QualDash: Adaptable Generation of Visualisation Dashboards for Healthcare Quality Improvement

VIEWER: an extensible visual analytics framework for enhancing mental healthcare

OBJECTIVE

A proof-of-concept study aimed at designing and implementing Visual & Interactive Engagement With Electronic Records (VIEWER), a versatile toolkit for visual analytics of clinical data, and systematically evaluating its effectiveness across various clinical applications while gathering feedback for iterative improvements.

MATERIALS AND METHODS

VIEWER is an open-source and extensible toolkit that employs natural language processing and interactive visualization techniques to facilitate the rapid design, development, and deployment of clinical information retrieval, analysis, and visualization at the point of care. Through an iterative and collaborative participatory design approach, VIEWER was designed and implemented in one of the United Kingdom's largest National Health Services mental health Trusts, where its clinical utility and effectiveness were assessed using both quantitative and qualitative methods.

RESULTS

VIEWER provides interactive, problem-focused, and comprehensive views of longitudinal patient data (n = 409 870) from a combination of structured clinical data and unstructured clinical notes. Despite a relatively short adoption period and users' initial unfamiliarity, VIEWER significantly improved performance and task completion speed compared to the standard clinical information system. More than 1000 users and partners in the hospital tested and used VIEWER, reporting high satisfaction and expressed strong interest in incorporating VIEWER into their daily practice.

DISCUSSION

VIEWER provides a cost-effective enhancement to the functionalities of standard clinical information systems, with evaluation offering valuable feedback for future improvements.

CONCLUSION

VIEWER was developed to improve data accessibility and representation across various aspects of healthcare delivery, including population health management and patient monitoring. The deployment of VIEWER highlights the benefits of collaborative refinement in optimizing health informatics solutions for enhanced patient care.

Bridging health registry data acquisition and real-time data analytics

The number of clinical studies and associated research has increased significantly in the last few years. Particularly in rare diseases, an increased effort has been made to integrate, analyse, and develop new knowledge to improve patient stratification and wellbeing. Clinical databases, including digital medical records, hold significant amount of information that can help understand the impact and progression of diseases. Combining and integrating this data however, has provided a challenge for data scientists due to the complex structures of digital medical records and the lack of site wide standardization of data entry. To address these challenges we present a python backed tool, Meda, which aims to collect data from different sources and combines these in a unified database structure for near real-time monitoring of clinical data. Together with an R shiny interface we can provide a near complete platform for real-time analysis and visualization.

Rank Ordered Design Attributes for Health Care Dashboards Including Artificial Intelligence: Usability Study

BACKGROUND

On average, people in the United States visit a doctor 4 times a year, and many of them have chronic illnesses. Because of the increased use of technology, people frequently rely on the internet to access health information and statistics. People use health care information to make better-educated decisions for themselves and others. Health care dashboards should provide pertinent and easily understood data, such as information on timely cancer screenings, so the public can make better-informed decisions. In order to enhance health outcomes, effective dashboards should provide precise data in an accessible and easily digestible manner.

OBJECTIVE

This study identifies the top 15 attributes of a health care dashboard. The objective of this research is to enhance health care dashboards to benefit the public by making better health care information available for more informed decisions by the public and to improve population-level health care outcomes.

METHODS

The authors conducted a survey of health care dashboards with 218 individuals identifying the best practices to consider when creating a public health care dashboard. The data collection was conducted from June 2023 to August 2023. The analyses performed were descriptive statistics, frequencies, and a comparison to a prior study.

RESULTS

From May 2023 to June 2023, we collected 3259 responses in multiple different states around the United States from 218 people aged 18 years or older. The features ranking in descending order of importance are as follows: (1) easy navigation, (2) historical data, (3) simplicity of design, (4) high usability, (5) use of clear descriptions, (6) consistency of data, (7) use of diverse chart types, (8) compliance with the Americans with Disabilities Act, (9) incorporated user feedback, (10) mobile compatibility, (11) comparison data with other entities, (12) storytelling, (13) predictive analytics with artificial intelligence, (14) adjustable thresholds, and (15) charts with tabulated data.

