Visual Dashboard Research Articles

The Trial Enrollment Diversity Dashboard for Acute Leukemia Clinical Research: Intervention Development and Cohort Analysis.

Participation in acute leukemia clinical trials is inequitable across multiple sociodemographic categories. Tools that provide researchers with performance feedback on the representativeness of the patients they enroll are limited. We aimed to develop an electronic health record (EHR)-based dashboard to provide such feedback and to describe any enrollment inequities uncovered. We created a visual dashboard linking leukemia clinical trial registration and EHR data at the Dana-Farber Cancer Institute. Accuracy of a patient inclusion and assignment algorithm was tested with a target area under the receiver-operator curve (AUROC) of >0.90 against manual review. Demographic metric identification, visualization construction, and dashboard refinement were performed through stakeholder cognitive testing. Analysis of a recent 5-year cohort generated by the final algorithm assessed bivariate associations between enrollment and demographic metrics. Multivariable logistic regression included significant bivariate results. The final algorithm assignment AUROC was 0.98. Metrics were identified and visualizations successfully constructed. Fourteen individuals participated in testing and identified areas for revision: category mergers, denominator filters, and data delivery preferences. In the initial cohort of 1,315 patients, 1,020 (77.6%) had enrolled in any study protocol: 553 (42.1%) in a treatment trial and 936 (71.2%) in a biobanking study. In a multivariable model, older age (odds ratio [OR], 0.83 [95% CI, 0.73 to 0.94]) and Non-Hispanic Black race-ethnicity (OR, 0.38 [95% CI, 0.18 to 0.82]) were associated with lower enrollment, and English primary language with higher enrollment (OR, 2.50 [95% CI, 1.30 to 4.79]). We developed a research participation equity performance feedback dashboard for clinical researchers, and we identified actionable inequities. Next steps include feasibility and efficacy testing as well as implementation.

Immediate Impact of a Patient-Reported Outcome Measure Visual Dashboard on Cleft lip and Palate Care Provision.

Cleft-related Patient Reported Outcome Measure (PROM) results were formatted into graphical displays for children scoring below the 25th percentile on one or more scales. Reports were piloted in a multidisciplinary clinic where providers reviewed them, and their impact was qualitatively recorded. Graphical PROM reports informed discussions, led to treatment plan changes, and raised awareness of unmet psychosocial needs. Because of the success of this quality improvement pilot, visual PROM reports will become a regular part of our multidisciplinary cleft care. More broadly, graphical PROM data display facilitates better understanding of the patient's perspective and leads to more informed visits.

Organizational decision making and analytics: An experimental study on dashboard visualizations

Although analytics have become a widespread practice, we still have minimal knowledge about how dashboards influence decision-makers and through what mechanisms they enhance decision making. In this study, we built on an experiment-based approach with mock-up visualizations and recruited 524 participants, who were divided into two groups (A and B) with variations in their visualizations. We found that the format, currency, and completeness of information indirectly affect decision making quality by reducing the perceived task complexity and enhancing information satisfaction. Our results contribute to a better understanding of the role of visual representation of information quality on dashboard visualizations.

Constructing a User-Centric Visual Real-Time Surgical Dashboard.

The existing surgery timetable is very simple, not user-friendly, and has very limited information. This article outlines the creation of a surgical dynamic dashboard for users, using Microsoft Power BI. The dashboard was developed based on in-depth interviews with the surgical team members to determine their requirements. The outcome of dashboard was evaluated by 5-likert scale questionnaire to measure satisfaction of all surgical team members. All team members were very satisfied with the dashboard compared to the existing surgery timetable. In addition, with the function of auto-generated analytic reports through data criteria selection on the dashboard saved time on manually generating reports. This study supports to replace the existing surgery timetable by the user-centric and real time surgical dashboard.

Using Natural Language Processing to Visualize Narrative Feedback in a Medical Student Performance Dashboard.

