Svoboda | Graniru | BBC Russia | Golosameriki | Facebook
'),o.close()}("https://assets.zendesk.com/embeddable_framework/main.js","jmir.zendesk.com");/*]]>*/

Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Currently submitted to: Online Journal of Public Health Informatics

Date Submitted: Mar 11, 2024
Open Peer Review Period: Mar 20, 2024 - May 15, 2024
(currently open for review)

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

Rank Ordered Design Attributes for Healthcare Dashboards including Artificial Intelligence (AI): Usability Study

  • Melina Malkani; 
  • Eesha Madan; 
  • Arav Madan; 
  • Neel Singh; 
  • Dillon Malkani; 
  • Tara Bamji

ABSTRACT

Background:

A healthcare dashboard is a visual representation of vital healthcare data designed to emphasize key information for individuals and organizations, aiding them to make informed decisions. [5] These dashboards are increasingly utilized worldwide to track and report emerging and widespread diseases, trends, and other information to allow the public to make better healthcare decisions. [6, 7] Some examples include the Johns Hopkins COVID-19 dashboard, the Centers for Disease Control and Prevention FluView Interactive dashboard, the World Health Organization Monkeypox dashboard, and the State of Pennsylvania’s Cancer Statistics dashboard.

Objective:

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

Methods:

The authors evaluated 250 US government and commercial healthcare dashboards and conducted a survey of healthcare dashboards with 218 individuals identifying the best practices to consider when creating a public healthcare dashboard. The dates of the survey and data collection were from June 2023 to August 2023. These features ranked in descending order of importance are (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 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 (AI), (14) adjustable thresholds, and (15) charts with tabulated data. The prior study on COVID dashboards with 118 participants showed similar results.[3] Both studies validated top attributes of healthcare dashboards as easy navigation, simplicity of design, high usability, use of clear descriptions, and use of diverse chart types. 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 with further evidentiary support.

Results:

The authors conducted a survey of 218 (n=218) individuals above the age of 18. The survey consisted of 15 questions. Responses of “yes” counted as one point, while responses of “no” counted as 0 points. The authors calculated a total of 3,259 responses - 2,945 responses of “yes” and 314 responses of “no”. The Use of Charts with Tabulated Data had the lowest percent agreement of “yes” responses of 83%, whereas Easy Navigation had the highest percent agreement of “yes” responses of 96%, and the use of Predictive Analytics using Artificial Intelligence had “yes” responses of 87%, ranking at the 13th most popular attribute.

Conclusions:

As technology evolves, the availability of resources and data has become increasingly easier and better. With a click or a quick search, consumers have access to an abundance of healthcare data and data dashboards which aid in making informed healthcare decisions. However, healthcare dashboards may not be of the highest quality or as easily understood. Through our observational review and multiple surveys, we evaluated the effectiveness of healthcare dashboards in the United States to better understand and improve their design elements. From our analysis, we were able to develop and confirm the top 15 best practices of healthcare dashboard design from the ease of navigation to the use of predictive analytics. These 15 top best practices were assessed as the most important aspects of a healthcare dashboard’s effectiveness. The studies validated and concluded that the top five attributes of healthcare dashboards, such as easy navigation, simplicity of design, high usability, use of clear descriptions, and use of diverse chart types. As identified and analyzed, the best practices can be incorporated in order to design and disseminate effective healthcare dashboards making valuable healthcare information available to the public. Ultimately, the availability of better healthcare dashboards will help consumers make better and more informed healthcare decisions resulting in better healthcare outcomes.


 Citation

Please cite as:

Malkani M, Madan E, Madan A, Singh N, Malkani D, Bamji T

Rank Ordered Design Attributes for Healthcare Dashboards including Artificial Intelligence (AI): Usability Study

JMIR Preprints. 11/03/2024:58277

DOI: 10.2196/preprints.58277

URL: https://preprints.jmir.org/ojs/index.php/preprints/preprint/58277

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.

Advertisement