Public health studies generate extensive datasets providing important insights into human health. The Norwegian Mother, Father, and Child Cohort Study (MoBa) is a longitudinal cohort study capturing information on pregnancy and early childhood. This information helps uncover the genetic underpinnings of traits or diseases drawing interest from researchers in public health. Non-experts are also attracted to the study, both to understand their contributions as data donors and relevant health determinants. However, the complexity of MoBa data hinders its exploration, analysis, and dissemination. We present a design study exploring the needs and uses of the MoBa dataset in a mixed-user context and introducing the MoBa GWAS Explorer, a web-based visual tool for exploration and analysis of MoBa data by a mixed audience. This tool supports experts in exploring and analyzing MoBa data interactively. Though designed primarily for researchers, we explored the potential for onboarding strategies to make this tool more approachable for non-experts. We conducted a qualitative study with both user groups to evaluate their experience with the tool and its usability. Our evaluation indicates that the application, along with the integrated onboarding, has potential to serve both expert and non-expert groups. Supplementary materials for this study are available at https://osf.io/k5bvj/.
In the precision medicine paradigm, oncological treatment leverages complex ensemble datasets of similar patients to estimate the outcomes for a current patient. A key challenge is developing and deploying easy-to-understand AI predictive models for the outcomes of a specific patient, based on patient data from multiple institutions. We describe the lessons learned from the development and deployment of an interactive dashboard to support the analysis of individual head and neck cancer patient outcomes based on cohort data. As required by the project, the dashboard design aims to handle a large client base. The dashboard combines an AI solution with a multi-view interface featuring domain-specific plots to facilitate the visual analysis of patient outcomes and to quickly stratify new patients into risk groups. A year after the successful public deployment of the dashboard, we evaluate it with clinician domain experts. We report the feedback and we reflect on the lessons learned through this experience.
Large Language Models (LLMs) are increasingly used for generating and adapting visualizations for different user groups. While recent efforts have focused on adapting visualizations to users’ cognitive and perceptual abilities, how LLMs cater to the distinct interests and subjective priorities of various stakeholder groups remains largely unexplored. Specifically, LLMs utilise rhetorical elements to prioritise data stories, which can shape user interpretation. We present a systematic approach to assessing how LLMs adapt their visualization rhetoric to match the priorities of different user personas in a healthcare context. Based on qualitative interviews with population health stakeholders, we demonstrate LLMs’ capabilities for (i) understanding user tasks and priorities from interview data, (ii) adapting visualizations to these priorities, and (iii) justifying design choices for the adaptations. Population health data presents an excellent space for experimentation, given: (a) the diversity of stakeholders (e.g., commissioners, population health experts, data analysts, and the public); and (b) the varied purposes and key messages for which visualizations are designed. We reflect on patterns in LLM reasoning about persona-specific design choices—in light of an established analytical framework for rhetorical visualization—and propose open questions to promote safer, more responsible practices in LLM-assisted visualization.
The complexity of intervention studies to assess physical activity (PA) is increasing, resulting in vast amounts of data being recorded in laboratory settings. Recent studies extend datasets with measurements outside the lab using wearable devices, allowing for a bridge to be built between the lab and real-life applications. Such heterogeneous, multigranular datasets impose various challenges for data analysis and visualization, and require tailored approaches to support domain experts. Contrarily, it enables data-driven hypothesis generation, which is particularly valuable in interdisciplinary contexts where theory-driven approaches fall short due to a lack of well-established theoretical foundations. While lab conditions are extensively handled in existing visual interfaces, measurements in everyday life situations are often neglected, yet have an essential impact on the capturing of PA. To facilitate exploration of this data, we propose a visual analytics application consisting of multiple linked views comprising a BiPlot, Variable Distribution plots, and a dense-pixel visualization allowing experts to generate novel interdisciplinary hypotheses based on laboratory and everyday life measurements. We evaluate our application by conducting an expert study with an end user of the application, showcasing the application’s benefits to support experts in solving tasks regarding exploration, pattern identification, association, and comparison.
Injury prevention in sports requires understanding how bio-mechanical risks emerge from movement patterns captured in real-world scenarios. However, identifying and interpreting injury prone events from raw video remains difficult and time-consuming. We present VAIR, a visual analytics system that supports injury risk analysis using 3D human motion reconstructed from sports video. VAIR combines pose estimation, bio-mechanical simulation, and synchronized visualizations to help users explore how joint-level risk indicators evolve over time. Domain experts can inspect movement segments through temporally aligned joint angles, angular velocity, and internal forces to detect patterns associated with known injury mechanisms. Through case studies involving Achilles tendon and Anterior cruciate ligament (ACL) injuries in basketball, we show that VAIR enables more efficient identification and interpretation of risky movements. Expert feedback confirms that VAIR improves diagnostic reasoning and supports both retrospective analysis and proactive intervention planning.