Clinical competency committees rely on narrative feedback for important insight into learner performance, but reviewing comments can be time-consuming. Techniques such as natural language processing (NLP) could create efficiencies in narrative feedback review. In this study, the authors explored whether using NLP to create a visual dashboard of narrative feedback to preclerkship medical students would improve the competency review efficiency. Preclerkship competency review data collected at the Northwestern University Feinberg School of Medicine from 2014 to 2021 were used to identify relevant features of narrative data associated with review outcome (ready or not ready) and draft visual summary reports of the findings. A user needs analysis was held with experienced reviewers to better understand work processes in December 2019. Dashboards were designed based on this input to help reviewers efficiently navigate large amounts of narrative data. The dashboards displayed the model's prediction of the review outcome along with visualizations of how narratives in a student's portfolio compared with previous students' narratives. Excerpts of the most relevant comments were also provided. Six faculty reviewers who comprised the competency committee in spring 2023 were surveyed on the dashboard's utility. Reviewers found the predictive component of the dashboard most useful. Only 1 of 6 reviewers (17%) agreed that the dashboard improved process efficiency. However, 3 (50%) thought the visuals made them more confident in decisions about competence, and 3 (50%) thought they would use the visual summaries for future reviews. The outcomes highlight limitations of visualizing and summarizing narrative feedback in a comprehensive assessment system. Future work will explore how to optimize the dashboards to meet reviewer needs. Ongoing advancements in large language models may facilitate these efforts. Opportunities to collaborate with other institutions to apply the model to an external context will also be sought.

Visual Analytics for Data-Driven Understanding of the Substance Use Disorder Epidemic.

The substance use disorder epidemic has emerged as a serious public health crisis, presenting complex challenges. Visual analytics offers a unique approach to address this complexity and facilitate effective interventions. This paper details the development of an innovative visual analytics dashboard, aimed at enhancing our understanding of the substance use disorder epidemic. By employing record linkage techniques, we integrate diverse data sources to provide a comprehensive view of the epidemic. Adherence to responsive, open, and user-centered design principles ensures the dashboard's usefulness and usability. Our approach to data and design encourages collaboration among various stakeholders, including researchers, politicians, and healthcare practitioners. Through illustrative outputs, we demonstrate how the dashboard can deepen our understanding of the epidemic, support intervention strategies, and evaluate the effectiveness of implemented measures. The paper concludes with a discussion of the dashboard's use cases and limitations.

The design of a quality improvement dashboard for monitoring spinal cord and column injuries

BackgroundInteractive dashboards are a powerful tool for dynamic visualization and monitoring of patient performance and serve as a useful to for optimal decision-making. The National Spinal Column and Cord Injury Registry of Iran (NSCIR-IR) was designed to efficiently display and broadcast important patient care data. This has been achieved through an electronic dashboard display (graph and visual displays), rather than traditional static paper reports (text). ObjectivesThe objective of this study was to design and develop an electronic visual dashboard as a display system to monitor the quality of care in the NSCIR-IR collaborating centers. MethodsThe indicators chosen were 20 pre-hospital and in-hospital quality of care (QoC) assessment tool indicators. A structured query was created from the NSCIR-IR system database to create the dashboard database. The Microsoft Power BI software was used. After data cleaning, filtering of erroneous records, and modeling, visual displays were designed and evaluated. ResultsThe dashboard reported on quality of care (QoC) for 2,745 patients registered in NSCIR-IR. 17% of registered cases had at least one data error in the quality of care indicators. These errors were automatically filtered by the system. The two most prominent weaknesses in (QoC indicators were delay in patient transfer by EMS (Mean and SD were 9.54 ± 13.8 h) and timing of surgical spinal cord decompression (114.5 ± 45.3 h). ConclusionsElectronic dashboards provide efficient and concise data summaries “at a glance”. However, their value and accuracy are dependent on the entered data quality. Identifying data source errors and correcting them continuously led to improved quality of data.

