ENHANCE

Improving biomedical data tools through
user-centered, human-AI-focused design

Improving biomedical data tools through user-centered, human-AI-focused design

ENHANCE fosters user-centered development of ARPA‑H’s toolset

Performers working with the Advanced Research Projects Agency for Health (ARPA‑H) are developing the Biomedical Data Fabric (BDF) Toolbox to consolidate biomedical data from a variety of health disciplines and resolve inconsistencies in how research data is currently stored and shared. The BDF Toolbox promises to make data readily available to researchers seeking to advance the development of next-generation treatments and cures.
A collection of tools is of little value unless all users can access it seamlessly in workflows. This is especially true in the rapidly evolving biomedical research sector with its vast array of new data and groundbreaking technologies. Charles River Analytics is working with ARPA‑H, an agency within the US Department of Health and Human Services (HHS), to make it easier to connect biomedical research data from thousands of sources and overcome barriers caused by incompatible data dialects to deliver better health outcomes.The toolset also needs to facilitate access to all authorized users, including clinicians and patients, and therefore needs to accommodate multiple levels of biomedical literacy. Charles River Analytics is helping with this aspect of the project.

“We’re conducting user-centered testing to strengthen the BDF Toolbox, recruiting representative user types across multiple biomedical and technical literacy levels. Ultimately, the goal for ENHANCE is to make sure that the tools being created as part of the BDF program are actually the tools that need to be created and have all the necessary functionality for the user.” 

Dr. Nicolette McGeorge
Senior Scientist and Principal Investigator on ENHANCE

The first aspect of ENHANCE involves identifying the users and understanding their workflows and relevant sub use cases. Once the team members identify the users and their workflows, they can evaluate elements of the planned toolbox using principles of human factors engineering and cognitive systems engineering.

The team will be assessing the tools with principles of good usability practice with the goal of supporting an iterative design and refinement process so the toolbox elements can be improved early on. By evaluating the different complex elements, they aim to ensure positive outcomes for patients.

The BDF Toolbox will also incorporate artificial intelligence (AI) into its framework, which means the ENHANCE team’s evaluation of the tool structure will also assess the effectiveness of human‑AI teaming elements. A key challenge when incorporating AI is understanding its limitations. Tools must be designed so that humans can recognize when AI has reached the bounds of it’s capabilities, just one facet of creating effective human-AI teams. ENHANCE will also support software verification and validation to ensure the BDF Toolbox tools follow robust software engineering practices.

ENHANCE’s cognitive systems engineering (CSE) approach includes facilitating early and regular access to a User Advocacy Committee (UAC), along with conducting targeted formative and validation studies with diverse representative user populations to ensure BDF Toolbox technologies address broadly ranging user needs, constraints, and biomedical literacy levels.
ENHANCE’s cognitive systems engineering (CSE) approach includes facilitating early and regular access to a User Advocacy Committee (UAC), along with conducting targeted formative and validation studies with various user populations to ensure BDF Toolbox technologies address broadly ranging user needs, constraints, and biomedical literacy levels.

McGeorge is excited that ARPA‑H has valued a user-centered focus, and it’s why ENHANCE is such a value-add to the BDF Toolbox project. “We’re calling the project ENHANCE because it goes beyond the basic usability evaluation with enhanced approaches to iterative design and evaluation of tools at the intersection of humans and AI in complex environments,” she explains. It’s not just about having buttons in the right places, McGeorge cautions. “Users need clear, relevant information exactly when they need it, presented in a way that makes it easy to understand and helps them make decisions effectively. That context is critical,” McGeorge says.

Contact us to learn more about our other capabilities in user interfaces and human-machine teaming, and health and medical tools.

This research was funded in part by the U.S. government. The views and conclusions contained in this document are those of the author(s) and should not be interpreted as representing the official policies, either expressed or implied, of the U.S. government.

Our passion for science and engineering drives us to find impactful, actionable solutions.