CONCLUSIONS

Future studies can extend the research to other types of dashboards such as bioinformatics, financial, and managerial dashboards as well as confirm these top 15 best practices for medical dashboards with further evidentiary support. The medical informatics community may benefit from standardization to improve efficiency and effectiveness as dashboards can communicate vital information to patients worldwide on critically prominent issues. Furthermore, health care professionals should use these best practices to help increase population health care outcomes by informing health care consumers to make better decisions with better data.

Dashboards to Support Implementation of the Quebec Alzheimer Plan: Evaluation Study With Regional and Professional Considerations

BACKGROUND

Health organizations face the critical task of executing and overseeing comprehensive health care. To address the challenges associated with this task, evidence-based dashboards have emerged as valuable tools. Since 2016, the regional health organizations of Quebec, Canada, have been responsible for ensuring implementation of the Quebec Alzheimer Plan (QAP), a provincial plan that aims to reinforce the capacity of primary care services to detect, diagnose, and treat persons with dementia. Despite the provincial scope of the QAP, the diverse material and human resources across regions introduce variability in the interest, utility, and specific needs associated with these dashboards.

OBJECTIVE

The aim of this study was to assess the interest and utility of dashboards to support the QAP implementation, as well as to determine the needs for improving these aspects according to the perspectives of various types of professionals involved across regions.

METHODS

An evaluative study using qualitative methods was conducted within a collaborative research approach involving different stakeholders, including the ministerial advisor and the four project managers responsible for supporting the implementation of the QAP, as well as researchers/scientific advisors. To support these organizations, we developed tailored, 2-page paper dashboards, detailing quantitative data on the prevalence of dementia, the use of health services by persons with dementia, and achievements and challenges of the QAP implementation in each organization's jurisdiction. We then conducted 23 focus groups with the managers and leading clinicians involved in the implementation of the QAP of each regional health organization. Real-time notes were taken using a structured observation grid. Content analysis was conducted according to different regions (organizations with university mandates or nearby organizations, labeled "university/peripheral"; organizations for which only part of the territory is in rural areas, labeled "mixed"; and organizations in remote or isolated areas, labeled "remote/isolated") and according to different types of participants (managers, leading clinicians, and other participants).

RESULTS

Participants from organizations in all regions expressed interest in these dashboards and found them useful in several ways. However, they highlighted the need for indicators on orphan patients and other health care providers. Differences between regions were observed, particularly in the interest in continuity of care in university/peripheral regions and the need for diagnostic tools adapted to the culture in remote/isolated regions.

CONCLUSIONS

These dashboards support the implementation of an Alzheimer Plan and contribute to the emergence of a learning health care system culture. This project allows each region to increase its monitoring capacity for the implementation of the QAP and facilitates reflection among individuals locally carrying out the implementation. The perspectives expressed will guide the preparation of the next iteration of the dashboards.

Dashboard of Short-Term Postoperative Patient Outcomes for Anesthesiologists: Development and Preliminary Evaluation

BACKGROUND

Anesthesiologists require an understanding of their patients' outcomes to evaluate their performance and improve their practice. Traditionally, anesthesiologists had limited information about their surgical outpatients' outcomes due to minimal contact post discharge. Leveraging digital health innovations for analyzing personal and population outcomes may improve perioperative care. BC Children's Hospital's postoperative follow-up registry for outpatient surgeries collects short-term outcomes such as pain, nausea, and vomiting. Yet, these data were previously not available to anesthesiologists.

OBJECTIVE

This quality improvement study aimed to visualize postoperative outcome data to allow anesthesiologists to reflect on their care and compare their performance with their peers.

METHODS

The postoperative follow-up registry contains nurse-reported postoperative outcomes, including opioid and antiemetic administration in the postanesthetic care unit (PACU), and family-reported outcomes, including pain, nausea, and vomiting, within 24 hours post discharge. Dashboards were iteratively co-designed with 5 anesthesiologists, and a department-wide usability survey gathered anesthesiologists' feedback on the dashboards, allowing further design improvements. A final dashboard version has been deployed, with data updated weekly.

