Healthcare professionals, just like any other community, can exhibit implicit biases. These biases adversely impact patients’ health outcomes. Promoting awareness of both social determinants of health (SDH) and the impact of implicit/explicit biases assists healthcare professionals to understand their patients well and improve care experiences. In addition, it helps to augment the long-lasting empathy and compassion in healthcare professionals towards patients for care treatments while maintaining better healthcare professional-patient relationships. Thus, this research provides Computer-Supported Expert-Guided Experiential Learning (CSEGEL) tools or mobile applications that facilitate healthcare professionals with a first-person learning experience to augment advanced healthcare skills (e.g., professional communication, cultural humility, awareness of both SDH and impact of biases on health outcomes). The CSEGEL tools in the form of mobile applications incorporate virtual reality-based serious role-playing scenarios along with a novel Life Course module to deliver first-person experiential learning capability to augment the advanced healthcare skills of healthcare professionals and public awareness. Finally, a preliminary data analysis is provided to demonstrate the positive influence of CSEGEL tools and measure the required number of sample sizes for concrete evidence to show effective results.
The COVID-19 virus induces infection in both the upper respiratory tract and the lungs. Chest X-ray are widely used to diagnose various lung diseases. Considering chest X-ray and CT images, we explore deep-learning-based models namely: AlexNet, VGG16, VGG19, Resnet50, and Resnet101v2 to classify images representing COVID-19 infection and normal health situation. We analyze and present the impact of transfer learning, normalization, resizing, augmentation, and shuffling on the performance of these models. We explored the vision transformer (ViT) model to classify the CXR images. The ViT model incorporates multi-headed attention to disclose more global information in constrast to CNN models at lower layers. This mechanism leads to quantitatively diverse features. The ViT model renders consolidated intermediate representations considering the training data. For experimental analysis, we use two standard datasets and exploit performance metrics: accuracy, precision, recall, and F1-score. The ViT model, driven by self-attention mechanism and longrange context learning, outperforms other models.
This paper proposes a novel information visualisation interface to help with the reading and improvement of biochips.The interface serves two main groups of end users.These are bio-chip model users and bio-chip model developers.Bio-chip model users are biologists who use the software to read chips and detect biochemical substances.Bio-chip model developers use the software to design and train classification models by seeing how well the different biosensors work and how well the data fits their model.The interface proposed uses a Random Forest classifier and visualises the classification to provide a better understanding of how the data is classified by showing how it fits different classifications and how changes in attribute values can affect the classification.The interface also allows model-developers to interact to see how their model works for different attribute values, and shows them how new data (sent by model-users) fits into their classification model.This allow the biochip designers to detect how their model may be limited so they can retrain the model accordingly.The particular challenge with this project is how we manage and visualise uncertainty related to bio-sensor readings (that can be resultant from the manufacturing process and environmental factors) and the machine learning models, so that biologists can account for this when designing or using chips.Overall, our interface demonstrates the potential of information visualisation to be used to allow developers and model-users to better understand the effectiveness of classification models for their data, as well as the potential of collaborative interfaces to help them work together to build more effective supervised classification models.
Care experiences and health outcomes may suffer greatly because of healthcare professionals' deficient educational preparation and practices. The limited awareness about the impact of stereotypes, implicit/explicit biases, and social determinants of health (SDH) may result in unpleasant care experiences and healthcare professional-patient relationships. Additionally, as healthcare professionals are no less prone to have biases than other people, it is essential to deliver the learning platform to enhance healthcare skills (e.g., awareness of the importance of cultural humility, inclusive communication proficiencies, awareness of the enduring impact of both SDH and implicit/explicit biases on health outcomes, and compassionate and empathetic attitude) of healthcare professionals, which eventually help to raise health equity in society. Moreover, employing the "learning-by-doing" approach directly in real-life clinical practices is less preferable wherein high-risk care is essential. Thus, there is a huge scope to deliver virtual reality-based care practices by engaging the digital experiential learning and human-computer interaction (HCI) approach to enhance patient care experiences, healthcare experiences, and healthcare skills. Thus, this research provides the computer-supported experiential learning (CSEL) approach-based tool or mobile application that facilitates virtual reality-based serious role-playing scenarios to enhance the healthcare skills of healthcare professionals and for public awareness.
