Analyzing and Forecasting Pediatric Fever Clinic Visits in High Frequency Using Ensemble Time-Series Methods After the COVID-19 Pandemic in Hangzhou, China: Retrospective Study.

BACKGROUND: The COVID-19 pandemic has significantly altered the global health and medical landscape. In response to the outbreak, Chinese hospitals have established 24-hour fever clinics to serve patients with COVID-19. The emergence of these clinics and the impact of successive epidemics have led to a surge in visits, placing pressure on hospital resource allocation and scheduling. Therefore, accurate prediction of outpatient visits is essential for informed decision-making in hospital management. OBJECTIVE: Hourly visits to fever clinics can be characterized as a long-sequence time series in high frequency, which also exhibits distinct patterns due to the particularity of pediatric treatment behavior in an epidemic context. This study aimed to build models to forecast fever clinic visit with outstanding prediction accuracy and robust generalization in forecast horizons. In addition, this study hopes to provide a research paradigm for time-series forecasting problems, which involves an exploratory analysis revealing data patterns before model development. METHODS: An exploratory analysis, including graphical analysis, autocorrelation analysis, and seasonal-trend decomposition, was conducted to reveal the seasonality and structural patterns of the retrospective fever clinic visit data. The data were found to exhibit multiseasonality and nonlinearity. On the basis of these results, an ensemble of time-series analysis methods, including individual models and their combinations, was validated on the data set. Root mean square error and mean absolute error were used as accuracy metrics, with the cross-validation of rolling forecasting origin conducted across different forecast horizons. RESULTS: Hybrid models generally outperformed individual models across most forecast horizons. A novel model combination, the hybrid neural network autoregressive (NNAR)-seasonal and trend decomposition using Loess forecasting (STLF), was identified as the optimal model for our forecasting task, with the best performance in all accuracy metrics (root mean square error=20.1, mean absolute error=14.3) for the 15-days-ahead forecasts and an overall advantage for forecast horizons that were 1 to 30 days ahead. CONCLUSIONS: Although forecast accuracy tends to decline with an increasing forecast horizon, the hybrid NNAR-STLF model is applicable for short-, medium-, and long-term forecasts owing to its ability to fit multiseasonality (captured by the STLF component) and nonlinearity (captured by the NNAR component). The model identified in this study is also applicable to hospitals in other regions with similar epidemic outpatient configurations or forecasting tasks whose data conform to long-sequence time series in high frequency exhibiting multiseasonal and nonlinear patterns. However, as external variables and disruptive events were not accounted for, the model performance declined slightly following changes in the COVID-19 containment policy in China. Future work may seek to improve accuracy by incorporating external variables that characterize moving events or other factors as well as by adding data from different organizations to enhance algorithm generalization.

Development of lung segmentation method in x-ray images of children based on TransResUNet.

Background: Chest x-ray (CXR) is widely applied for the detection and diagnosis of children's lung diseases. Lung field segmentation in digital CXR images is a key section of many computer-aided diagnosis systems. Objective: In this study, we propose a method based on deep learning to improve the lung segmentation quality and accuracy of children's multi-center CXR images. Methods: The novelty of the proposed method is the combination of merits of TransUNet and ResUNet. The former can provide a self-attention module improving the feature learning ability of the model, while the latter can avoid the problem of network degradation. Results: Applied on the test set containing multi-center data, our model achieved a Dice score of 0.9822. Conclusions: This novel lung segmentation method proposed in this work based on TransResUNet is better than other existing medical image segmentation networks.

Research on CT Lung Segmentation Method of Preschool Children based on Traditional Image Processing and ResUnet.