Measuring the Reach and Impact of Information Warfare

Information is a critical component of national power, with new information narratives emerging daily. While some narratives deserve attention by leaders, others lack enough traction to warrant attention. In the context of Information Warfare, leaders must understand key metrics of emerging narratives to determine their importance. Faced with the problem that leaders do not know if a social media story matters, we created a dashboard to aid leaders in identifying Information Warfare campaigns and their impacts. The methodology consisted of measuring four metrics of distinct narratives: reach, virality, propagation, and organic versus inorganic activity. Taken together, these metrics show how narratives spread, the speed of spread, authenticity, and impact. When packaged together in dashboard visualizations, these metrics enable informed decision making in strategic environments in the information dimension.

Use of Explainable AI Algorithm Revealing Longitudinal Changes in Practice Patterns and Toxicity Models

Dosimetric constraints evolve as clinicians implement practice changes, requiring modeling approaches to be dynamic. We applied a semi-automated explainable artificial intelligence (eAI) algorithm and dashboard visualizations to model dysphagia and xerostomia for head and neck cancer patients. We coupled a large, comprehensive, "real-world" database to the eAI for discovery of features with the strongest combined statistical and machine learning based evidence and to identify clinically actionable thresholds. Cohort included 758 patients treated 2017-2021 for HN cancer with conventional fractionation. Features included age, sex, diagnosis, staging, chemotherapy, smoking and alcohol status, BMI, weight loss, re-simulation, DVH curves, PTV and OAR volumes. Patients were scored for toxicity within 2 yrs of RT for dysphagia grade ≥ 3 and xerostomia grade ≥ 2. Bootstrap resampling of thresholds, ROC-AUC, PR-ROC, SN, SP, F1 and diagnostic odds ratio was used to statistically profile strength of evidence for candidate features. XGBoost models with 10-fold cross validation were repeated (n = 20) to identify mean and CIs for statistical measures of predictions. DVH metrics included standard template values and those with highest statistical evidence and low cross correlation with other features. Backward feature selection was used to identify the most relevant feature subset, where the least informative feature is iteratively removed from the model. This workflow was repeated by year and overall. Annual incidence of dysphagia averaged 0.13 ± 0.02 overall years. Xerostomia incidence decreased from 0.32 to 0.12 (2017-2021). Box-whisker plots by year showed consistent reductions in standard practice toxicity linked DVH metric values. Median dose to superior constrictors (PCM), contralateral parotid and contralateral submandibular gland (SMG) declined from 2017 to 2021 by 48 to 33 Gy, 17 to 10 Gy, and 28 to 22 Gy respectively. Statistics of XGBoost models of dysphagia for all years were ROC-AUC = 0.72 ± 0.05. Strongest overall years predictors were Oral Cavity (OC) D50%[Gy] < 32, inferior PCM Max [Gy] < 60, contralateral SMG D10%[Gy] < 53 and use of Paclitaxel. Xerostomia models were less predictive with ROC-AUC = 0.65 ± 0.05. Strongest predictors over each year were ipsilateral parotid D30%[Gy] < 35, contralateral SMG D96%[Gy] < 18.4, and overall staging < II. Predictive features varied substantially by year for both, showing the most consistency for SMG doses. For example, OC D50%[Gy] < 27 and contralateral SMG D96%[Gy] < 18 dominated xerostomia model in 2017 but not in 2021 when practice norms shifted to lower doses. As OAR doses were systematically reduced, statistical and AI models evidence highlighted contralateral SMG dose as important to both dysphagia and xerostomia for clinical practice change. The "real-world" database + eAI + visualization dashboards provided a method for continuous learning as clinical practice changes.

MANAJEMEN PROYEK PEMBUATAN DASHBOARD UNTUK VISUALISASI CURAH HUJAN DI JAKARTA

Project management is a way for organizing to managing and completing projects from start to finish. Using weather data collected from BMKG to carry out data processing by creating a dashboard to display rainfall visualizations using Power BI. This methode research implements use the BI roadmap method. The purpose of this research is to be one of the ways to make decisions. The purpose of the results in this research, it is hoped that making a dashboard visualizations can be useful for users, namely everyone who needs weather information for outdoor activities.