We present a new web-based, client-server data processing and visualization framework that supports a flexible workflow, enabling the user to customize different data processing and visualization tasks with tools implemented in different programming languages. Our framework supports server-side applications developed with different languages, allowing visualization researchers to easily make their new techniques available to the target users. The client-side of our framework is implemented in the web browser environment with customizable interface and visualizations. We describe the design of the architecture of our framework and the process of adding new user-defined tasks, followed by the demonstration of the proposed framework on a number of data processing and visualization tasks.
This paper presents an online tool for heritage education that visualizes large-scale digital architectural data of the Roman Forum in Rome, Italy. Leveraging Potree and WebGL, the tool enables the web-based visualization of registered point cloud data as the base framework for the context and the reconstructed geometries with mesh models wrapped with images of standing monuments as the focus. The tool enables users to overview the entire heritage site and examine the fine monument details. The 3D reconstructed mesh and surface models are built to allow users to explore and study the site as it exists today in relation to its reconstructed views. The site is tagged with historical information and imagery for further referencing. The paper concludes with a report on visualization results and an ad-hoc evaluation provided by domain experts.
The paper deals with data visualization for media planning. Media planning database is a collection of heterogeneous content (image/video/graphics, text, data analytics, logical expressions, …) to be aggregated, managed, and displayed together. The main contribution is the multi-layer visualization architecture that allows any type of visualization element to be created in its most appropriate libraries. Such visualization ensures spatio-temporal synchronization of displayed content, as well as the proper evolution with the user interaction. The illustrations are provided on two real (yet anonymized) media plans and show how a complex, 7 steps interaction workflow with the media plan can be dealt with.
Noise, vibration, and harshness (NVH) simulation represents an important step in modern automotive design. It produces large and complex data which is not easy to analyze. The data resides in two domains, the spatial and the frequency domain. In this paper, we extend the current state of the art in visual exploration of such data by supporting comparison tasks. We support the comparison of velocity values of a subset of surface elements for multiple frequency bands. We combine data aggregation on the 3D model with multiple bar charts in a coordinated multiple views system. This new approach allows for an intuitive comparison of multiple velocity values in the context of both domains. We demonstrate the deployment of this approach for an example from the automotive industry, but it can be used with any simulation data that relates to two domains at the same time.
The development of interactive visualization applications that are applicable to many real-world problems is a challenging affair. For every new project, developers need to follow the same repetitive steps of fetching the raw data, transforming the data into processable form, defining visual structures and then displaying them appropriately. To accelerate this, we propose the Versatile Visual Analytics Framework for Exploration and Research (VVAFER). VVAFER is planned to be an extensible visual analytics framework, upon which different applications can be developed with minimum overload at the development side. Through modular architecture, unified data formats, reusable templates and software components, developers will be able to quickly deploy and create their visualization applications by configuring existing templates with their own specific functionalities. In this paper, we describe our motivation for this future framework and its architectural design.
In injection molding machines the molds are rarely equipped with sensor systems. The availability of non-invasive ultrasound-based in-mold sensors provides better means for guiding operators of injection molding machines throughout the production process. However, existing visualizations are mostly limited to plots of temperature and pressure over time. In this work, we present the result of a design study created in collaboration with domain experts. The resulting prototypical application uses real-world data taken from live ultrasound sensor measurements for injection molding cavities captured over multiple cycles during the injection process. Our contribution includes a definition of tasks for setting up and monitoring the machines during the process, and the corresponding web-based visual analysis tool addressing these tasks. The interface consists of a multi-view display with various levels of data aggregation that is updated live for newly streamed data of ongoing injection cycles.
To improve clinical care practice, it is important to understand the variability of clinical pathways executed in different contexts (e.g., pathways in different geographical locations, demographics, and phenotypic groups). A common way of representing clinical pathways is through network-based representations that capture trajectories of treatment steps. However, first-order networks, which are based on the Markovian property and the de facto standard model to represent transitions between steps, often fail to capture real trajectories. This paper introduces a visual analytic tool to explore and compare pathways represented in higher-order networks. Because each higher node in the network is a subtrajectory (i.e., partial or full history of treatment steps), the tool can display true sequences of treatment steps and compute the similarity of the two networks in a space of higher-order nodes. The tool also highlights areas in which the two networks are similar and dissimilar and how a certain subtrajectory is realized differently in different pathways. The paper demonstrates the tool's usefulness by applying it to multiple antidepressant pharmacotherapy pathways for veterans diagnosed with major depressive disorder and by illustrating heterogeneity in prescription patterns across pathways.