Lung segmentation using computed tomography (CT) images is important for diagnosing various lung diseases. Currently, no lung segmentation method has been developed for assessing the CT images of preschool children, which may differ from those of adults due to (1) presence of artifacts caused by the shaking of children, (2) loss of a localized lung area due to a failure to hold their breath, and (3) a smaller CT chest area, compared with adults. To solve these unique problems, this study developed an automatic lung segmentation method by combining traditional imaging methods with ResUnet using the CT images of 60 children, aged 0-6 years. First, the CT images were cropped and zoomed through ecological operations to concentrate the segmentation task on the chest area. Then, a ResUnet model was used to improve the loss for lung segmentation, and case-based connected domain operations were performed to filter the segmentation results and improve segmentation accuracy. The proposed method demonstrated promising segmentation results on a test set of 12 cases, with average accuracy, Dice, precision, and recall of 0.9479, 0.9678, 0.9711, and 0.9715, respectively, which achieved the best performance relative to the other six models. This study shows that the proposed method can achieve good segmentation results in CT of preschool children, laying a good foundation for the diagnosis of children's lung diseases.

Highly antifouling, biocompatible and tough double network hydrogel based on carboxybetaine-type zwitterionic polymer and alginate.

Because of resistance to bio-macromolecular adhesion, antifouling hydrogels have attracted great attention in biomedical field. But traditional antifouling hydrogels made by hydrophilic polymers are always poor of mechanical properties. Herein, a new hybrid ionic-covalent cross-linked double network (DN) hydrogel was prepared by a simple one-pot method based on sodium alginate and the zwitterionic material carboxybetaine acrylamide (CBAA). The DN hydrogel has good mechanical properties, including high elastic modulus (0.28 MPa), high tensile strength (0.69 MPa), as well as good self-recovery capability. More importantly, the DN hydrogel is highly resistance to the adsorption of non-specific protein, cells, bacteria and algae, exhibiting an outstanding antifouling property. The in vitro and in vivo experiments prove that the DN hydrogel is highly biocompatible. This study provides a new strategy for the preparation of antifouling DN hydrogels with good mechanical properties for different needs, such as tissue scaffolds, wound dressings, implantable devices, and other fields.

Highly transparent, self-healing, injectable and self-adhesive chitosan/polyzwitterion-based double network hydrogel for potential 3D printing wearable strain sensor.

A purely physically crosslinked double network (DN) hydrogel, poly(sulfobetaine-co-acrylic acid)/chitosan-citrate (P(SBMA-co-AAc)/CS-Cit) DN hydrogel, was prepared based on electrostatic interaction and hydrogen bonding between the polymer chains. The hydrogel is highly stretchable, transparent, anti-fatigue, self-adhesive and has good self-healing properties with a self-healing efficiency as high as 95.4%. Furthermore, the resistance of the P(SBMA-co-AAc)/CS-Cit DN hydrogel is sensitive to a wide strain window and the relative resistance shows stable and reliable change during deformation. Herein, the hydrogel was demonstrated as a strain sensor to detect human motions, such as joint bending and swallowing. More excitingly, before ionic crosslinking, the P(SBMA-co-AAc)/CS-Cit composite hydrogel is injectable, thus the P(SBMA-co-AAc)/CS-Cit DN hydrogel sensor can be made into various complex shapes by injecting the P(SBMA-co-AAc)/CS-Cit composite hydrogel into citrate solution, including multilayer structures, exhibiting a great potential for applications as 3D printing strain sensors.

Ultra-high strength poly(N-(2-hydroxyethyl)acrylamide)/chitosan hydrogel with "repelling and killing" bacteria property.

Hydrogels with good mechanical properties are promising for various applications. In this work, a simple yet effective method for preparing a novel double-network hydrogel was reported. First, nonfouling polymer, poly(N-(2-hydroxyethyl)acrylamide) (PHEAA), was crosslinked through covalent bonds. Antibacterial polysaccharide, chitosan (CS), was then crosslinked by chelation between the N-glucosamine units on the CS and citrate or sulfate ions. The poly(N-(2-hydroxyethyl)acrylamide)/chitosan double-network hydrogels (PHEAA/CS DN hydrogels) exhibited high tensile strength (3.8 MPa), strong elastic modulus (0.6 MPa). And the dynamic ionic crosslinking in CS network provided the DN gels with fast self-recovery ability as well as excellent fatigue resistance. Furthermore, the mechanical properties of the DN gels were enhanced after stretching and relaxing because of the molecular orientation and reconstruction of chitosan network. More importantly, the hydrogels have excellent antifouling and antibacterial properties, which is called "repelling and killing", making them competitive candidates for applications in the biomedical field.

