The modern medical system does not serve all its patients equally—not even nearly so.

Significant disparities in health outcomes have been recognized and persisted for decades. The causes are complex, and solutions will involve political, social and educational changes, but some factors can be addressed immediately by applying artificial intelligence to ensure diversity in clinical trials. A lack of diversity in clinical trial patients has contributed to gaps in our understanding of diseases, preventive factors and treatment effectiveness.

Diversity factors include gender, age group, race, ethnicity, genetic profile, disability, socioeconomic background and lifestyle conditions.

As the Action Plan of the FDA Safety and Innovation Act succinctly states, “Medical products are safer and more effective for everyone when clinical research includes diverse populations.”

But certain demographic groups are underrepresented in clinical trials due to financial barriers, lack of awareness, and lack of access to trial sites. Beyond these factors, trust, transparency and consent are ongoing challenges when recruiting trial participants from disadvantaged or minority groups.

There are also ethical, sociological and economic consequences to this disparity. An August 2022 report by the National Academies of Sciences, Engineering, and Medicine projected that hundreds of billions of dollars will be lost over the next 25 years due to reduced life expectancy, shortened disability-free lives, and fewer years working among populations that are underrepresented in clinical trials.

In the US, diversity in trials is a legal imperative. The FDA office of Minority Health and Health Equity provides extensive guidelines and resources for trials and recently released guidance to improve participation from underrepresented populations.

From moral, scientific, and financial perspectives, designing more diverse and inclusive clinical trials is an increasingly prominent goal for the life science industry. A data-driven approach, aided by machine learning and artificial intelligence (AI), can aid these efforts.

The opportunity

Life science companies have been required by FDA regulations to present the effectiveness of new drugs by demographic characteristics such as age group, gender, race and ethnicity. In the coming decades, the FDA will also increasingly focus on genetic and biological influences that affect disease and response to treatment.

As summarized in a 2013 FDA report, “Scientific advances in understanding the specific genetic variables underlying disease and response to treatment are increasingly becoming the focus of modern medical product development as we move toward the ultimate goal of tailoring treatments to the individual, or class of individuals, through personalized medicine.”

Beyond demographic and genetic data, there is a trove of other data to analyze, including electronic medical records (EMR) data, claims data, scientific literature and historical clinical trial data.

Using advanced analytics, machine learning and AI on the cloud, organizations now have powerful ways to:

• Form a large, complicated, diverse set of patient demographics, genetic profiles and other patient data
• Understand the underrepresented subgroups
• Build models that encompass diverse populations
• Close the diversity gap in the clinical trial recruitment process
• Ensure that data traceability and transparency align with FDA guidance and regulations

Initiating a clinical trial consists of four steps:

1. Understanding the nature of the disease
2. Gathering and analyzing the existing patient data
3. Creating a patient selection model
4. Recruiting participants

Addressing diversity disparity during steps two and three will help researchers better understand how drugs or biologics work, shorten clinical trial approval time, increase trial acceptability amongst patients and achieve medical product and business goals.

A Data-driven Framework for Diversity

Here are some examples to help us understand the diversity gaps. Hispanic/Latinx patients make up 18.5% of the population but only 1% of typical trial participants; African-American/Black patients make up 13.4% of the population but only 5% of typical trial participants. Between 2011 and 2020, 60% of vaccine trials did not include any patients over 65—even though 16% of the U.S. population is over 65. To fill diversity gaps like these, the key is to include the underrepresented populations in the clinical trial recruitment process.

For the steps leading up to recruitment, we can evaluate the full range of data sources listed above. Depending on the disease or condition, we can evaluate which diversity parameters are applicable and what data sources are relevant. From there, clinical trial design teams can define patient eligibility criteria, or expand trials to additional sites to ensure all populations are properly represented in the trial design and planning phase.

Artificial intelligence (AI)-enabled data collection and management can be a game changer for life sciences companies in the drug development process.

Once the stuff of science fiction, AI has made the leap to practical reality. Yet, to date, most life sciences companies have only scratched the surface of AI’s potential. One area that holds particular promise: is digital data flow automation for clinical trials. With the power of AI, companies can rapidly digitize clinical-trial processes so they can complete studies faster. That means life-saving medicines and treatments can get to patients more quickly—and life sciences companies could gain a competitive edge. 

 it often takes 10 to 12 years to bring a new drug to market. The clinical-trial phase averages five to seven years. This timeline is due to the traditional flow of data across the clinical-trial life cycle, which can be a complicated maze of manual effort, rework, and inefficiency. As one life sciences executive summed up, “We still use the same processes that we used over 50 years ago. It feels like it’s 1972, not 2022.”

Consider these key data-related limitations of the traditional clinical trials process:

• Fragmented data and disconnected systems: Inputs for trial artefacts are often scattered across dozens of designs and formats.
• Extensive manual effort: Artifact creation requires manual data transcription from documents and systems.
• Rework and repetition: Although trials typically reuse data components, the same work is often repeated across trials. In the words of one executive, “Databases are still being built from the ground up for most trials. We end up building the same database 400 times.”
• Challenges in enabling innovative trial models: Complexities and limitations related to integrating data from new sources can create challenges with virtual trial designs.

Life sciences companies can also face numerous patient-related challenges that can limit their ability to collect trial data in the first place:

• Patient recruitment and enrollment: The process of travelling to trial sites can be burdensome and time-consuming for trial participants, which can negatively affect enrollment.
• Patient monitoring, medical adherence, and retention: Frequent visits to trial sites may become invasive and unpleasant, leading participants to drop out of trials.
• Clinical-trial diversity: Companies often struggle to enrol diverse populations in clinical trials because trial sites may be inaccessible to underrepresented populations. Recent research identified access as one of the biggest barriers to enrolling diverse trial participants.