In this paper, we introduce FastPoints, a state-of-the-art point cloud renderer for the Unity game development platform. Our program supports standard unprocessed point cloud formats with non-programmatic, drag-and-drop support, and creates an out-of-core data structure for large clouds without requiring an explicit preprocessing step; instead, the software renders a decimated point cloud immediately and constructs a shallow octree online, during which time the Unity editor remains fully interactive.
Computational modeling frequently generates sets of related simulation runs, known as ensembles. These simulations often output 3D surface mesh data, where the geometry and variable values of the mesh are changing with each time step. Comparing these ensembles depends on comparing not only geometric properties, but also associated field data. In this paper, we propose a new metric for comparing mesh geometry combined with field data variables. Our measure is a generalization of the well-known Metro algorithm used in mesh simplification. The Metro algorithm can compare two meshes but doesn't consider field variables. Our metric evaluates a single variable in combination with the mesh geometry. Combining our metric with multidimensional scaling, we visualize a low dimensional representation of all the time steps from a set of example ensembles to demonstrate the effectiveness of this approach.
Teaching color science to Electrical Engineering and Computer Science (EECS) students is critical to preparing them for advanced topics such as graphics, visualization, imaging, Augmented/Virtual Reality. Color historically receive little attention in EECS curriculum; students find it difficult to grasp basic concepts. This is because today's pedagogical approaches are nonintuitive and lack rigor for teaching color science. We develop a set of interactive tutorials that teach color science to EECS students. Each tutorial is backed up by a mathematically rigorous narrative, but is presented in a form that invites students to participate in developing each concept on their own through visualization tools. This paper describes the tutorial series we developed and discusses the design decisions we made.
Given the amount of data created and available to everyone, there is a gap in consumable everyday data analytic tools for anyone to make sense of their data. At anonymous university, we designed an introductory data visualization course to teach college students how to analyze data. Students enrolled in this six-week summer course and used utilize Trifacta \cite{Trifacta}, Tableau \cite{Tableau}, and ObservableHQ \cite{ObservableHQ} on the IEEE VAST Challenge 2022 dataset. The course emphasized the uncertainty and deception involved in data visualization. We structured the course around ethical design choices. In this paper, we describe an overview of the ethical goals of our six-week data visualization summer course, review example student work on the IEEE VAST Challenge, and provide recommendations for ways to add ethical functionality to visualization tools. The goal is for more data visualization tools which are consumable for novice users and support ethical design choices.
We present CoursePathVis, a visual analytics tool for exploring and analyzing students’ progress through a college curriculum using a Sankey diagram. Focusing on four student cohorts in a department, we group students in multiple ways (by their AP courses, term courses, and a user-specified funnel course) to comprehensively understand the data. CoursePathVis helps us identify patterns or outliers that affect student success with these flexible grouping techniques and the funnel-augmented Sankey diagram. Three stakeholders from the same department formulate design requirements and provide an ad-hoc evaluation.
When conducting Coastal Water Navigation, a ship's Navigating Officer (NavO) has multiple sources of data to consider. To obtain the information required to safely manoeuvre the ship, they make use of specialized equipment. The time spent interacting with the equipment is a risk, as it prevents them from visually monitoring the ever-changing maritime environment. Data visualization through Augmented Reality (AR) offers a way to obtain the information while maintaining a proper and effective lookout. Additionally, our research suggests that the information can be presented in new ways. We created a simulator that allows testing and evaluation of AR Navigation Aids (ARNAs). These visualizations were evaluated by subject matter experts through a user study. The user study suggests that ARNAs can improve maritime safety and assist in the conduct of navigation.