We introduce our ongoing work toward an insight-based evaluation methodology aimed at understanding practitioners' mental models when exploring medical data. It is based on ParcoursVis, a Progressive Visual Analytics system designed to visualize event sequences derived from Electronic Health Records at scale (millions of patients, billions of events), developed in collaboration with the Emergency Departments of 16 Parisian hospitals and with the French Social Security. Building on prior usability validation, our current evaluation focuses on the insights generated by expert users and aims to better understand the exploration strategies they employ when engaging with exploration visualization tools. We describe our system and outline our evaluation protocol, analysis strategy, and preliminary findings. Building on this approach and our pilot results, we contribute a design protocol for conducting insight-based studies under real-world constraints, including the availability of health practitioners whom we were fortunate to interview. Our findings highlight a loop, where the use of the system helps refine data variables identification and the system itself. We aim to shed light on generated insights, to highlight the utility of exploratory tools in health data analysis contexts.
Dementia care requires healthcare professionals to balance a patient’s medical needs with a deep understanding of their personal needs, preferences, and emotional cues. However, current digital tools prioritise quantitative metrics over empathetic engagement, limiting caregivers’ ability to develop a deeper personal understanding of their patients. This paper presents an empathy-centred visualisation framework, developed through a design study, to address this gap. The framework integrates established principles of person-centred care with empathy mapping methodologies to encourage deeper engagement. Our methodology provides a structured approach to designing for indirect end-users, patients whose experience is shaped by a tool they may not directly interact with. To validate the framework, we conducted evaluations with healthcare professionals, including usability testing of a working prototype and a User Experience Questionnaire (UEQ) study. Results suggest the feasibility of the framework, with participants highlighting its potential to support a more personal and empathetic relationship between medical staff and patients. The work starts to explore how empathy could be systematically embedded into visualisation design, as we contribute to ongoing efforts in the data visualisation community to support human-centred, interpretable, and ethically-aligned clinical care, addressing the urgent need to improve dementia patients’ experiences in hospital settings.
The rapid growth of biomedical research has led to an overwhelming volume of literature, making it challenging for researchers to efficiently explore and analyze. While existing tools provide an overview of semantic maps and publication distributions, further refinement is needed to reveal fine-grained nuances and hierarchical topics. To address this, we propose a novel method for hierarchical topic modeling and label generation on 2D semantic maps. Our approach consists of three steps. First, we apply density-based hierarchical clustering using HDBSCAN to construct a topic tree. Second, we employ a novel tree-based TF-IDF method to refine topic representation using MeSH terms, capturing both general and local topic distinctions. Finally, we optimize label positioning using a centroid-based method to enhance visualization.
Practitioners of evidence-based medicine need to know the level of certainty in the evidence they are applying to patient care. We use a living interactive evidence synthesis framework to create and maintain living, interactive systematic reviews (LISRs). With each new update, it is critical to report any changes to the confidence level or certainty of synthesized evidence (CoE) for patient important endpoints. Ascertaining CoE is a complex task and thus challenging in the setting of LISRs. Therefore, we propose a hybrid approach, which leverages an interactive web-based visualization techniques to accelerate the CoE evaluation.
Healthcare Quality Improvement (QI) frequently employs Statistical Process Control (SPC) charts, but current tools are cumbersome, requiring extensive expertise and manual data manipulation. Our SPC ChartR software streamlines SPC chart generation, enabling intuitive exploration and contextual storytelling. This system offers an innovative solution for both experienced QI professionals and clinicians with limited data literacy, and it enhances data visualization efficiency as validated by substantial task completion rate improvements and a high System Usability Scale score.
We conducted usability testing with five patients and eight care team members on a mobile Health application (care team and patients) and dashboard (care team). These digital tools are designed to support Medicaid-insured pregnant individuals who have type 2 diabetes (T2D) to better manage health-related social needs, T2D, and pregnancy. We built prototypes and collected feedback and future recommendations on functionality and user experience. These suggestions will guide future improvements of the digital tools.
The SARS-CoV-2 pandemic gave rise to multiple data analytics strategies and visualizations related to the spread of the virus and community health. These visualizations aim to track SARS-CoV-2 variant diffusion among the population and help public health officials determine what interventions and policies could counter the spread of SARS-CoV-2 variants of interest. Existing visualizations for variant diffusion are typically static and have a rigid workflow. In this paper, we present a new dashboard for the visualization of SARS-CoV-2 variants diffusion. The dashboard, named VISTA, combines multiple datasets in an easy-to-use and intuitive interface that allows users to visually generate numerous analytic tasks, including correlation among regions, comparisons between regional and overall trends, and characterizations of variants with features of interest to public health officials.
