Visual Analytics Tool Research Articles

5106A pattern-discovery-based outcome predictive tool integrated with clinical data repository: design and a case study on contrast related acute kidney injury

Abstract Introduction Clinical data repositories (CDR) including electronic health record (EHR) data have great potential for outcome prediction and risk modeling. However, most CDRs were only used for data displaying, and using data from CDR for outcome prediction often requires careful study design and sophisticated modeling techniques before a hypothesis can be tested. Purpose We built a prediction tool integrated with CDR based on pattern discovery aiming to bridge the above gap and demonstrated a case study on contrast related acute kidney injury (AKI) with the system. Methods A cardiovascular CDR integrated with multiple hospital informatics systems was established. For the case study on AKI, we included patients undergoing cardiac catheterization from January 13, 2015 to April 27, 2017, excluding those with dialysis, end-stage renal disease, renal transplant, and missing pre- or post-procedural creatinine. To handle missing data, a prior-history-note composer was designed to fill in structured data of 14 diseases related to cardiovascular problem. Crucial data such as ejective fraction was extracted from the structured reports. AKI was defined according to Acute Kidney Injury Network by increase of serum creatinine from most recent baseline to the post-procedure 7-day peak. To build predictive modeling, we selected 17 variables covered in existing AKI models. Pattern discovery was recently developed as an interpretable predictive model which works on incomplete noisy data. In this study, we developed a pattern discovery based visual analytics tool, and trained it on 70% data up to August 2016 with three interactive knowledge incorporation modes to develop 3 models: 1) pure data-driven, 2) domain knowledge, and 3) clinician-interactive. In last two modes, a physician using the visual analytics could change the variables and further refine the model, respectively. We tested and compared it with other models on the 30% consecutive patients dated afterwards, which is shown in Figure 1. Results Among 2,560 patients in the final dataset with 17 pre-procedure variables derived from CDR data, 169 (7.3%) had AKI. We measured 4 existing models, whose areas under curves (AUCs) of receiver operating characteristics curve for the test set were 0.70 (Mehran's), 0.72 (Chen's), 0.67 (Gao's) and 0.62 (AGEF), respectively. A pure data-driven machine learning method achieves AUC of 0.72 (Easy Ensemble). The AUCs of our 3 models are 0.77, 0.80, 0.82, respectively, with the last being top where physician knowledge is incorporated. Demo and demonstration Conclusions We developed a novel pattern-discovery-based outcome prediction tool integrated with CDR and purely using EHR data. On the case of predicting contrast related AKI, the tool showed user-friendliness by physicians, and demonstrated a competitive performance in comparison with the state-of-the-art models.

Ablate, Variate, and Contemplate: Visual Analytics for Discovering Neural Architectures.

The performance of deep learning models is dependent on the precise configuration of many layers and parameters. However, there are currently few systematic guidelines for how to configure a successful model. This means model builders often have to experiment with different configurations by manually programming different architectures (which is tedious and time consuming) or rely on purely automated approaches to generate and train the architectures (which is expensive). In this paper, we present Rapid Exploration of Model Architectures and Parameters, or REMAP, a visual analytics tool that allows a model builder to discover a deep learning model quickly via exploration and rapid experimentation of neural network architectures. In REMAP, the user explores the large and complex parameter space for neural network architectures using a combination of global inspection and local experimentation. Through a visual overview of a set of models, the user identifies interesting clusters of architectures. Based on their findings, the user can run ablation and variation experiments to identify the effects of adding, removing, or replacing layers in a given architecture and generate new models accordingly. They can also handcraft new models using a simple graphical interface. As a result, a model builder can build deep learning models quickly, efficiently, and without manual programming. We inform the design of REMAP through a design study with four deep learning model builders. Through a use case, we demonstrate that REMAP allows users to discover performant neural network architectures efficiently using visual exploration and user-defined semi-automated searches through the model space.

Dementia Patient Segmentation Using EMR Data Visualization: A Design Study

(1) Background: The Electronic Medical Record system, which is a digital medical record management architecture, is critical for reliable medical research. It facilitates the investigation of disease patterns and efficient treatment via collaboration with data scientists. (2) Methods: In this study, we present multidimensional visual tools for the analysis of multidimensional datasets via a combination of 3-dimensional radial coordinate visualization (3D RadVis) and many-objective optimization (e.g., Parallel Coordinates). Also, we propose a user-driven research design to facilitate visualization. We followed a design process to (1) understand the demands of domain experts, (2) define the problems based on relevant works, (3) design visualization, (4) implement visualization, and (5) enable qualitative evaluation by domain experts. (3) Results: This study provides clinical insight into dementia based on EMR data via visual analysis. Results of a case study based on questionnaires surveying daily living activities indicated that daily behaviors influenced the progression of dementia. (4) Conclusions: This study provides a visual analytical tool to support cluster segmentation. Using this tool, we segmented dementia patients into clusters and interpreted the behavioral patterns of each group. This study contributes to biomedical data interpretation based on a visual approach.