3D object clouds, first introduced by Hong and Brooks, visualize the pairwise similarity between a set of objects and a central object of interest. This similarity is used to determine the position of each object within the cloud. However, this does not capture the semantic relationship of all the objects and the lack of consistency may reduce the expectation of finding an object when performing visual search. To generate a semantic 3D object cloud, we define and subsequently minimize an energy function that captures the pairwise similarity amongst all objects within the cloud. The energy is minimized using several statistical machine learning techniques and we show that the generated layouts from such techniques outperform those of other algorithms on a variety of metrics for evaluating layouts.
This paper presents Nirmaan, an open-source web-based tool for generating synthetic datasets of multiclass blobs for use in research related to scatterplots. We demonstrate how to use Nirmaan to generate datasets in the context of a user study where users must determine the centers of each class, but this tool can be used to generate datasets for other scatterplot tasks as well.
Simulation is a recognized and much-appreciated tool in healthcare and education. Advances in simulation have led to the burgeoning of various technologies. In recent years, one such technological advancement has been Augmented Reality (AR). Augmented Reality simulations have been implemented in healthcare on various fronts with the help of a plethora of devices including cellphones, tablets, and wearable AR headsets. AR headsets offer the most immersive experience of the AR simulation as they are head-mounted and offer a stereoscopic view of the superimposed 3D models through the attached goggles overlaid on real-world surfaces. To this effect, it is important to understand the performance capabilities of the AR headsets based on workload. In this paper, our objective is to compare the performances of two prominent AR headsets of today, the Microsoft Hololens and the Magic Leap One. We use surgical AR software that allows the surgeons to show internal structures, such as the rib cage, to assist in the surgery as a reference application to obtain performance numbers for those AR devices. Based on our research, there are no performance measurements and recommendations available for these types of devices in general yet. Introduction In an attempt to measure the feasibility and effectiveness of using AR in surgery and nursing education, we developed an application titled ARiSE (Augmented Reality in Surgery and Education) [39]. We incorporated two facets of this application, one to be used during surgery in the Operating Room (OR), and another to assist in the education of nursing students. Surgeons would use this application in the OR during rib-plating surgery and be able to visualize an accurate model of the patient’s rib cage derived from computerized tomography (CT) scans outside their body. The nursing education application would be used by nursing students during the training of fundamental cardiopulmonary physical assessment skills. The students will be able to visualize stock models of various human organs overlaid on manikins along with visual guides to correct auscultation assessment. The aforementioned applications were developed and deployed into the first generation Microsoft Hololens and Magic Leap One AR headsets for practical use. While the application was deployed successfully and demonstrated accurate usability in both devices, our objective in this paper was to measure and compare the performances between the two AR headsets to derive recommendations for when to use which of these devices. The contributions of this paper are as follows: 1. Direct comparison of head-mounted augmented reality devices from the major brands, namely Microsoft and Magic Leap. 2. Expert evaluation based on real-world application tested with the help of domain specialists. 3. Recommendations for head-mounted Augmented Reality devices. Related Work In this section, we discuss some of the other works that relate to our project and use augmented reality techniques and devices. The related work is split into separated subsections with AR being the common theme applied to different medical areas. Augmented Reality in Mobile Devices for Medical Learning Required clinical content cannot always be imparted in live settings due to various restrictions. Educators have instead started using simulation to enhance clinical education. AR simulations have been used to assist the teaching of emergency situations, procedural training, and anatomy [35]. One such AR simulation is described by Von Jan et al. [1] in their paper. The researchers present an application that may be implemented on cellphones and tablet devices that present life-like scenarios which are overlaid on real-world objects. The trainee would visualize these scenarios through their mobile or tablet devices. This application is called mARble, and the researchers report their findings that indicate that AR enhances learning in medical education settings, specifically for subjects that are visually oriented. Augmented Reality Used in Education In their paper, Steve Chi-Yin Yuen et al. [13] have implemented AR in education and training and evaluated its efficiency. The researchers discuss the applications of AR in various fields including architecture, advertising, entertainment, medicine, gaming, books, travel, and the military. With respect to medical education, their results show