The newfangled medical system does not serve all patients equally – even approximately. Significant differences in health outcomes have been recognized and have persisted for decades. The causes are complicated and the solutions will include political, social and educational changes, but some factors can be addressed immediately by using artificial intelligence to ensure diversity in clinical trials.
The lack of diversity among patients participating in clinical trials has contributed to gaps in our knowledge of diseases, preventive factors and treatment effectiveness. Diversity factors include gender, age group, race, ethnicity, genetic profile, disability, socioeconomic background and living conditions. as FDA Safety and Innovation Act Action Plan succinctly states, “Medical products are safer and more effective for everyone when clinical trials include diverse populations.” However, some demographic groups are underrepresented in clinical trials due to financial barriers, lack of awareness and lack of access to research facilities. In addition to these factors, trust, transparency, and consent are ongoing challenges when recruiting research participants from disadvantaged or minority groups.
This disproportion also has ethical, sociological and economic consequences. Some August 2022 report by the National Academies of Sciences, Engineering, and Medicine projected that hundreds of billions of dollars would be lost over the next 25 years due to shortened life expectancy, fewer years of life free from disability, and fewer years of work in populations underrepresented in clinical trials.
In the US, process diversity is a legal imperative. FDA’s Office of Minority Health and Health Equity provides extensive guidelines and resources for rehearsals and recently published guidelines to escalate the participation of underrepresented populations.
From a moral, scientific and financial standpoint, designing more diverse and inclusive clinical trials is an increasingly crucial goal for the life sciences industry. A data-driven approach, powered by machine learning and artificial intelligence (AI), can aid these efforts.
Opportunity
FDA regulations require life sciences companies to report the effectiveness of novel drugs by demographic characteristics such as age group, gender, race and ethnicity. In the coming decades, the FDA will also increasingly focus on the genetic and biological influences that influence disease and response to treatment. As summarized in A 2013 FDA report“Scientific progress in understanding the specific genetic variables underlying disease and response to treatment is becoming an increasing focus in the development of newfangled medical products as we move closer to the ultimate goal of tailoring therapies to an individual or class of people through personalized medicine “.
In addition to demographic and genetic data, there is a wealth of other data to analyze, including electronic medical record (EMR) data, claims data, scientific literature, and data from historical clinical trials.
Using advanced analytics, machine learning and artificial intelligence in the cloud, organizations now have effective ways to:
- Create a vast, complicated, and diverse set of patient demographics, genetic profiles, and other data
- Understanding underrepresented subgroups
- Create models that include diverse populations
- Eliminate the diversity gap in the clinical trial recruitment process
- Ensure data traceability and transparency are consistent with FDA guidelines and regulations
Starting a clinical trial consists of four stages:
- Understanding the nature of the disease
- Collection and analysis of existing patient data
- Creating a patient selection model
- Recruitment of participants
Addressing diversity disparities in phases two and three will assist researchers better understand how drugs or biologics work, reduce clinical trial approval times, escalate patient acceptability of trials, and achieve medical product and business goals.
A data-driven diversity framework
Here are some examples to assist us understand diversity gaps. Hispanic/Latino patients make up 18.5% of the population, but only 1% of typical study participants; African American/Black patients represent 13.4% of the population but only 5% of typical study participants. In 2011-2020 60% of vaccine trials did not include any patients over the age of 65, even though 16% of the U.S. population is over 65. To fill these types of diversity gaps, the key is to include underrepresented populations in the clinical trial recruitment process.
In the stages leading up to recruitment, we may evaluate the full range of data sources listed above. Depending on the disease or condition, we can assess which diversity parameters apply and which data sources are relevant. From this, clinical trial design teams can define patient eligibility criteria or expand trials to additional sites to ensure that all populations are adequately represented during trial design and planning.
How IBM can assist
To effectively ensure diversity in clinical trials, IBM offers a variety of solutions, including data management, performing artificial intelligence and advanced analytics in the cloud, and setting up an ML Ops platform. It helps trial designers deliver and prepare data, combine different aspects of patient data, identify heterogeneity parameters, and eliminate bias in modeling. It does this through an AI-powered process that optimizes patient selection and recruitment by better defining clinical trial inclusion and exclusion criteria.
Because this process is traceable and fair, it ensures a stalwart selection process for recruiting study participants. When life sciences companies adopt such a framework, they can build trust that clinical trials are being conducted in diverse populations and therefore build confidence in their products. Such processes also assist healthcare professionals better understand and predict the possible impact that products may have on specific populations, rather than reacting ad hoc when it may already be too delayed to treat conditions.
summary
IBM solutions and consulting services can assist you leverage additional data sources and identify more appropriate diversity parameters, allowing you to re-examine and optimize trial inclusion and exclusion criteria. These solutions can also assist determine whether the patient selection process accurately reflects disease prevalence and improve clinical trial recruitment. With machine learning and artificial intelligence, these processes can be easily scaled across a range of samples and populations in a streamlined, automated workflow.
These solutions can assist life sciences companies build trust among communities that have been historically underrepresented in clinical trials and improve health outcomes.
Learn more about IBM Consulting Life Sciences solutions