costs than NP patients when the previous one chose the LA. CONCLUSION: This study confirmed that a lower socioeconomic status has significantly negative impact on the occurrence and treatment of appendicitis and appendectomy. In terms of hospital costs and LOS, LIP patients benefit more from the LA approach than they do from the OA approach in the treatment of appendicitis.