Breaking Barriers: How Our AI Drives Diversity in Clinical Trials

Breaking Barriers: How Our AI Drives Diversity in Clinical Trials

Clinical research is key to developing new medical treatments. And clinical trial participants should reflect the demographics of the patients who receive those therapies. However, while many diseases disproportionately impact ethnic minorities, these minority groups are often underrepresented in clinical research.

There are a variety of reasons for this underrepresentation. Principal investigators (PIs) often limit their search for study participants to their own patients. Implicit bias can result in minorities not being presented with the option to join active studies. And other factors come into play as well such as language and cultural barriers, lack of resources in underserved neighborhoods and less outreach to people in specific communities.

This is where our software is invaluable and helps to overcome such barriers in clinical trials. Using AI methods like natural language processing (NLP) and machine learning, we can reduce biases and reach new communities to precision-match patients for trials. These methods can help increase diversity, equity and inclusion while providing access to life saving treatments.

Patient Populations and Representation in Research

There is a level of distrust in the U.S. minority groups stemming from historic medical mistreatment (e.g., the Tuskegee Experiment). This mistreatment, and the resulting lack of diversity in research, has impacted people of different races, ethnicities, socioeconomic statuses and more. 

Today, clinical research and patient representation still does not reflect our diverse population. This lack of representation in research has led to an incomplete understanding of how different diseases impact different people, and how effectively the treatments work. 

However, there are promising federal efforts to combat this issue. In fact, a bill enacted by the FDA in 2023 now requires diversity action plans for clinical trials to reach a broad study population. 

AI Technology Helps Make Research More Inclusive

Our technology allows us to reach new populations who previously didn’t have easy access to clinical trials. We’re also helping to counteract the biases that have led to today’s gaps in trial participant diversity. For instance, our AI can perform functions — such as patient recruitment — that were previously done manually, decreasing the biases of inequitable practices.

Our company connects all research stakeholders in a powerful, real-time ecosystem. The software uses NLP to search through both the structured and unstructured EMR data to precision-match patients and sites, thereby accelerating and improving the recruitment process. Without it, researchers manually sort through unstructured data, like physicians’ notes, often from multiple systems. 

On our platform users easily edit the protocol exclusion and inclusion criteria and get real-time feasibility counts. This allows users to ensure criteria are necessary based on which patient populations are eliminated with each one. Otherwise, some criteria may inadvertently exclude groups of people and impact the study results. After the trial’s criteria are added, a list of potential participants is generated, leaving the researcher only to validate these matches before reaching out to the patients. 

Doctors often tell their patients about a trial when they come in for an appointment, or PIs rely on referrals to reach patients they don’t treat. Our platform is implemented on a health system’s entire EMR. When a search is conducted, the list of potential matching patients spans the entire hospitals and doctors’ offices in the health system, including those who receive treatment in smaller clinics.

The sponsors in our ecosystem use our platform to precision-match patients and find the best sites to run their trials. One of the biggest causes of a failed trial is a site’s inability to meet its recruitment goals. Using our software, more sites and sponsors can better understand the patients required for a study and meet their goals with a diverse patient population.

Our software opens up new opportunities: patients in smaller hospitals can be approached for studies more often. Often, patients with critical conditions that require novel treatments look for trials on their own. However, because clinical trial criteria are complex, these patients often do not match the studies they try to join.  

When physicians have better tools, they can have confidence in bringing the best new treatments to their patients. As technology continues to evolve, we hope to keep playing a part in the efforts toward more inclusive and equitable treatment options. 

Interested in learning more about how our software can improve patient diversity in clinical trials? Reach out to us here.

Author

Nour Malki, Communications and Content Specialist

nour@deep6.ai

About The Author

Nour Malki