Objective: The anxiety of Alzheimer's disease (AD) contributes significantly to decreased quality of life, increased morbidity, higher levels of caregiver distress, and the decision to institutionalize a patient. However, the incidence of anxiety in AD patients hasn't been discussed. In this study, artificial neural networks were used to predict the incidence of anxiety inAD patients.
Methods: A large randomized controlled clinical trial was analyzed in this study, which involved AD patients and caregivers from 6 different sites in the United States. The incidence of anxiety in AD patients was predicted by backpropagation artificial neural networks with one and hidden layers. After cross validation, the Predictive Accuracy (PA) of the models was measured to select the best structure of artificial neural networks.
Results: Among all models for predicting the incidence of anxiety in AD patients, the artificial neural network with respectively 6 and 3 neurons in the first and second hidden layers achieved the highest predictive accuracy of 85.56%.
Conclusions: The incidence of anxiety in AD patients can be predicted by an accuracy of over 80%. When used for anxiety prediction, neural networks with two hidden layers perform better than those with one hidden layer. These findings will benefit the prevention and early intervention of anxiety in Alzheimer's patients.
Gluteal muscle contracture (GMC) is a chronic fibrotic disease of gluteal muscles due to multiple etiologies. Emilin 1 plays a determinant role in fibers formation, but its role in the progression of GMC remains unclear. The present study was aimed to search for the predictive role and regulatory mechanism of Emilin 1 on GMC. Here, Protein and mRNA expression of Emilin 1 were decreased in GMC tissues compared to normal muscle tissues. Using the analysis of target prediction, Emilin 1 was observed to be a potential downstream sponge of miR-491-5p. In comparison to Emilin 1, miR-491-5p showed an aberrant elevation in GMC tissues, which was further proven to have a negative correlation with Emilin 1. The direct binding of miR-491-5p to Emilin 1 mRNA was confirmed by luciferase reporter gene assay, and miR-491-5p mimics inhibited, while miR-491-5p inhibitor promoted the protein expression and secretion of Emilin 1 in contraction bands (CB) fibroblasts. Additionally, miR-491-5p mimics promoted the expression of cyclin-dependent kinase 2 and cyclin D1 and the proliferation of CB fibroblasts, which could be reversed by Emilin 1 overexpression. Mechanistically, miR-491-5p mimics possibly activated transforming growth factor β1 (TGF-β1)/Smad3 signal cascade via binding to 3’-untranslated region of Emilin 1 mRNA, thereby promoting the progression of fibrosis of CB fibroblasts. Collectively, miR-491-5p inhibited Emilin 1 expression, and subsequently promoted CB fibroblasts proliferation and fibrosis via activating TGF-β1/Smad3 signal axis. MiR-491-5p might be a potentially effective biomarker for predicting GMC, providing a novel therapeutic strategy for GMC.