The aim of this study was to determine the effectiveness of corneal collagen cross-linking (CXL) for the treatment of progressive keratoconus (KC). Some of the published literature, including a few small, randomized controlled trials (RCTs), demonstrated good results after CXL, but large RCTs with long-term follow-up to establish a cause-effect relationship are lacking. Using PubMed, EMBASE, and the Cochrane Library database, we searched for relevant studies published between October 2007 and March 2014. A comprehensive literature search was performed using the Cochrane Collaboration methodology to identify the effectiveness of CXL for treating KC. The primary outcome parameters included uncorrected visual acuity (UCVA), best-corrected visual acuity (BCVA), refraction, corneal topography, and corneal thickness at baseline and at 1, 3, 6, 12, and 18 months after CXL. A total of 1171 participants (1557 eyes) were enrolled in this meta-analysis. CXL may be effective in halting the progress of KC for at least 12 months under certain conditions. However, further research from randomized trials is needed to confirm our findings.
Autism spectrum disorder (ASD) is a developmental disorder that impacts more than 1.6% of children aged 8 across the United States. It is characterized by impairments in social interaction and communication, as well as by a restricted repertoire of activity and interests. The current standardized clinical diagnosis of ASD remains to be a subjective diagnosis, mainly relying on behavior-based tests. However, the diagnostic process for ASD is not only time consuming, but also costly, causing a tremendous financial burden for patients’ families. Therefore, automated diagnosis approaches have been an attractive solution for earlier identification of ASD. In this work, we set to develop a deep learning model for automated diagnosis of ASD. Specifically, a multichannel deep attention neural network (DANN) was proposed by integrating multiple layers of neural networks, attention mechanism, and feature fusion to capture the interrelationships in multimodality data. We evaluated the proposed multichannel DANN model on the Autism Brain Imaging Data Exchange (ABIDE) repository with 809 subjects (408 ASD patients and 401 typical development controls). Our model achieved a state-of-the-art accuracy of 0.732 on ASD classification by integrating three scales of brain functional connectomes and personal characteristic data, outperforming multiple peer machine learning models in a k-fold cross validation experiment. Additional k-fold and leave-one-site-out cross validation were conducted to test the generalizability and robustness of the proposed multichannel DANN model. The results show promise for deep learning models to aid the future automated clinical diagnosis of ASD.
BackgroundRetinal vein occlusion (RVO) is a common retinal venous disorder that causes vision loss. No specific therapy has been developed. Controversy exists regarding two treatments: intravitreal dexamethasone implants and anti-vascular endothelial growth factor (VEGF). The goal of this study is to compare the effectiveness and safety of dexamethasone implants and anti-VEGF treatment for RVO.MethodsThe PubMed, Embase, and Cochrane Library databases were searched for studies comparing dexamethasone implants with anti-VEGF in patients with RVO. Best-corrected visual acuity (BCVA), central subfield thickness (CST), intraocular pressure changes, conjunctival haemorrhage, reduced VA, and macular oedema were extracted from the final included studies. RevMan 5.3 was used to conduct the quantitative analysis and bias assessment.ResultsFour randomised controlled trials assessing 969 eyes were included. The anti-VEGF treatment showed better BCVA improvement (mean difference [MD] = − 10.59, P < 0.00001) and more CST decrease (MD = − 86.71 μm, P = 0.02) than the dexamethasone implants. However, the dexamethasone implants required fewer injections. As for adverse effects, the dexamethasone implants showed significantly higher intraocular pressure (IOP) and more cataracts than the anti-VEGF treatment. No significant differences were found in conjunctival haemorrhage, reduced VA, and macular oedema.ConclusionsAnti-VEGF treatment showed better functional and anatomical improvement with less risk of IOP elevation and cataract formation compared to dexamethasone implants. Thus, anti-VEGF treatment is the first choice for treating RVO patients.
Medical concept embedding is to learn a distributed representation for a medical related entity, e.g. diagnosis, treatment procedure, and medicine, which is a code stored in Electronic Health Record (EHR). The distributed representation is expected to preserve the comprehensive relationships among medical concepts rather than one-hot encoding, and it will be the inputs of machine learning based healthcare analytic tasks. Therefore, the performance of the analytic tasks highly depends on the quality of embedding outputs. To fully utilise the information in EHR, this paper proposes a novel attentive dual embedding method, namely MC2Vec, to intensively capture the proximity relationships among medical concepts. In particular, the proposed MC2Vec method uses a two-step optimisation framework to recursively refine the embedding via two components 1) Skip-gram based method to generate the initial embedding of medical concept, and 2) Attentive CBOW based method to fine-tune the code embedding by adding the temporal information of one patient's sequential healthcare activities. The experiment studies on two public EHR datasets demonstrate the effectiveness of the proposed MC2Vec method, which performs superior than other five state-of-the-art embedding methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.