Status,challenges,and future prospects of stem cell therapy in pelvic floor disorders

Pelvic floor disorders(PFDs)represent a group of common and frequentlyoccurring diseases that seriously affect the life quality of women,generally including stress urinary incontinence and pelvic organ prolapse.Surgery has been used as a treatment for PFD,but almost 30%of patients require subsequent surgery due to a high incidence of postoperative complications and high recurrence rates.Therefore,investigations of new therapeutic strategies are urgently needed.Stem cells possess strong multi-differentiation,self-renewal,immunomodulation,and angiogenesis abilities and they are able to differentiate into various cell types of pelvic floor tissues and thus provide a potential therapeutic approach for PFD.Recently,various studies using different autologous stem cells have achieved promising results by improving the pelvic ligament and muscle regeneration and conferring the tissue elasticity and strength to the damaged tissue in PFD,as well as reduced inflammatory reactions,collagen deposition,and foreign body reaction.However,with relatively high rates of complications such as bladder stone formation and wound infections,further studies are necessary to investigate the role of stem cells as maintainers of tissue homeostasis and modulators in early interventions including therapies using new stem cell sources,exosomes,and tissueengineering combined with stem cell-based implants,among others.This review describes the types of stem cells and the possible interaction mechanisms in PFD treatment,with the hope of providing more promising stem cell treatment strategies for PFD in the future.

Enhancing recommender systems by incorporating social information

Although recommendation techniques have achieved distinct developments over the decades,the data sparseness problem of the involved user-item matrix still seriously influences the recommendation quality.Most of the existing techniques for recommender systems cannot easily deal with users who have very few ratings.How to combine the increasing amount of different types of social information such as user generated content and social relationships to enhance the prediction precision of the recommender systems remains a huge challenge.In this paper,based on a factor graph model,we formalize the problem in a semi-supervised probabilistic model,which can incorporate different user information,user relationships,and user-item ratings for learning to predict the unknown ratings.We evaluate the method in two different genres of datasets,Douban and Last.fm.Experiments indicate that our method outperforms several state-of-the-art recommendation algorithms.Furthermore,a distributed learning algorithm is developed to scale up the approach to real large datasets.