Enhanced Grid-Based Visual Analysis of Retinal Layer Thickness with Optical Coherence Tomography

Optical coherence tomography enables high-resolution 3D imaging of retinal layers in the human eye. The thickness of the layers is commonly assessed to understand a variety of retinal and systemic disorders. Yet, the thickness data are complex and currently need to be considerably reduced prior to further processing and analysis. This leads to a loss of information on localized variations in thickness, which is important for early detection of certain retinal diseases. We propose an enhanced grid-based reduction and exploration of retinal thickness data. Alternative grids are computed, their representation quality is rated, and best fitting grids for given thickness data are suggested. Selected grids are then visualized, adapted, and compared at different levels of granularity. A visual analysis tool bundles all computational, visual, and interactive means in a flexible user interface. We demonstrate the utility of our tool in a complementary analysis procedure, which eases the evaluation of ophthalmic study data. Ophthalmologists successfully applied our solution to study localized variations in thickness of retinal layers in patients with diabetes mellitus.

User Evaluation of Map-Based Visual Analytic Tools

Big data have also become a big challenge for cartographers, as the majority of big data may be localized. The use of visual analytics tools, as well as comprising interactive maps, stimulates inter-disciplinary actors to explore new ideas and decision-making methods. This paper deals with the evaluation of three map-based visual analytics tools by means of the eye-tracking method. The conceptual part of the paper begins with an analysis of the state-of-the-art and ends with the design of proof-of-concept experiments. The verification part consists of the design, composition, and realization of the conducted eye-tracking experiment, in which three map-based visual analytics tools were tested in terms of user-friendliness. A set of recommendations on GUI (graphical user interface) design and interactive functionality for map makers is formulated on the basis of the discovered errors and shortcomings in the assessed stimuli. The results of the verification were used as inputs for improving the three tested map-based visual analytics tools and might serve as a best practice for map-based visual analytics tools in general, as well as for improving the policy making cycle as elaborated by the European project PoliVisu (Policy Development based on Advanced Geospatial Data Analytics and Visualization).

ImaCytE: Visual Exploration of Cellular Micro-Environments for Imaging Mass Cytometry Data.

Tissue functionality is determined by the characteristics of tissue-resident cells and their interactions within their microenvironment. Imaging Mass Cytometry offers the opportunity to distinguish cell types with high precision and link them to their spatial location in intact tissues at sub-cellular resolution. This technology produces large amounts of spatially-resolved high-dimensional data, which constitutes a serious challenge for the data analysis. We present an interactive visual analysis workflow for the end-to-end analysis of Imaging Mass Cytometry data that was developed in close collaboration with domain expert partners. We implemented the presented workflow in an interactive visual analysis tool; ImaCytE. Our workflow is designed to allow the user to discriminate cell types according to their protein expression profiles and analyze their cellular microenvironments, aiding in the formulation or verification of hypotheses on tissue architecture and function. Finally, we show the effectiveness of our workflow and ImaCytE through a case study performed by a collaborating specialist.

Innovative Geospatial and Cartographic Approaches to Identification, Analysis, and Visualisation of Land Degradation