AR enhancing surgical procedures and aiding clinical procedures by enhancing efficiency, reducing cost, and improving safety. The researchers also state that AR ahs the potential to invent new clinical and surgical procedures. AR has been integrated with existing medical equipment by Fischer et al. in their research [17]. There has also been research that claims AR to have the potential to make surgery minimally invasive [13] and also to enhance the learning experience in educational settings [29]. Chien et al. have used AR to assist in teaching students the anatomy of a 3D skull [16]. Researchers have also demonstrated that AR may enhance the teaching of human anatomy [19]. AR in Nursing Education Wuller et. al. have reviewed existing AR research to assist nursing education [30]. Foronda et. al. have described 3 types of AR applications used to supplement nursing education [6]. Researchers use the Microsoft Hololens to overlay muscles and bones of the human anatomy on manikins. Rahn et. al., overlay 3D models of human organs in real-time on students using iPads[31]. AR was also used with the help of iPads by Abersold et. al. in their study to assist in the training of the placement of the nasogastric tube(NGT) [32]. Ferguson et. al. have claimed game-based AR applications as having the potential to enhance nursing education [33]. This is also supported by Garrett et. al. who demonstrate improved nursing and clinical skills acquisition in students who participated in AR training scenarios [34]. Simulating Surgeries Scott Delp et al. have reviewed the shortcomings of educating medical personnel in providing appropriate emergency care [2]. In their research Samset et al. [14] developed AR tools for minimal invasive therapies (MIT). Scenarios presented by them include liver surgery, liver tumors, and cardiac surgery. With the help of AR the researchers superimpose real-world objects with 3D models obtained from CT scans. Results demonstrated improved surgical procedures and hence the potential of AR to improve healthcare in terms of utility, quality, and cost-effectiveness. Other research has also been conducted with regards to using AR during surgery. Kawamata et al. describe an AR application in their research that assists in the surgery of pituitary tumors [18]. Their results demonstrated this type of AR navigation allowing surgeons to perform accurate and safe endoscopic operations on these tumors. Memory Retention While Using AR Using Steady State Topography (SST) brain imaging to examine the brain activity of people who participated in AR and non-AR tasks, Heather Andrew et. al. [12] found that the visual attention is almost double when performing AR tasks when compared to non-AR tasks. The author also found that what is stored in memory is 70% higher for AR experiences [12]. Other studies show that the long-term memory of the learner can be enhanced by using multiple media interactions in the learning process [11]. Adedukon-Shittu et. al. have also demonstrated the effectiveness of AR technology with regards to enhancing memory retention and performance [23]. Other studies have also demonstrated the enhanced knowledge acquisition and retention of adequate memory when using AR as a supplemental tool in the education process [24]. Feasibility of Using AR to Train Resuscitation Steve Balian et al. [8] introduced a method of testing the feasibility of using augmented reality to educate healthcare providers about administration of Cardio Pulmonary Resuscitation (CPR). Using the Microsoft Hololens to provide users with audio and visual feedback, the blood flow in the human body was superimposed in real time onto a manikin. The study deployed 51 volunteers for this study. The volunteering health care providers were asked to perform CPR using only the Hololens for two minutes. The chest compression parameters were then recorded for this test. The participants generally responded positively to the system. The approach was perceived to be realistic and the AR was considered a helpful tool for training in medical education. Among the volunteers, 94% stated that they would be willing to use this application for CPR training in the future. The further support the notion of AR’s usefulness in education, Balien et al. successfully demonstrated another augmented reality tool that proved to be valuable for existing education approaches in medical training[16]. Menon et al. [37] developed an augmented reality application to improve the training of nursing students that showed a measurable improvement in student outcomes. Time and again augmented reality has proven to be advantageous when integrated into education in terms of novelty, memory retention, and knowledge gained [14] [12] [23] [24] . AR Triage Training for Multi-Casualty Scenarios The order in which patients are treated can have a detrimental effect on the survival rate of a group of patients. Hence, triage, i.e. selecting the most critical patients based on their chance of survival is crucial. John Hendricks et al. [4] devised a virtual reality simulation that assists medical personnel in their training and military field medics in making appropriate decisions in triage training environments. Their model deploys a scene in which users encounter a virtual patient with multiple injury scenarios. The virtual patients can vary with respect to their injuries as well physiological conditions and these conditions can evolve with timebased on their injuries. The injuries are visually supported by animations, such as bleeding and seizures. Augmented rea