Collecting data—and making it flow

Thankfully, AI can help CIOs overcome these challenges. AI technologies can be used to create structured, standardized, and digital data elements from a range of inputs and sources. For example, CIOs can implement new AI-powered tools to automate data management across the trial lifecycle. These tools intelligently interpret data elements, feed downstream systems, and auto-populate required reports and analyses. These tools can leverage existing systems to seamlessly integrate the data flow—providing a single, collaborative touch point for all interactions during a clinical trial. They can even use AI to generate insights from past and current trials to inform and improve future trials. Additional AI opportunities and use cases include:

• AI-enabled study design could help optimize and accelerate the creation of patient-centric designs. This could help to reduce patient burden, decrease the number of amendments, increase the likelihood of success, and improve overall efficiencies.
• AI is driving more innovative ways of collecting clinical-trial data and reducing reliance on in-person trial sites. For example, by capturing data from body sensors and wearable devices such as bracelets, heart monitors, patches, and sensor-enabled clothing, researchers can monitor a patient’s vital signs and other information remotely and less invasively. AI algorithms, in combination with wearable technology, can reveal real-time insights into study execution and patient adherence.
• Coupling AI with robotic process automation can harmonize and link data across different data collection modalities.
• Machine learning applied to clinical data could help illuminate complex relationships between different data domains—and enable automated data management.
• Auto-generating content (using natural language generation) for trial artefact creation can streamline and accelerate the regulatory document-authoring process.

The AI Advantage

With AI, life sciences and healthcare organizations can likely gain significant benefits—both in collecting trial data and promoting digital data flow:

• Tapping more participants and more diverse populations: AI-powered wearable devices can lessen the need for participants to travel to a physical site, which can enable organizations to recruit patients and diversify clinical trial participation.
• Boosting participant retention: Remote patient monitoring allows patients to participate in clinical trials with fewer potential hassles. AI algorithms can also be used to understand individual patient behaviours or needs, resulting in more patient-centric interactions and better retention.
• Producing faster trials at lower cost: Using AI, life sciences companies can reduce the cost and time required to process clinical-trial data through smart automation, improved efficiency, and less need for rework.
• Increasing reusable data: Organizations can use AI technologies to intelligently reuse existing data based on standards and metadata, reducing the need to start from scratch across trials.

With AI, life sciences organizations can shift from large teams working across dozens of data systems to a single AI-enabled, standards- and metadata-driven backbone that requires minimal user input. By reducing the time and effort required for clinical trials, AI-enabled data collection and management can accelerate the drug development process and help companies get new treatments to market more quickly. That puts the power in the CIO’s hands to get patients faster access to safe medicines that can change—and even save—their lives.

Clinical trial study redesign

Effective study design is essential for all clinical trials, as mistakes in this area could have a disastrous effect on costs, efficiency, and overall success. Through focused data analysis, AI software can sort through all of the relevant variables to determine the optimal country and site strategies, as well as the ideal enrollment model, patient recruitment approach, and initial plan.

By providing this level of guidance, AI technology lets healthcare organizations shorten their overall cycle time for protocol development, reduce design corrections, and improve overall efficiency throughout each study. Such improvements result in higher recruitment rates, as well as fewer non-enrolling sites and protocol amendments. In practice, these benefits are often the deciding factor in whether or not a given trial can attain accurate and reliable results.

Site identification, recruitment and enrollment

For many industry leaders, locating viable trial sites and identifying patients that match their inclusion and exclusion criteria remain monumental tasks. Particularly when studies begin targeting niche communities, patient recruitment tends to become all the more arduous, costly, and time-consuming.

Yet these bottlenecks are by no means inevitable. When using AI tools, organizations that perform on-site clinical trials consistently see better enrollment numbers. One of the many ways AI technology helps navigate this process is through the mapping of areas with a dense patient population. By using data analysis to identify the best avenues for patient recruitment, AI tools can overcome these obstacles even while helping healthcare organizations save on costs. Advanced data processing leads to more productive sites, accelerated recruiting, and a lower risk of under-enrollment. 

Pharmacovigilance

By harnessing the power of proactive analytics, AI tools can also help organizations process roughly 8,000 case life cycles per week, with no human intervention required. This extra layer of analysis enables significant improvements in patient safety.

AI also increases visibility in other ways. For example, data listening and optical character recognition allow conversations on various social networking platforms to be monitored, helping healthcare organizations assess subject, site, and study risks. Negative events are swiftly and automatically documented, while the simultaneous formatting of unstructured data allows for faster and more comprehensive safety reviews. These tools are capable of translating millions of words in several languages, ensuring that no potential data point is overlooked.

Patient monitoring

AI tools are now being designed to identify early signs of developing diseases – even before they cause any harm. This innovation is made possible through automated data capturing, the digitalization of standard clinical assessments, and the cross-sharing of data across various systems.

AI algorithms can even provide continuous patient monitoring through wearable technology. Real-time insights are generated from data collected by the wearable tech, allowing for predictive algorithms which are far more accurate than traditional evaluation methods.

Safety, efficiency, and speed

Organizations that invest wisely in AI technology can sidestep traditional industry obstacles, and turn their vast data assets into valuable clinical insights. With the right AI solutions in place, industry leaders will find it much easier to recruit participants, remove bottlenecks related to data processing, streamline slow manual processes, predict developing diseases, and provide faster risk assessments. Clearing away these roadblocks enables far more successful clinical trials, opening the door to faster innovation and a new generation of industry growth.

Each of these advancements is made possible by the power and versatility of AI. When used to its full potential, this revolutionary tool creates real value for healthcare organizations, putting them on solid footing for growth in a post-COVID world.