RESULTS

The dashboard contains three sections: (1) 24-hour outcomes, (2) PACU outcomes, and (3) a practice profile containing individual anesthesiologist's case mix, grouped by age groups, sex, and surgical service. At the time of evaluation, the dashboard included 24-hour data from 7877 cases collected from September 2020 to February 2023 and PACU data from 8716 cases collected from April 2021 to February 2023. The co-design process and usability evaluation indicated that anesthesiologists preferred simpler designs for data summaries but also required the ability to explore details of specific outcomes and cases if needed. Anesthesiologists considered security and confidentiality to be key features of the design and most deemed the dashboard information useful and potentially beneficial for their practice.

CONCLUSIONS

We designed and deployed a dynamic, personalized dashboard for anesthesiologists to review their outpatients' short-term postoperative outcomes. This dashboard facilitates personal reflection on individual practice in the context of peer and departmental performance and, hence, the opportunity to evaluate iterative practice changes. Further work is required to establish their effect on improving individual and department performance and patient outcomes.

Use of a Medication Safety Audit and Feedback Tool in the Emergency Department Is Affected by Prescribing Characteristics

BACKGROUND

The Enhancing Quality of Prescribing Practices for Older Veterans Discharged from the Emergency Department (EQUIPPED) program developed an audit and feedback health information technology (IT) solution with the intent to replace the in-person academic detailing service provided by the program. The EQUIPPED dashboard provides emergency department (ED) providers with a personalized view of their prescribing performance.

OBJECTIVES

Here, we analyze the association between ED provider characteristics and viewership of the EQUIPPED dashboard, adding insight into strategies for addressing barriers to initial use.

METHODS

We performed a retrospective analysis of EQUIPPED dashboard viewership among four Veterans Affairs (VA) EDs. We extracted quantitative data from user interaction logs to determine evidence of dashboard use. Provider characteristics and baseline potentially inappropriate medication (PIM) prescribing rate were extracted from the VA's Corporate Data Warehouse. Logistic regression was used to examine the association between dashboard use and provider characteristics.

RESULTS

A total of 82 providers were invited to receive audit and feedback via the EQUIPPED dashboard. Among invited providers, 40 (48.7%) had evidence of at least 1 dashboard view during the 1-year feedback period. Adjusted analyses suggest that providers with a higher baseline PIM prescribing rate were more likely to use the dashboard (odds ratio [OR]: 1.22; 95% confidence interval [CI]: 1.01-1.47). Furthermore, providers at ED site D were more likely to use the dashboard in comparison to the other sites (OR: 9.99; 95% CI: 1.72-58.04) and reportedly had the highest site-level baseline PIM rate.

CONCLUSION

Providers with lower PIM prescribing rates (i.e., <5%) receive communication from an integrated dashboard reminder system that they are "optimal prescribers" which may have discouraged initial attempts to view the dashboard. Site D had the highest baseline PIM rate, but further qualitative investigation is warranted to better understand why site D had the greatest users of the dashboard.

Dashboard Design Patterns

This paper introduces design patterns for dashboards to inform dashboard design processes. Despite a growing number of public examples, case studies, and general guidelines there is surprisingly little design guidance for dashboards. Such guidance is necessary to inspire designs and discuss tradeoffs in, e.g., screenspace, interaction, or information shown. Based on a systematic review of 144 dashboards, we report on eight groups of design patterns that provide common solutions in dashboard design. We discuss combinations of these patterns in "dashboard genres" such as narrative, analytical, or embedded dashboard. We ran a 2-week dashboard design workshop with 23 participants of varying expertise working on their own data and dashboards. We discuss the application of patterns for the dashboard design processes, as well as general design tradeoffs and common challenges. Our work complements previous surveys and aims to support dashboard designers and researchers in co-creation, structured design decisions, as well as future user evaluations about dashboard design guidelines. Detailed pattern descriptions and workshop material can be found online: https://dashboarddesignpatterns.github.io.