Abstract. Land degradation has increasingly been recognised as a serious environmental problem throughout the whole world. Six major threats may be identified that place soil fertility at risk, namely, soil erosion, loss of organic matter, soil biodiversity, soil compaction, soil salinity, and soil pollution. Several of those risks could be effectively identified, analysed, visualised and consequently limited by approaches originating from the geospatial domain.The China – European Union research and innovation project “SIEUSOIL” (SIno-EU Soil Observatory for Intelligent Land Use Management), funded between 2019 and 2022, as well as the European Big Data flagship research and innovation project “DataBio” (Data-Driven Bioeconomy), funded between 2017 and 2019, aim at the above mentioned challenges of land degradation from innovative geospatial perspectives.Such innovative approaches include local geological, geomorphological, climate, yield maps as well as global soil maps provided commonly by the European Commission (Directorate General Joint Research Centre) and the Chinese Academy of Sciences. Among the data inputs there are farm machinery tracking and interpreted satellite images. The second level of activities consists of selected standards and specification of ontologies for the integration and sharing of soil related data, facilitating their reuse and understanding. The resulting ontology and other selected models provide the basis for the integration, publication, and querying of the source datasets using Linked data as a federated layer. Besides offering an integrated view of the datasets, this layer also enables new insights through the discovery of links.From the cartographic perspective, several visualization techniques are deployed; from static maps to interactive visualisations. The main focus of visualization techniques is therefore given to the interactivity through utilizing the concept of Multiple Coordinated Views (also known as visual analytics tools) and dynamic queries to emphasize the impact of changes of various phenomena in space and time. For instance, see Figure 1 on monitoring of machinery fleet movement and especially its spatiotemporal changes that can bring new insights into the consequences of human decisions from many areas. Economic reasons are related to economic evidence for a farmer, including fuel consumption, efficiency of trajectory, etc. to revenue authority or subsidies management. On the other hand, ecologic motivations aim to decrease of environmental burden caused e.g. by high CO2 emissions due to a lack of movement optimisation, water pollution by nitrogen due to excessive fertilisation, etc.The outcomes of the above mentioned research are intended as a feedback to (inter)national policies within the environmental domain including the Montreal Protocol (on substances that deplete the Ozone Layer), European Common Agricultural Policy, Nitrates Directive, Air Quality Framework Directive, Water Framework Directive, the Chinese Water Pollution Prevention Law, etc.

Visual Analytics for Regional Economic Environment Factors Based on a Dashboard Design

Abstract. Economic environment is vital for commercial investment, city planning and company strategy planning in urban areas. Mastering the economical trend may help the entrepreneurs, government officers and individuals in their decision-making process. In this study, we explore multiple geo-economic datasets using visual analytics methods for understanding the economic environment. More specifically, we user time-series Gross Domestic Product (GDP) data as an economic indicator of economic development and land use data to support the spatial analysis at a refined geographic scale. The spatiotemporal patterns of the regional economic environment are revealed both qualitatively and quantitatively. The work has a three-fold contributions: (1) we apply a grid-based spatial interpolation model to derive GDP values at a file granularity based on land use data; (2) we design a novel interactive dashboard for the GDP data exploration, which serves as a visual analytical tool between data and users; (3) we combine quantitative analysis with visualizations to strengthen the qualitative analysis. The feasibility of visual analytics methods and the dashboard design are tested in one of the most developed regions, Jiangsu Province, China. Both expected and unexpected economical patterns were extracted.

A new approach for routine quantification of microplastics using Nile Red and automated software (MP-VAT).

Microplastics are widespread contaminants in the environment. However, most identification protocols rely on long and subjective visual counting, which could be improved using staining dyes. Thus, the objective of this work is to identify the best staining dye protocol and create an objective and quick automated counting software for microplastics. Tests were conducted to identify the most appropriate of eight staining dye solutions and of six wavelengths for virgin and weathered synthetic polymers, textile fibers, natural organic matter and filters. Nile Red produced the best results (without interfering in infrared spectra) rendering microplastics fluorescent at 254 nm, but with limited number of fluorescent polymers, and at 470 nm (with orange filter), with fluorescence of plastics as well as natural organic matter (requiring a digestion step). Next, a script was developed in ImageJ for the automatic quantification and characterization in shape (fiber, fragment, particle) and size of fluorescent microplastics, the Microplastics Visual Analysis Tool (MP-VAT). MP-VAT was evaluated, producing recovery rates in the range of 89.0-111.1% in spiked filters under 470 nm. Furthermore, this package is accompanied by a script that sets a scale from a known filter diameter, MP-SCALE, and a script that allows user threshold setting, MP-ACT.

Gathering Real World Evidence Through the Evaluation of Decision History.

Clinical Practice Guidelines (CPGs) gather latest evidence-based results to guide and support clinicians over the decision-making process to provide best care. Nevertheless, clinical cases may be subject to some biases (understood as non-compliance with CPGs) that can lead to adapt care delivery. In this work an experience-based decision support leaning on the structuration of the Decisional Event concept for tracking and storing each clinical decision is presented. Moreover, a visual analytics tool is provided in order to facilitate the visualization of biases from guideline-based decision support and the identification and inclusion of real-world evidence into the reasoning process by augmenting the knowledge formalized in the implemented guidelines.