Antibacterial and Antifouling Hybrid Ionic-Covalent Hydrogels with Tunable Mechanical Properties.

Because of their self-recovery ability and fatigue resistance, double-network (DN) hydrogels with hybrid ionical-covalent cross-linking have received wide attention. In this work, by a simple "one-pot" method, a novel kind of hybrid ionic-covalent chitosan/poly(sulfobetaine methacrylate) (CS/PSBMA) DN hydrogels was prepared. The hydrogels showed high tensile strength (2.0 MPa), strong elastic modulus (0.5 MPa), fast self-recovery ability as well as excellent fatigue resistance, high mechanical strength, and toughness retention rate after soaking in water for 24 h. Additionally, the mechanical properties of the DN gels were enhanced after stretch and relaxation because of the rearrangement of the CS network. More excitingly, because of the antifouling feature of PSBMA and the inherent antibacterial property of CS, the hybrid DN hydrogels demonstrated a "repel and kill" effect on microorganisms. The CS/PSBMA DN hydrogels may find potential applications in biomedical fields, such as artificial connective tissues, implantable devices, and wound dressing.

Dual-Sensitive Graphene Oxide Loaded with Proapoptotic Peptides and Anticancer Drugs for Cancer Synergetic Therapy.

A dual-sensitive drug delivery system (DDS) based on graphene oxide (GO) which is simultaneously loaded with proapoptotic peptides and anticancer drugs was rationally designed and fabricated for cancer synergetic therapy. Specifically, a kind of cell apoptosis peptide (KLAKLAK)2 (KLA) was anchored on the surface of GO via a disulfide bond to obtain GO-SS-KLA. Then, the aromatic anticancer drug doxorubicin (DOX) was loaded on GO through π-π conjugation and hydrogen bonding interactions. Finally, bovine serum albumin (BSA) was used to coat the GO carrier to obtain a biological medium-stable GO-based DDS, DOX@GO-SS-KLA/BSA. The results show that KLA and DOX can be released responding to the reductive and pH stimulus inside the cells, respectively, and achieve a synergetic therapy for cancer. Moreover, the results of stability studies show that DOX@GO-SS-KLA/BSA could be stably dispersed in water for more than 8 days and in 10% fetal bovine serum for at least 6 days. The constructed DOX@GO-SS-KLA/BSA exhibits great potential as a drug carrier for co-delivery of various therapeutic agents.

A dual-sensitive mesoporous silica nanoparticle based drug carrier for cancer synergetic therapy.

A multifunctional envelope-type mesoporous silica nanoparticle (MSN) was delicately designed for subcellular co-delivery of drug and therapeutic peptide to tumor cells. Firstly, a kind of cell apoptosis peptide (KLAKLAK)2 (KLA) was anchored on surface of MSN via disulfide bond to obtain MSN-SS-KLA. Subsequently, anticancer drug doxorubicin hydrochloride (DOX) was loaded into the pores of MSN-SS-KLA. Then, the drug loaded MSN-SS-KLA (DOX@MSN-SS-KLA) was further coated with bovine serum albumin (BSA) to obtain a biological media stable MSN based drug delivery system (DDS), DOX@MSN-SS-KLA/BSA, for cancer synergetic therapy. The results show that stability of the DOX@MSN-SS-KLA/BSA is much better than that of DOX@MSN-SS-KLA and it could keep well dispersed in serum for more than 24 h. After accumulating at tumor site by EPR effect, the DOX@MSN-SS-KLA/BSA could be effectively phagocytosed by HeLa cells and release apoptotic peptide KLA as well as DOX simultaneously responding to reductive stimulus inside the cells. In vitro cell experiment results show that the DOX@MSN-SS-KLA/BSA complex exhibits much better inhibition on HeLa cells compared with pure DOX, indicating that co-delivery of KLA and DOX is expected to achieve synergetic therapy of cancer.