MEDLEY: Intent-based Recommendations to Support Dashboard Composition

Despite the ever-growing popularity of dashboards across a wide range of domains, their authoring still remains a tedious and complex process. Current tools offer considerable support for creating individual visualizations but provide limited support for discovering groups of visualizations that can be collectively useful for composing analytic dashboards. To address this problem, we present MEDLEY, a mixed-initiative interface that assists in dashboard composition by recommending dashboard collections (i.e., a logically grouped set of views and filtering widgets) that map to specific analytical intents. Users can specify dashboard intents (namely, measure analysis, change analysis, category analysis, or distribution analysis) explicitly through an input panel in the interface or implicitly by selecting data attributes and views of interest. The system recommends collections based on these analytic intents, and views and widgets can be selected to compose a variety of dashboards. MEDLEY also provides a lightweight direct manipulation interface to configure interactions between views in a dashboard. Based on a study with 13 participants performing both targeted and open-ended tasks, we discuss how MEDLEY's recommendations guide dashboard composition and facilitate different user workflows. Observations from the study identify potential directions for future work, including combining manual view specification with dashboard recommendations and designing natural language interfaces for dashboard authoring.

Visualization for epidemiological modelling: challenges, solutions, reflections and recommendations

We report on an ongoing collaboration between epidemiological modellers and visualization researchers by documenting and reflecting upon knowledge constructs-a series of ideas, approaches and methods taken from existing visualization research and practice-deployed and developed to support modelling of the COVID-19 pandemic. Structured independent commentary on these efforts is synthesized through iterative reflection to develop: evidence of the effectiveness and value of visualization in this context; open problems upon which the research communities may focus; guidance for future activity of this type and recommendations to safeguard the achievements and promote, advance, secure and prepare for future collaborations of this kind. In describing and comparing a series of related projects that were undertaken in unprecedented conditions, our hope is that this unique report, and its rich interactive supplementary materials, will guide the scientific community in embracing visualization in its observation, analysis and modelling of data as well as in disseminating findings. Equally we hope to encourage the visualization community to engage with impactful science in addressing its emerging data challenges. If we are successful, this showcase of activity may stimulate mutually beneficial engagement between communities with complementary expertise to address problems of significance in epidemiology and beyond. See https://ramp-vis.github.io/RAMPVIS-PhilTransA-Supplement/. This article is part of the theme issue 'Technical challenges of modelling real-life epidemics and examples of overcoming these'.

Visualization for epidemiological modelling: challenges, solutions, reflections and recommendations

We report on an ongoing collaboration between epidemiological modellers and visualization researchers by documenting and reflecting upon knowledge constructs-a series of ideas, approaches and methods taken from existing visualization research and practice-deployed and developed to support modelling of the COVID-19 pandemic. Structured independent commentary on these efforts is synthesized through iterative reflection to develop: evidence of the effectiveness and value of visualization in this context; open problems upon which the research communities may focus; guidance for future activity of this type and recommendations to safeguard the achievements and promote, advance, secure and prepare for future collaborations of this kind. In describing and comparing a series of related projects that were undertaken in unprecedented conditions, our hope is that this unique report, and its rich interactive supplementary materials, will guide the scientific community in embracing visualization in its observation, analysis and modelling of data as well as in disseminating findings. Equally we hope to encourage the visualization community to engage with impactful science in addressing its emerging data challenges. If we are successful, this showcase of activity may stimulate mutually beneficial engagement between communities with complementary expertise to address problems of significance in epidemiology and beyond. See https://ramp-vis.github.io/RAMPVIS-PhilTransA-Supplement/. This article is part of the theme issue 'Technical challenges of modelling real-life epidemics and examples of overcoming these'.

Informing the Design of Data Visualization Tools to Monitor the COVID-19 Pandemic in Portugal: A Web-Delphi Participatory Approach

Due to the large amount of data generated by new technologies and information systems in the health arena, health dashboards have become increasingly popular as data visualization tools which stimulate visual perception capabilities. Although the importance of involving users is recognized in dashboard design, a limited number of studies have combined participatory methods with visualization options. This study proposes a novel approach to inform the design of data visualization tools in the COVID-19 context. With the objective of understanding which visualization formats should be incorporated within dashboards for the COVID-19 pandemic, a specifically designed Web-Delphi process was developed to understand the preferences and views of the public in general regarding distinct data visualization formats. The design of the Delphi process aimed at considering not only the theory-based evidence regarding input data and visualization formats but also the perception of final users. The developed approach was implemented to select appropriate data visualization formats to present information commonly used in public web-based COVID-19 dashboards. Forty-seven individuals completed a two-round Web-Delphi process that was launched through a snowball approach. Most respondents were young and highly educated and expressed to prefer distinct visualisation formats for different types of indicators. The preferred visualization formats from the participants were used to build a redesigned version of the official DGS COVID-19 dashboard used in Portugal. This study provides insights into data visualization selection literature, as well as shows how a Delphi process can be implemented to assist the design of public health dashboards.

