Health Equity Solutions: Leveraging Data to Improve Diverse Patient Recruitment

AI is increasingly taking hold across healthcare. A recent Bain & Co. survey found the number of health systems with a robust AI strategy in place has tripled in the last year, while more than 70% are optimistic about generative AI’s potential to improve their organization.  ‍

Current and potential use cases for AI abound. Health systems are automating administrative processes, augmenting clinical decision-making, and supporting virtual care. Organizations are also exploring AI’s role in providing health equity solutions that increase access to care and eliminate bias in treatment decisions—such as during pain management. 

One AI use case that’s often overlooked is the ability to predict clinical trial engagement. Sponsors that can determine the likelihood of an individual to enroll in a trial are positioned to recruit more  representative participants in less time. Furthermore, their trials are more likely to reach an endpoint more aligned with health equity—retaining the right patients to help ensure a trial measures outcomes in historically underserved populations. 

Using data to make patient recruitment more diverse is a three-step process. Sponsors need to look for patterns in data with tools such as e-DICT, use the data to inform their recruitment strategies, and pair data-driven recruitment strategies with engaging communities through platforms like NOWINCLUDED.

Step 1

Measuring health equity by looking at patterns in data

Trial sponsors increasingly emphasize recruitment strategies that increase diversity. Not only does a lack of diversity in clinical trials lead to skewed data, cost sponsors money, and delay time to market; it also further perpetuates the inequalities that persist in the U.S. healthcare system at large. 

Effective strategies for increasing diversity within this context include health equity solutions capable of analyzing vast datasets and identifying patterns related to patient demographics, preferences, and barriers to participation. As the California Health Care Foundation points out, AI provides a deep dive into data—especially unstructured data such as electronic health records—to surface insights that may otherwise go unnoticed. Algorithms can flag individuals based on their medical history or risk factors related to race, gender, or ethnicity—and determine whether they’re good candidates for a treatment option in a trial.  

Using clinical research software driven by AI, sponsors can go a step further and explore factors that may impact an individual’s willingness or ability to participate. Someone may live in a ZIP code that’s far from the trial site and lacks public transit. Or the data may show a community has limited access to broadband Internet, which would make remote monitoring difficult. A platform such as e-DICT adds value by aggregating data on engagement with clinical and community content, further indicating the likelihood of an individual’s participation.

Step 2

Using data and digital health for equity in recruitment strategies

Once a trial sponsor gains these insights into individuals and populations, it’s important to apply them to recruitment strategies. This will help sponsors dedicate resources appropriately and ensure benchmarks are met, especially those related to enrolling individuals from communities of color. 

AI supports clinical trial recruitment in multiple ways. Health equity solutions such as e-DICT pair data analysis related to individual and community engagement efforts with qualitative information from sponsor sites. This helps organizations determine which outreach efforts are succeeding and warrant expansion, as well as which content is missing the mark and should be reconsidered. 

Additionally, some algorithms can support measuring health equity by prescreening potential participants prior to enrollment. This analysis helps align participants with a study’s inclusion criteria—no small task given the many exclusions increasingly common in trials for highly targeted therapeutics. Algorithms can also flag individuals who meet inclusion criteria but may face barriers to participating in a trial. This can help sponsors anticipate and address challenges in the early stages of trial design—before participants begin to drop out due to predictable circumstances. 

Step 3

Promoting health equity solutions by pairing analysis with community

Increasing diversity in clinical trials requires more than just the latest in digital health. Equity advances when sponsors can truly engage with communities of color. As a recent commentary in MedCity News noted, engagement supported by AI can lead to more equitable access, improve clinical outcomes, and lower overall healthcare costs. 

Where e-DICT enables targeted, representative clinical research by indicating which communities are more likely to participate, Acclinate’s NOWINCLUDED offers access through digital and in-person engagement facilitated by relationships with organizations that communities of color know and trust. This combination of omnichannel outreach and robust analytics gives sponsors access to communities of color paired with insight into who’s willing to remain engaged because evidence shows they’re the right fit for the trial.

Leverage advanced digital health equity solutions for your trial

Acclinate has been laser-focused on increasing diversity in patient recruitment since e-DICT was launched five years ago. Today we continue to explore the role of data and AI in measuring health equity and improving engagement with communities of color. See why more and more clinical research teams are leveraging Acclinate for better health equity data. Schedule a 1:1 meeting with our team.