A taxonomy generation tool for semantic visual analysis of large corpus of documents

Taxonomies are semantic resources that help to categorize and add meaning to data. In a hyperconnected world where information is generated at a rate that exceeds human capacities to process and make sense of it, such semantic resources can help to access relevant information more efficiently by extracting knowledge from large and unstructured data sets. Taxonomies are related to specific domains of knowledge in which they identify relevant topics. However, they have to be validated by experts to guarantee that its terms and relations are meaningful. In this paper, we introduce a semiautomatic taxonomy generation tool for supporting domain experts in building taxonomies that are then used to automatically create semantic visualizations of data. Our proposal combines automatic techniques to extract, sort and categorize terms, and empowers domain experts to take part at any stage of the process by providing a visual edition tool. We tested the tool’s usability in two use cases from different domains and languages. Results show that all the functionalities are easy to use and interact with. Lessons learned from this experience will guide the design of a utility evaluation involving domain experts interested in data analysis and knowledge modeling.

Open data visualizations and analytics as tools for policy-making

Government agencies collect large amounts of structured and unstructured data. Although these data can be used to improve services as well as policy processes, it is not always clear how to analyze the data and how to glean insights for policy making, especially when the data includes large volumes of unstructured text data. This article reports opinions found in “We the People” petition data using topic modeling and visual analytics. It provides an assessment of the usability of the visual analytics results for policy making based on interviews with data professionals and policy makers. We found that visual analytics have potentially positive impacts on policy making practices. Experts also articulated potential barriers regarding the adoption of visual analytics tools, and made suggestions. Potential barriers included insufficient resources in government agencies and difficulty integrating analytics with current work practices. The main suggestions involved providing training and interpretation guidelines along with the visual analytics tools. Major contributions of this study include: (1) suggesting viable visualization tools for analyzing textual data for policy making, and (2) suggesting how to lower barriers to adoption by increasing usability.

Real-time and archival data visualisation techniques in city dashboards

ABSTRACTCity dashboards have become a common smart city technology, emerging as a key means of sharing and visualising urban data for the benefit of the public and city administrations. Operating as the front-end of many cities’ data stores, dashboards display and benchmark indicators relating to city operations, characteristics, and trends, displayed through interactive visual representations of spatial and temporal patterns. Many dashboards collect, archive, and present data collected in real-time, as well as more traditional time-sliced administrative data. In this paper, we evaluate the techniques that dashboards employ to present real-time data to dashboard users. Our analysis identifies two factors that shape and differentiate real-time visual analytic tools: the dynamic nature of the data, how they are refreshed, and how the realtimeness of the data is communicated to the user; and how the tool enables archival comparison. We assess dashboard design according to the strategies used to address specific challenges associated with each factor, specifically change blindness and temporal pattern detection. We conclude by proposing effective techniques for city dashboard design.

BEAMES: Interactive Multimodel Steering, Selection, and Inspection for Regression Tasks.

Interactive model steering helps people incrementally build machine learning models that are tailored to their domain and task. Existing visual analytic tools allow people to steer a single model (e.g., assignment attribute weights used by a dimension reduction model). However, the choice of model is critical in such situations. What if the model chosen is suboptimal for the task, dataset, or question being asked? What if instead of parameterizing and steering this model, a different model provides a better fit? This paper presents a technique to allow users to inspect and steer multiple machine learning models. The technique steers and samples models from a broader set of learning algorithms and model types. We incorporate this technique into a visual analytic prototype, BEAMES, that allows users to perform regression tasks via multimodel steering. This paper demonstrates the effectiveness of BEAMES via a use case, and discusses broader implications for multimodel steering.

Analysis of Decadal Climate Predictions with User‐guided Hierarchical Ensemble Clustering

AbstractIn order to gain probabilistic results, ensemble simulation techniques are increasingly applied in the weather and climate sciences (as well as in various other scientific disciplines). In many cases, however, only mean results or other abstracted quantities such as percentiles are used for further analyses and dissemination of the data. In this work, we aim at a more detailed visualization of the temporal development of the whole ensemble that takes the variability of all single members into account. We propose a visual analytics tool that allows an effective analysis process based on a hierarchical clustering of the time‐dependent scalar fields. The system includes a flow chart that shows the ensemble members' cluster affiliation over time, reflecting the whole cluster hierarchy. The latter one can be dynamically explored using a visualization derived from a dendrogram. As an aid in linking the different views, we have developed an adaptive coloring scheme that takes into account cluster similarity and the containment relationships. Finally, standard visualizations of the involved field data (cluster means, ground truth data, etc.) are also incorporated. We include results of our work on real‐world datasets to showcase the utility of our approach.