Quality of acute myocardial infarction care in England and Wales during the COVID-19 pandemic: linked nationwide cohort study

BACKGROUND AND OBJECTIVE

The impact of the COVID-19 pandemic on the quality of care for patients with acute myocardial infarction (AMI) is uncertain. We aimed to compare quality of AMI care in England and Wales during and before the COVID-19 pandemic using the 2020 European Society of Cardiology Association for Acute Cardiovascular Care quality indicators (QIs) for AMI.

METHODS

Cohort study of linked data from the AMI and the percutaneous coronary intervention registries in England and Wales between 1 January 2017 and 27 May 2020 (representing 236 743 patients from 186 hospitals). At the patient level, the likelihood of attainment for each QI compared with pre COVID-19 was calculated using logistic regression. The date of the first national lockdown in England and Wales (23 March 2020) was chosen for time series comparisons.

RESULTS

There were 10 749 admissions with AMI after 23 March 2020. Compared with before the lockdown, patients admitted with AMI during the first wave had similar age (mean 68.0 vs 69.0 years), with no major differences in baseline characteristics (history of diabetes (25% vs 26%), renal failure (6.4% vs 6.9%), heart failure (5.8% vs 6.4%) and previous myocardial infarction (22.9% vs 23.7%)), and less frequently had high Global Registry of Acute Coronary Events risk scores (43.6% vs 48.6%). There was an improvement in attainment for 10 (62.5%) of the 16 measured QIs including a composite QI (43.8% to 45.2%, OR 1.06, 95% CI 1.02 to 1.10) during, compared with before, the lockdown.

CONCLUSION

During the first wave of the COVID-19 pandemic in England and Wales, quality of care for AMI as measured against international standards did not worsen, but improved modestly.

The DynAIRx Project Protocol: Artificial Intelligence for dynamic prescribing optimisation and care integration in multimorbidity

Background

Structured Medication Reviews (SMRs) are intended to help deliver the NHS Long Term Plan for medicines optimisation in people living with multiple long-term conditions and polypharmacy. It is challenging to gather the information needed for these reviews due to poor integration of health records across providers and there is little guidance on how to identify those patients most urgently requiring review.

Objective

To extract information from scattered clinical records on how health and medications change over time, apply interpretable artificial intelligence (AI) approaches to predict risks of poor outcomes and overlay this information on care records to inform SMRs. We will pilot this approach in primary care prescribing audit and feedback systems, and co-design future medicines optimisation decision support systems.

Design

DynAIRx will target potentially problematic polypharmacy in three key multimorbidity groups, namely, people with (a) mental and physical health problems, (b) four or more long-term conditions taking ten or more drugs and (c) older age and frailty. Structured clinical data will be drawn from integrated care records (general practice, hospital, and social care) covering an ∼11m population supplemented with Natural Language Processing (NLP) of unstructured clinical text. AI systems will be trained to identify patterns of conditions, medications, tests, and clinical contacts preceding adverse events in order to identify individuals who might benefit most from an SMR.

Discussion

By implementing and evaluating an AI-augmented visualisation of care records in an existing prescribing audit and feedback system we will create a learning system for medicines optimisation, co-designed throughout with end-users and patients.

