PP133 Developing A Novel Multifaceted Graphical Visualization For Treatment Ranking Within An Interactive Network Meta-Analysis Application

IntroductionNetwork meta-analysis (NMA) is a key methodology for comparing the effectiveness of multiple interventions or treatments simultaneously. This project aimed to ascertain current methods and visualizations for treatment ranking within an NMA framework and to subsequently develop a novel graphic within MetaInsight (an interactive NMA web application), to aid clinicians and stakeholders when making decisions regarding the “best” intervention(s) for their patient(s).MethodsCurrent literature on the methodology or visualization of treatment ranking published in the last 10 years was collated and studied. Based on the literature, a novel graphical visualization was developed using RShiny (RStudio, PBC) and integrated within MetaInsight, which is currently hosted on shinyapps.io.ResultsBayesian analyses produce rank probabilities from which mean or median rank and surface under the cumulative ranking curve can be calculated. For frequentist analyses the p-value is available. The simpler methods may be easier to interpret, but they are often more unstable and do not encompass the whole analysis (and vice versa). To aid interpretation and facilitate sensitivity analysis, an interactive graphic was developed that presents rankings alongside treatment effect and study quality results.ConclusionsTreatment ranking is useful, but the results should be interpreted cautiously, and the visualization should be transparent and all-encompassing. A ‘living’ version of MetaInsight, with treatment ranking, would allow interested parties to follow the evidence base as it grows.

Integrating Cognitive Developmental Neuroscience in Society: Lessons Learned From a Multidisciplinary Research Project on Education and Social Safety of Youth

Integrating fundamental science in society, with the goal to translate research findings to daily practice, comes with certain challenges. Successfully integrating research projects into society requires (1) good collaboration between scientists and societal stakeholders, (2) collaboration partners with common expectations and goals, and (3) investment in clear communication. Here we describe an integrative research project conducted by a large Dutch consortium that consisted of neuroscientists, psychologists, sociologists, ethicists, teachers, health care professionals and policy makers, focusing on applying cognitive developmental neuroscience for the benefit of youth in education and social safety. We argue that to effectively integrate cognitive developmental neuroscience in society, (1) it is necessary to invest in a well-functioning, diverse and multidisciplinary team involving societal stakeholders and youth themselves from the start of the project. This aids to build a so-called productive interactive network that increases the chances to realize societal impact in the long-term. Additionally, we propose that to integrate knowledge, (2) a different than standard research approach should be taken. When focusing on integration, the ultimate goal of research is not solely to understand the world better, but also to intervene with real-life situations, such as education or (forensic) youth care. To accomplish this goal, we propose an approach in which integration is not only started after the research has been conducted, but taken into account throughout the entire project. This approach helps to create common expectations and goals between different stakeholders. Finally, we argue that (3) dedicating sufficient resources to effective communication, both within the consortium and between scientists and society, greatly benefits the integration of cognitive developmental neuroscience in society.

The landscape of metabolic brain alterations in Alzheimer's disease

We present a comprehensive reference map of metabolic brain changes in Alzheimer's disease (AD). In a multi-center study within the Accelerating Medicines Partnership in AD, we metabolically profiled 500 samples from the dorsolateral prefrontal cortex (DLPFC) and 83 samples from the temporal cortex (TCX). In the DLPFC, 298 metabolites were correlated with AD-related traits, including late-life cognitive performance and neuropathological β-amyloid and tau tangle burden. Out of these 298 metabolites, 35 replicated in TCX and a previous study. A conditional analysis suggests that metabolic associations with tangle burden were largely independent of β-amyloid load in the brain. Our results provide evidence of brain alterations in bioenergetic pathways, cholesterol metabolism, neuroinflammation, osmoregulation, and other pathways. In a detailed investigation of the glutamate/GABA neurotransmitter pathway, we demonstrate how integration of complementary omics data can provide a comprehensive view of dysregulated biochemical processes. All associations are available as an interactive network at https://omicscience.org/apps/brainmwas/.

A Skin Cancer Detection Interactive Application Based on CNN and NLP

Skin cancer is the most common cancer with several different types. According to current estimations, one in five Americans will develop skin cancer in their lifetime. Therefore, early diagnosis and treatment of it is of crucial significance. Several advanced image processing methods have been applied to predict skin cancer. However, few researchers utilize those methods to build an interactive application. In this work, we implemented an interactive skin cancer diagnosis website, combining the convolutional neural network (CNN) and natural language processing (NLP) technology. The neural network model uses four convolutional layers and dense layers respectively to improve the accuracy. Two max-pooling layers were used to reduce redundant information. To address the severe overfitting problem, we chose to utilize the batch normalization along with dropout layers. Based on our results, 0.9935 in accuracy and 0.0225 loss is realized for training data, and accuracy of 0.8393 and 0.6648 loss for testing data. Natural language processing (NLP) was used to implement a chatbot for interaction with users. We crawled skin cancer related questions and answers from Quora and used them to train our chatbot. Lastly, we combined CNN and NLP to build an interactive skin cancer diagnosis website. VUE.js and Django were used to build the front-end and back-end of our website. These results offer a guideline for combining artificial intelligence with not only medicine but also interactive network, which enables people to get medical care more easily.

Crowd intelligence evolution based on complex network

Purpose In recent years, with the increase in computing power, artificial intelligence can gradually be regarded as intelligent agents and interact with humans, this interactive network has become increasingly complex. Therefore, it is necessary to model and analyze this complex interactive network. This paper aims to model and demonstrate the evolution of crowd intelligence using visual complex networks. Design/methodology/approach This paper uses the complex network to model and observe the collaborative evolution behavior and self-organizing system of crowd intelligence. Findings The authors use the complex network to construct the cooperative behavior and self-organizing system in crowd intelligence. Determine the evolution mode of the node by constructing the interactive relationship between nodes and observe the global evolution state through the force layout. Practical implications The simulation results show that the state evolution map can effectively simulate the distribution, interaction and evolution of crowd intelligence through force layout and the intelligent agents’ link mode the authors proposed. Originality/value Based on the complex network, this paper constructs the interactive behavior and organization system in crowd intelligence and visualizes the evolution process.

Hypergraph-based Logistic Matrix Factorization for Metabolite-disease Interaction Prediction

Motivation Function-related metabolites, the terminal products of the cell regulation, show a close association with complex diseases. The identification of disease-related metabolites is critical to the diagnosis, prevention and treatment of diseases. However, most existing computational approaches build networks by calculating pairwise relationships, which is inappropriate for mining higher-order relationships. Results In this study, we presented a novel approach with hypergraph-based logistic matrix factorization, HGLMF, to predict the potential interactions between metabolites and disease. First, the molecular structures and gene associations of metabolites and the hierarchical structures and GO functional annotations of diseases were extracted to build various similarity measures of metabolites and diseases. Next, the kernel neighborhood similarity of metabolites (or diseases) was calculated according to the completed interactive network. Second, multiple networks of metabolites and diseases were fused, respectively, and the hypergraph structures of metabolites and diseases were built. Lastly, a logistic matrix factorization based on hypergraph was proposed to predict potential metabolite-disease interactions. In computational experiments, HGLMF accurately predicted the metabolite-disease interaction, and performed better than other state-of-the-art methods. Moreover, HGLMF could be employed to predict new metabolites (or diseases). As suggested from the case studies, the proposed method could discover novel disease-related metabolites, which has been confirmed in existing studies. Availability The codes and dataset are available at: https://github.com/Mayingjun20179/HGLMF. Supplementary information Supplementary data are available at Bioinformatics online.