Analisis Visualisasi Data Prestasi Mahasiswa Universitas Lampung Menggunakan Tableau

This research focuses on visualizing student academic and non-academic achievement data for the years 2018, 2019, 2020, as well as data related to the 2020 MBKM program at the University of Lampung. The data is processed using Tableau software, allowing for the examination of visual patterns in achievement data based on key attributes, including types of achievements, participants categorized by faculties, and achievement levels classified into three categories: international, national, regional, and provincial achievements. Tableau Public Tools is a software application used for analyzing and presenting data sets to support decision-making processes and assist in organizational data analysis. The output produced using Tableau is presented in the form of a visual dashboard, presenting pre-defined attribute data. This dashboard offers valuable insights and graphical representations of achievement attribute data, which can be utilized for evaluating achievement data by BP2M staff and capturing the interest of the University of Lampung community.

Similarities in COVID-19 Mortality Between Canadian Provinces and American States Before Vaccines Were Available.

Canada and the USA are often compared for their markedly different approaches to health care despite cultural similarities and sharing the world's longest international boundary. The period between the onset of the COVID-19 pandemic in January 2020 and the availability of a vaccine in December 2020 offers an ideal opportunity to compare subnational Canadian and American pandemic mortality. Preventing the spread of COVID-19 was through compliance with health orders and best practices; treatment was only available to those admitted to hospitals and whose lives were at risk. Using publicly available data from the Johns Hopkins University 2019 Novel Coronavirus Visual Dashboard, we seek to uncover if there were any similarities in Canadian provinces' and American states' monthly COVID-19 mortality per 100,000 people, building on a broader scientific push towards understanding the successes and failures of different health systems in the pandemic. The similar province and state cumulative COVID-19 mortality rate trajectories identified in our analyses do not amount to intuitive comparative jurisdictions which suggests the importance of identifying localized pandemic responses.

Informing clinical assessment by contextualizing post-hoc explanations of risk prediction models in type-2 diabetes

Medical experts may use Artificial Intelligence (AI) systems with greater trust if these are supported by ‘contextual explanations’ that let the practitioner connect system inferences to their context of use. However, their importance in improving model usage and understanding has not been extensively studied. Hence, we consider a comorbidity risk prediction scenario and focus on contexts regarding the patients’ clinical state, AI predictions about their risk of complications, and algorithmic explanations supporting the predictions. We explore how relevant information for such dimensions can be extracted from Medical guidelines to answer typical questions from clinical practitioners. We identify this as a question answering (QA) task and employ several state-of-the-art Large Language Models (LLM) to present contexts around risk prediction model inferences and evaluate their acceptability. Finally, we study the benefits of contextual explanations by building an end-to-end AI pipeline including data cohorting, AI risk modeling, post-hoc model explanations, and prototyped a visual dashboard to present the combined insights from different context dimensions and data sources, while predicting and identifying the drivers of risk of Chronic Kidney Disease (CKD) - a common type-2 diabetes (T2DM) comorbidity. All of these steps were performed in deep engagement with medical experts, including a final evaluation of the dashboard results by an expert medical panel. We show that LLMs, in particular BERT and SciBERT, can be readily deployed to extract some relevant explanations to support clinical usage. To understand the value-add of the contextual explanations, the expert panel evaluated these regarding actionable insights in the relevant clinical setting. Overall, our paper is one of the first end-to-end analyses identifying the feasibility and benefits of contextual explanations in a real-world clinical use case. Our findings can help improve clinicians’ usage of AI models.

Real-Time Anomaly Detection in Cold Chain Transportation Using IoT Technology

There are approximately 88 million tonnes of food waste generated annually in the EU alone. Food spoilage during distribution accounts for some of this waste. To minimise this spoilage, it is of utmost importance to maintain the cold chain during the transportation of perishable foods such as meats, fruits, and vegetables. However, these products are often unfortunately wasted in large quantities when unpredictable failures occur in the refrigeration units of transport vehicles. This work proposes a real-time IoT anomaly detection system to detect equipment failures and provide decision support options to warehouse staff and delivery drivers, thus reducing potential food wastage. We developed a bespoke Internet of Things (IoT) solution for real-time product monitoring and alerting during cold chain transportation, which is based on the Digital Matter Eagle cellular data logger and two temperature probes. A visual dashboard was developed to allow logistics staff to perform monitoring, and business-defined temperature thresholds were used to develop a text and email decision support system, notifying relevant staff members if anomalies were detected. The IoT anomaly detection system was deployed with Musgrave Marketplace, Ireland’s largest grocery distributor, in three of their delivery vans operating in the greater Belfast area. Results show that the LTE-M cellular IoT system is power efficient and avoids sending false alerts due to the novel alerting system which was developed based on trip detection.