Semantic Snapping for Guided Multi-View Visualization Design

Visual information displays are typically composed of multiple visualizations that are used to facilitate an understanding of the underlying data. A common example are dashboards, which are frequently used in domains such as finance, process monitoring and business intelligence. However, users may not be aware of existing guidelines and lack expert design knowledge when composing such multi-view visualizations. In this paper, we present semantic snapping, an approach to help non-expert users design effective multi-view visualizations from sets of pre-existing views. When a particular view is placed on a canvas, it is "aligned" with the remaining views-not with respect to its geometric layout, but based on aspects of the visual encoding itself, such as how data dimensions are mapped to channels. Our method uses an on-the-fly procedure to detect and suggest resolutions for conflicting, misleading, or ambiguous designs, as well as to provide suggestions for alternative presentations. With this approach, users can be guided to avoid common pitfalls encountered when composing visualizations. Our provided examples and case studies demonstrate the usefulness and validity of our approach.

Analysis of a Web-Based Dashboard to Support the Use of National Audit Data in Quality Improvement: Realist Evaluation

BACKGROUND

Dashboards can support data-driven quality improvements in health care. They visualize data in ways intended to ease cognitive load and support data comprehension, but how they are best integrated into working practices needs further investigation.

OBJECTIVE

This paper reports the findings of a realist evaluation of a web-based quality dashboard (QualDash) developed to support the use of national audit data in quality improvement.

METHODS

QualDash was co-designed with data users and installed in 8 clinical services (3 pediatric intensive care units and 5 cardiology services) across 5 health care organizations (sites A-E) in England between July and December 2019. Champions were identified to support adoption. Data to evaluate QualDash were collected between July 2019 and August 2021 and consisted of 148.5 hours of observations including hospital wards and clinical governance meetings, log files that captured the extent of use of QualDash over 12 months, and a questionnaire designed to assess the dashboard's perceived usefulness and ease of use. Guided by the principles of realist evaluation, data were analyzed to understand how, why, and in what circumstances QualDash supported the use of national audit data in quality improvement.

RESULTS

The observations revealed that variation across sites in the amount and type of resources available to support data use, alongside staff interactions with QualDash, shaped its use and impact. Sites resourced with skilled audit support staff and established reporting systems (sites A and C) continued to use existing processes to report data. A number of constraints influenced use of QualDash in these sites including that some dashboard metrics were not configured in line with user expectations and staff were not fully aware how QualDash could be used to facilitate their work. In less well-resourced services, QualDash automated parts of their reporting process, streamlining the work of audit support staff (site B), and, in some cases, highlighted issues with data completeness that the service worked to address (site E). Questionnaire responses received from 23 participants indicated that QualDash was perceived as useful and easy to use despite its variable use in practice.

CONCLUSIONS

Web-based dashboards have the potential to support data-driven improvement, providing access to visualizations that can help users address key questions about care quality. Findings from this study point to ways in which dashboard design might be improved to optimize use and impact in different contexts; this includes using data meaningful to stakeholders in the co-design process and actively engaging staff knowledgeable about current data use and routines in the scrutiny of the dashboard metrics and functions. In addition, consideration should be given to the processes of data collection and upload that underpin the quality of the data visualized and consequently its potential to stimulate quality improvement.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.1136/bmjopen-2019-033208.

Requirements for a Dashboard to Support Quality Improvement Teams in Pain Management

Pain management is often considered lower priority than many other aspects of health management in hospitals. However, there is potential for Quality Improvement (QI) teams to improve pain management by visualising and exploring pain data sets. Although dashboards are already used by QI teams in hospitals, there is limited evidence of teams accessing visualisations to support their decision making. This study aims to identify the needs of the QI team in a UK Critical Care Unit (CCU) and develop dashboards that visualise longitudinal data on the efficacy of patient pain management to assist the team in making informed decisions to improve pain management within the CCU. This research is based on an analysis of transcripts of interviews with healthcare professionals with a variety of roles in the CCU and their evaluation of probes. We identified two key uses of pain data: direct patient care (focusing on individual patient data) and QI (aggregating data across the CCU and over time); in this paper, we focus on the QI role. We have identified how CCU staff currently interpret information and determine what supplementary information can better inform their decision making and support sensemaking. From these, a set of data visualisations has been proposed, for integration with the hospital electronic health record. These visualisations are being iteratively refined in collaboration with CCU staff and technical staff responsible for maintaining the electronic health record. The paper presents user requirements for QI in pain management and a set of visualisations, including the design rationale behind the various methods proposed for visualising and exploring pain data using dashboards.