Enabling Efficient Clinical Trial Operations with Artificial Intelligence

Blog written in collaboration with Saama

Artificial intelligence (AI), in brief terms, is an intelligent computer program that can receive inputs from humans, interpret and learn from such inputs, and exhibit actions in pursuit of a particular goal. AI uses the machine simulation of human intelligence processes, such as learning, reasoning, and self-correction, to mimic human decision-making. In the world of clinical trial operations, AI is used to recognize and interpret patterns in large datasets so clinical researchers can work faster, more accurately, and more efficiently.

AI encompasses a variety of techniques that accelerate clinical research processes. Machine learning (ML), for example, trains algorithms on existing clinical data so they can help researchers instantly spot anomalies, resolve queries, and turn raw data into submission-ready formats.  

Though AI is one of the most talked about topics in clinical research today, many life science companies are hesitant to take the plunge. “Everyone wants progress, but nobody wants change,” said Malaikannan (Malai) Sankarasubbu, VP of AI Research at Saama, during a panel discussion called “Are We Ready for Artificial Intelligence in Clinical Trial Operations?” The session was hosted by Halloran Consulting Group at CORE West on June 2nd, 2022 and also featured Aamir Jaka, Saama’s VP of Life Science Strategy and Customer Success, and Scott Chetham, CEO of Faro Health.

Instead of wondering if your clinical research program is ready for AI, you’ll realize that the time to embrace it is now.

During the session, some attendees said they were worried that AI would somehow take over clinical research. Malai assured the crowd that “AI is meant to assist clinical professionals – not replace them.”

In this blog post, we’ll share our perspective on how AI enables more efficient clinical trial design and operations under human supervision. You’ll learn about successful use cases and discover how to adopt a technology mindset for accelerating clinical research without sacrificing quality. Instead of wondering if your clinical research program is ready for AI, you’ll realize that the time to embrace it is now.

AI Use Cases for Clinical Research Professionals

With costs and clinical trial failure rates high, AI is becoming a valuable tool for drug developers of all sizes, from large pharma companies to emerging biotechs.

Some of the most important benefits of AI for clinical research, as outlined by Malai and Aamir during the presentation, include a variety of clinical operations task automation, including:

• Site optimization
• Query generation
• Data mapping

Let’s take site optimization as an example. During the CORE West session, Malai shared how one sponsor learned the hard way that distant parking lots were deterring patients from keeping their appointments. By instantly scanning maps of various site locations, AI can recommend sites that reduce the risk of dropout due to a lack of convenience.

Saama is best known for helping Pfizer embrace AI during the development of its breakthrough COVID-19 vaccine. After a competitive hackathon prior to the pandemic, Saama was invited by Pfizer to develop and deploy an AI-powered analytical tool geared toward clearing many of the obstacles faced by study managers and monitors. The AI solution, known today as Smart Data Query (SDQ), was used to deliver higher quality work in less time during the company’s COVID-19 vaccine development.

During the trial, Pfizer provided the clinical data to train Saama’s AI models. In turn, SDQ automated the processes of identifying data discrepancies and generating and resolving queries. With a human always in the loop for review, the application’s recommendations could be approved or rejected, as needed. This type of feedback makes AI even smarter over time, improving predictions and requiring less human intervention.

After all was said and done, SDQ helped ensure data quality throughout the trial and cut the data cleaning time down from 30+ days to just 22 hours.

Navigating AI Hesitation

Despite rapid advances in AI technologies and use cases for clinical drug development, AI adoption and implementation continue to be met with feelings of doubt and uncertainty. Here are four common reasons why life sciences companies aren’t pulling the AI trigger.

Regulatory Complexity

The Food and Drug Administration (FDA) considers AI/ML-based software to be a medical device. This means that AI innovators must comply with a host of additional clinical, analytical, technical validation, quality, safety, and efficacy requirements.

Personnel Capabilities

Pharma companies are concerned about hiring people with the right data science and technological skills to manage trials in an AI-enabled environment, and existing employees may be afraid of being replaced by AI. AI-native applications from Saama, like SDQ, are assistive in nature and don’t require any special skills beyond clinical research expertise. In fact, it’s this combination of technology and human experience that maximizes AI’s value.

Data Accessibility

How much data is required to enable AI technology to truly assist clinical professionals as part of a layered decision-making process? The AI Research Team at Saama is constantly learning how to train AI models on less data so companies can start using the technology as soon as possible. Saama is also adept at integrating data from various current and historical sources, so AI models have the right inputs to detect critical patterns and anomalies.

Big Operational Shift

While the science side of drug development has embraced innovation, the adoption of new technologies has been met with a great deal of resistance. All change requires commitment, and once clinical researchers grasp the value of AI to accelerate their work and improve its quality, they usually become champions of change.

How to Get Ready for AI in Your Clinical Trials

As we think about our outlook for AI in clinical research, these three tenets are at the center of our vision for effective adoption:

• Patient-centric design
• Reduction in clinical trial timelines
• Efficient clinical operations and quality data

As sponsor companies become open to AI technology, it’s important to identify change agents who will ensure widespread adoption. With any new change, best practices and a plan for success must be deployed to create quick wins, foster positive user experiences, maximize AI possibilities, and create a cultural acceptance of technology to better serve patients.

Contact us to learn more about Halloran Consulting Group and how we assist companies like yours from early drug development to commercialization.

About CORE West

CORE East, the Clinical Operations Retreat for Executives, was launched in 2004 by the Halloran Consulting Group and is an invitation-only meeting that brings together an exclusive group of senior leaders in clinical development to discuss and debate the most pressing issues around the business of product development and building enduring companies in this space. Following the success of CORE East, CORE West was launched in 2021 with the same mission.

About Saama Technologies, Inc.
Saama enables the life sciences industry to conduct faster and safer clinical development and regulatory programs. Saama’s Life Science Analytics Cloud (LSAC) is currently being used by more than 65 biotech companies, including many of the top 20 pharmaceutical companies.

Saama’s Life Science Analytics Cloud (LSAC) is a single, unified data aggregation and analytics platform that helps drug development teams—including clinical operations, medical review, data management, biostatistics, pharmacovigilance, and translational research—make faster, better decisions.