Promoting equity, inclusion, and efficiency: A team science approach to the development of authorship guidelines for a multi-disciplinary research team.

Large research teams and consortia present challenges for authorship. The number of disciplines involved in the research can further complicate approaches to manuscript development and leadership. The CHARM team, representing a multi-disciplinary, multi-institutional genomics implementation study, participated in facilitated discussions inspired by team science methodologies. The discussions were centered on team members' past experiences with authorship and perspectives on authorship in a large research team context. Team members identified challenges and opportunities that were used to create guidelines and administrative tools to support manuscript development. The guidelines were organized by the three values of equity, inclusion, and efficiency and included eight principles. A visual dashboard was created to allow all team members to see who was leading or involved in each paper. Additional tools to promote equity, inclusion, and efficiency included providing standardized project management for each manuscript and making "concept sheets" for each manuscript accessible to all team members. The process used in CHARM can be used by other large research teams and consortia to equitably distribute lead authorship opportunities, foster coauthor inclusion, and efficiently work with large authorship groups.

1047: THE USE OF VISUAL ANALYTICS TO MONITOR PICU PATIENT TRANSFER ORDERS TO ACUTE CARE

Introduction: Timely transfers from the PICU to acute care are essential to improve patient flow and admission readiness. To improve the patient transfer flow, the QI team needed objective data. We created a dashboard to monitor the transfer orders time of the day and when the actual transfer occurs. Methods: We developed a visual dashboard using the Tableau (version 2020.4.5). The tool tracks the patient transfer orders from the PICU to the general and surgical ward. The transfer orders are monitored daily, from 7 am until 12 am hourly and from 12 am to 6 am as one value. The transfer order to transfer start time is monitored and reported as average and median values. The data can be filtered by transfer order date, transfer destination, and transfer order to transfer start. When a patient has multiple transfer orders, we choose the one closest to the 24 hours before the transfer. The data is presented in separate graphs for transfer orders before noon and before 2 pm since it was the target that the QI team is focused on monitoring and improving. These graphs have on the y-axis the percentage of transfer orders and on the x-axis the weekly date. The average, the 2SD, the overall, and the slope is calculated and expressed linearly. The transfer orders by the hour are calculated as a percentage of the total count, with the total count on the axis and the hour on the x-axis. The transfer order transfer starts in minutes and is calculated monthly. Results: We obtained baseline results which helped to develop strategies to improve the time for patient transfer orders. Our PICU baseline percentage of patient transfer orders before noon was 33.5 %, and before 2 pm, 44%. By the end of the six-month period with PDSA improvement cycles, our noon transfer orders increased to 50% and 75% by 2 pm. Conclusions: We used visual analytics to monitor the PICU transfer orders, focused on the percentage of transfer orders before noon and 2 pm and the time from transfer order to transfer start. The visual analytics helped the team to establish baseline data and monitor over time the results after the implemented changes. After obtaining the data, the QI team created a transfer process map and recognized different areas for improvement. The team implemented a systematic approach for changes that we can monitor in real-time.