An Exploratory User Study of Visual Causality Analysis

AbstractInteractive visualization tools are being used by an increasing number of members of the general public; however, little is known about how, and how well, people use visualizations to infer causality. Adapted from the mediation causal model, we designed an analytic framework to systematically evaluate human performance, strategies, and pitfalls in a visual causal reasoning task. We recruited 24 participants and asked them to identify the mediators in a fictitious dataset using bar charts and scatter plots within our visualization interface. The results showed that the accuracy of their responses as to whether a variable is a mediator significantly decreased when a confounding variable directly influenced the variable being analyzed. Further analysis demonstrated how individual visualization exploration strategies and interfaces might influence reasoning performance. We also identified common strategies and pitfalls in their causal reasoning processes. Design implications for how future visual analytics tools can be designed to better support causal inference are discussed.

Capture & Analysis of Active Reading Behaviors for Interactive Articles on the Web

AbstractJournalists, educators, and technical writers are increasingly publishing interactive content on the web. However, popular analytics tools provide only coarse information about how readers interact with individual pages, and laboratory studies often fail to capture the variability of a real‐world audience. We contribute extensions to the Idyll markup language to automate the detailed instrumentation of interactive articles and corresponding visual analysis tools for inspecting reader behavior at both micro‐ and macro‐levels. We present three case studies of interactive articles that were instrumented, posted online, and promoted via social media to reach broad audiences, and share data from over 50,000 reader sessions. We demonstrate the use of our tools to characterize article‐specific interaction patterns, compare behavior across desktop and mobile devices, and reveal reading patterns common across articles. Our contributed findings, tools, and corpus of behavioral data can help advance and inform more comprehensive studies of narrative visualization.

Characterizing Exploratory Visual Analysis: A Literature Review and Evaluation of Analytic Provenance in Tableau

AbstractSupporting exploratory visual analysis (EVA) is a central goal of visualization research, and yet our understanding of the process is arguably vague and piecemeal. We contribute a consistent definition of EVA through review of the relevant literature, and an empirical evaluation of existing assumptions regarding how analysts perform EVA using Tableau, a popular visual analysis tool. We present the results of a study where 27 Tableau users answered various analysis questions across 3 datasets. We measure task performance, identify recurring patterns across participants' analyses, and assess variance from task specificity and dataset. We find striking differences between existing assumptions and the collected data. Participants successfully completed a variety of tasks, with over 80% accuracy across focused tasks with measurably correct answers. The observed cadence of analyses is surprisingly slow compared to popular assumptions from the database community. We find significant overlap in analyses across participants, showing that EVA behaviors can be predictable. Furthermore, we find few structural differences between behavior graphs for open‐ended and more focused exploration tasks.

Interactive Volumetric Visual Analysis of Glycogen‐derived Energy Absorption in Nanometric Brain Structures

AbstractDigital acquisition and processing techniques are changing the way neuroscience investigation is carried out. Emerging applications range from statistical analysis on image stacks to complex connectomics visual analysis tools targeted to develop and test hypotheses of brain development and activity. In this work, we focus on neuroenergetics, a field where neuroscientists analyze nanoscale brain morphology and relate energy consumption to glucose storage in form of glycogen granules. In order to facilitate the understanding of neuroenergetic mechanisms, we propose a novel customized pipeline for the visual analysis of nanometric‐level reconstructions based on electron microscopy image data. Our framework supports analysis tasks by combining i) a scalable volume visualization architecture able to selectively render image stacks and corresponding labelled data, ii) a method for highlighting distance‐based energy absorption probabilities in form of glow maps, and iii) a hybrid connectivitybased and absorption‐based interactive layout representation able to support queries for selective analysis of areas of interest and potential activity within the segmented datasets. This working pipeline is currently used in a variety of studies in the neuroenergetics domain. Here, we discuss a test case in which the framework was successfully used by domain scientists for the analysis of aging effects on glycogen metabolism, extracting knowledge from a series of nanoscale brain stacks of rodents somatosensory cortex.

Racial Dot Maps Based on Dasymetrically Modeled Gridded Population Data

Racial geography, mapping spatial distributions of different racial groups, is of keen interest in a multiracial society like the United States. A racial dot map is a method of visualizing racial geography, which depicts spatial distribution, population density, and racial mix in a single, easy-to-understand map. Because of the richness of information it carries, the dot map is an excellent tool for visual analysis of racial distribution. Presently-used racial dot maps are based on the Census data at the tract or the block level. In this paper, we present a method of constructing a more spatially-accurate racial dot map based on a sub-block-resolution population grid. The utility of our dot maps is further enhanced by placing dots on the map in random order regardless of the race they represent in order to achieve a more accurate depiction of local racial composition. We present a series of comparisons between dot maps based on tract, block, and grid data. The advantage of a grid-based dot map is evident from the visual comparison of all maps with an actual image of the mapped area. We make available the R code for constructing grid-based dot maps. We also make available 2010 grid-based racial dot maps for all counties in the conterminous United States.