A hybrid model for hand-foot-mouth disease prediction based on ARIMA-EEMD-LSTM.

BACKGROUND: Hand, foot, and mouth disease (HFMD) is a common infectious disease that poses a serious threat to children all over the world. However, the current prediction models for HFMD still require improvement in accuracy. In this study, we proposed a hybrid model based on autoregressive integrated moving average (ARIMA), ensemble empirical mode decomposition (EEMD) and long short-term memory (LSTM) to predict the trend of HFMD. METHODS: The data used in this study was sourced from the National Clinical Research Center for Child Health and Disorders, Chongqing, China. The daily reported incidence of HFMD from 1 January 2015 to 27 July 2023 was collected to develop an ARIMA-EEMD-LSTM hybrid model. ARIMA, LSTM, ARIMA-LSTM and EEMD-LSTM models were developed to compare with the proposed hybrid model. Root mean square error (RMSE), mean absolute error (MAE) and coefficient of determination (R2) were adopted to evaluate the performances of the prediction models. RESULTS: Overall, ARIMA-EEMD-LSTM model achieved the most accurate prediction for HFMD, with RMSE, MAPE and R2 of 4.37, 2.94 and 0.996, respectively. Performing EEMD on the residual sequence yields 11 intrinsic mode functions. EEMD-LSTM model is the second best, with RMSE, MAPE and R2 of 6.20, 3.98 and 0.996. CONCLUSION: Results showed the advantage of ARIMA-EEMD-LSTM model over the ARIMA model, the LSTM model, the ARIMA-LSTM model and the EEMD-LSTM model. For the prevention and control of epidemics, the proposed hybrid model may provide a more powerful help. Compared with other three models, the two integrated with EEMD method showed significant improvement in predictive capability, offering novel insights for modeling of disease time series.

An engineered lamellar bone mimicking full-scale hierarchical architecture for bone regeneration.

Lamellar bone, compactly and ingeniously organized in the hierarchical pattern with 6 ordered scales, is the structural motif of mature bone. Each hierarchical scale exerts an essential role in determining physiological behavior and osteogenic bioactivity of bone. Engineering lamellar bone with full-scale hierarchy remains a longstanding challenge. Herein, using bioskiving and mineralization, we attempt to engineer compact constructs resembling full-scale hierarchy of lamellar bone. Through systematically investigating the effect of mineralization on physicochemical properties and bioactivities of multi-sheeted collagen matrix fabricated by bioskiving, the hierarchical mimicry and hierarchy-property relationship are elucidated. With prolongation of mineralization, hierarchical mimicry and osteogenic bioactivity of constructs are performed in a bidirectional manner, i.e. first rising and then descending, which is supposed to be related with transformation of mineralization mechanism from nonclassical to classical crystallization. Construct mineralized 9 days can accurately mimic each hierarchical scale and efficiently promote osteogenesis. Bioinformatic analysis further reveals that this construct potently activates integrin α5-PI3K/AKT signaling pathway through mechanical and biophysical cues, and thereby repairing critical-sized bone defect. The present study provides a bioinspired strategy for completely resembling complex hierarchy of compact mineralized tissue, and offers a critical research model for in-depth studying the structure-function relationship of bone.

A Self-Healing Multifunctional Hydrogel System Accelerates Diabetic Wound Healing through Orchestrating Immunoinflammatory Microenvironment.

Developing an effective treatment strategy of drug delivery to improve diabetic wound healing remains a major challenge in clinical practice nowadays, due to multidrug-resistant bacterial infections, angiopathy, and oxidative damage in the wound microenvironment. Herein, an effective and convenient strategy was designed through a self-healing multiple-dynamic-bond cross-linked hydrogel with interpenetrating networks, which was formed by multiple-dynamic-bond cross-linking of reversible catechol-Fe3+ coordinate bonds, hydrogen bonding, and Schiff base bonds. The excellent autonomous healing of the hydrogel was initiated and accelerated by Schiff bonds with reversible breakage between 3,4-dihydroxybenzaldehyde containing catechol and aldehyde groups and chitosan chains, and further consolidated by the co-optation of other noncovalent interactions contributed of hydrogen bonding and Fe3+ coordinate bonds. Intriguingly, cathelicidin LL-37 was introduced and uniformly dispersed in the dynamic interpenetrating networks of the hydrogel as a bioactive molecular to orchestrate the diabetic wound healing microenvironment. This multifunctional wound dressing can significantly promote diabetic wound healing by antibacterial activity, immunomodulation, anti-inflammation, neovascularization, and antioxidant activity. Therefore, this study provided an effective and safe strategy for guiding the diabetic wound treatment in clinical applications.