Use of interrupted Time Series Design in COVID-19 data of Nepal

Introduction: Nepal was hit hard by COVID-19 pandemic and is still struggling with its implications for individuals, societies, and health systems. We applied Interrupted Time Series (ITS) analysis to see if the government's decision to end two nationwide lockdowns had an impact on the average daily new cases of COVID-19 reported in Nepal.&#x0D; &#x0D; Method: ITS analysis on daily new cases of COVID-19 was performed for first and second nationwide lockdown on data of Nepal from data depository for 2019 Novel Coronavirus Visual Dashboard operated by Johns Hopkins University Center for Systems Science and Engineering. Impact of ''ending nationwide lockdown'' and possible associated factors were investigated.&#x0D; Result: The impact of removing first nationwide lockdown contributed to statistically significant rise of an average difference of 899 daily new cases due to community transmission of COVID-19. During second lockdown, even after imposing lockdown, cases overwhelmed existing healthcare system due to high infectivity of new Delta variant followed by a lack of adherence to public health measures and delayed decision to impose lockdown due to economic reasons. Whereas significant decline of cases was observed with an average difference of 2970 daily new cases after ending second nationwide lockdown mostly due to vaccine acceptance.&#x0D; &#x0D; Conclusion: First lockdown was imposed early due to uncertainty about progression of disease, curative measures and unavailability of vaccines. Ending of first lockdown was done untimely due to economic reasons and festive seasons. The unusual decline in cases after ending second lockdown could be contributed to increased vaccination in the country.&#x0D;

Dashboard for the Management and Acceptance of Customer Orders

Abstract Background: This paper focuses on activities related to Customer Orders Management withing an auto components plant in the Automotive Industry. The main challenge was highlighted: customers don’t always regard the flexibility rules agreed with the company. Hence, planners must decide if variation in ordered quantity can be accepted in the forecast period or if adjusting is necessary. Objectives: The purpose was not only to streamline the decision-making process in the planning team but also to provide essential tools for the execution of their daily tasks – a visual and interactive dashboard to assess whether variations in customer orders were within the limits agreed with the company. Methods/Approach: Following Lean information management and business intelligence principles, a thorough process analysis was carried out, centralized and standardized reports were created that served as databases, and the dashboard was developed. Results: The proposed tool allowed reductions from 3,5h per week, spent mainly on collecting data, calculating variations, and selecting and adjusting the flexibility limits, to 0,2h a day per planner. Conclusions: Besides streamlining planners’ daily activities, main contributions regard the promotion of digital transformation, data-driven decision-making, and an automated record of customer order variations that could easily be adapted to suppliers.

VisOJ: real-time visual learning analytics dashboard for online programming judge

VisOJ: real-time visual learning analytics dashboard for online programming judge

The development of a visual dashboard report to assess physician assistant and nurse practitioner financial and clinical productivity

The evolving COVID-19 pandemic has unevenly affected academic medical centers (AMCs), which are experiencing resource-constraints and liquidity challenges while at the same time facing high pressures to improve patient access and clinical outcomes. Technological advancements in the field of data analytics can enable AMCs to achieve operational efficiencies and improve bottom-line expectations. While there are vetted analytical tools available to track physician productivity, there is a significant paucity of analytical instruments described in the literature to adequately track clinical and financial productivity of physician assistants (PAs) and nurse practitioners (NPs) employed at AMCs. Moreover, there is no general guidance on the development of a dashboard to track PA/NP clinical and financial productivity at the individual, department, or enterprise level. At our institution, there was insufficient tracking of PA/NP productivity across many clinical areas within the enterprise. Thus, the aim of the project is to leverage our institution’s existing visualization tools coupled with the right analytics to track PA/NP productivity trends using a dashboard report.MethodsWe created an intuitive and customizable highly visual clinical/financial analytical dashboard to track productivity of PAs/NPs employed at our AMC.ResultsThe APP financial and clinical dashboard is organized into two main components. The volume-based key performance indicators (KPIs) included work relative value units (wRVUs), gross charges, collections (payments), and payer-mix. The session utilization (KPIs) included (e.g., new versus return patient ratios, encounter type, visit volume, and visits per session by provider). After successful piloting, the dashboard was deployed across multiple specialty areas and results showed improved data transparency and reliable tracking of PAs/NPs productivity across the enterprise. The dashboard analytics were also helpful in assessing PA/NP recruitment requests, independent practice sessions, and performance expectations.ConclusionTo our knowledge, this is the first paper to highlight steps AMCs can take in developing, validating, and deploying a financial/clinical dashboard specific to PAs/NPs. However, empirical research is needed to assess the impact of qualitative and quantitative dashboards on provider engagement, revenue, and quality of care.