We conducted a usability assessment of a resident clinical competency dashboard among eleven Clinical Competency Committee members using the System Usability Scale (SUS) and open-ended questions. Although the average SUS score was 53.47, indicating below-average usability, qualitative feedback highlighted strengths in data integration and interface layout but identified technical issues and requested features for improvement. Findings will inform future development efforts for the dashboard.
Pre-medical students face the challenge of managing rigorous academic and extracurricular demands, which can lead to burnout. Effective tracking and visualization of their activities are crucial in keeping records of student progress. This study aimed to develop and evaluate a user-friendly dashboard tailored for pre-medical student data management. Semi-structured interviews with nine medical sciences baccalaureate program (MSBP) faculty members identified major issues in current data management practices, including standardization and tracking. Using affinity diagramming and Miroboard, five key themes emerged, guiding the creation of an initial dashboard prototype. After iterative critiques and revisions, the final design received positive feedback from the MSBP committee. Limitations include a small sample size and a lack of formal usability testing. Future work will focus on addressing implementation challenges and refining the design based on user feedback.
To monitor trends for late recognition of deterioration, developing a visual analytics dashboard helps address clinical deterioration rates in pediatric health systems. The dashboard enables ongoing trend analysis and detecting outliers in patient demographics or hospital units through control chart implementation using control limits set at 3 standard errors. The deterioration outcomes are defined by published evidence where EHR documentation can inform the cohort needing ICU interventions within a specific time.
Artificial Intelligence (AI) is well-suited to help support complex decision-making tasks within clinical medicine, including clinical imaging applications like radiographic differential diagnosis of central nervous system (CNS) tumors. So far, there have been numerous examples of theoretical AI solutions for this space, for example, large-scale corporate efforts like IBM’s Watson AI. However, clinical implementation remains limited due to factors related to the alignment of this technology in the clinical setting. User-Centered Design (UCD) is a design philosophy that focuses on developing tailored solutions for specific users or user groups. In this study, we applied UCD to develop an explainable AI tool to support clinicians in our use case. Through four design iterations, starting from basic functionality and visualizations, we progressed to functional prototypes in a realistic testing environment. We discuss our motivation and approach for each iteration, along with key insights gained. This UCD process has advanced our conceptual idea from feasibility testing to interactive functional AI interfaces designed for specific clinical and cognitive tasks. It has also provided us with directions to develop further an AI system for the non-invasive diagnosis of CNS tumors.
We introduce ExpLIMEable for enhancing the understanding of Local Interpretable Model-Agnostic Explanations (LIME), with a focus on medical image analysis. LIME is a popular and widely used method in explainable artificial intelligence (XAI) that provides locally faithful and interpretable post-hoc explanations for black box models. However, LIME explanations are not always robust due to variations in perturbation techniques and the selection of interpretable functions. The proposed visual analytics application aims to address these concerns by enabling the users to freely explore and compare the explanations generated by different LIME parameter instances. The application utilizes a convolutional neural network (CNN) for brain MRI tumor classification and allows users to customize post-hoc LIME parameters to gain insights into the model's decision-making process. The developed application assists machine learning developers in understanding the limitations of LIME and its sensitivity to different parameters, as well as the doctors in providing an explanation to machine learning models, enabling more informed decision-making, with the ultimate goal of improving its robustness and explanation quality.
This demo paper introduces the final version of a cohort analysis module for the support of treating patients with inflammatory bowel disease (IBD). It is not trivial to correctly diagnose the specific IBD in patients, and wrongly treated patients have to endure the disease effects for a long time, with large costs for the individuals and the healthcare systems. The goal of this work is complementing the examination of individual patients with interactive analyses of cohorts and populations with similar disease patterns to support learning from such similarities for future treatments. We report on additional data and functionality compared to 2021 and discuss an evaluation with eight IBD experts.
Clinical decision support systems based on machine learning are a rising application in healthcare. Early detection of deteriorating conditions provide the opportunity for medical intervention in hospital patients. Recent approaches increasingly rely on Large Language Models such as BERT, because patient data is often in the form of structured temporal data. These models are notoriously hard to interpret and therefore to trust, while precisely trust is an essential principle for technology in healthcare. We develop a visual analytics system to inspect, compare, and explain pre-trained transformer models for a given clinical outcome prediction task. The work is developed on the basis of a large hospital patient dataset and prediction tasks for acute kidney injury and heart failure. Discussion with healthcare professionals confirms that our system can lead to a faster decision process and improved modeling results.
Metastatic hormone-producing tumors have characteristics of both tumors and endocrine disorders with many time-series parameters. Therefore, making treatment decisions is often challenging. Data visualization methods have recently been developed to visualize time series, single or multiple pieces of information, and complex patient information. We focused on metastatic pheochromocytoma and paraganglioma and summarized the clinical needs and dashboard data visualization ideas for precision medicine.
