Revolutionizing clinical trials: A streamlined, smarter, and more rational future

Revolutionizing clinical trials: A streamlined, smarter, and more rational future Rachel Marley

Quick Takes

• Moving towards virtual and remote clinical trials could enable patients and healthcare providers to more easily engage in research
• Leveraging data and digital tools more effectively could help to reduce bias while accounting for local markets, policy, privacy, and cultural needs
• Savvy healthcare executives are incorporating clinical trials as a strategy to reduce cost, improve the patient experience, and enhance real-world data

Clinical trials, the cornerstone of medical advancements, are on the brink of a transformative era that promises to reshape research as we know it.

The future of clinical trials can be characterized by global expansion, streamlined processes, smarter study design, rational patient engagement, AI integration, and strategic utility for healthcare executives. This vision promises a healthcare landscape that is more efficient, equitable, and patient-focused. Bias is reduced with a more global approach, which further enhances the quality of decisions and care in this changing landscape.

In a recent interview, industry visionary Craig Lipset delved into the evolving landscape of clinical research, unveiling a spectrum of innovations that are set to revolutionize the field.

The impact of digital transformation in clinical trials

HT: The healthcare industry is going through a major digital transformation. In your opinion, why do we need to change our approach to clinical trials?

Craig Lipset: Clinical trials demand an even greater level of digital transformation than what we’re currently witnessing in healthcare. The momentum in clinical trial advancements and drug development has been at a standstill for several years while research protocols have grown increasingly complex and burdensome.

The encouraging news is that we have the very solutions we need at our fingertips. The potential of harnessing data and optimizing digital tools invites us to explore smarter and more innovative ways of working.  Whether it’s upfront and how we can improve the selection of molecules to introduce into clinical research portfolios, or how we can use data to transform the way we design, plan, and execute those trials.

When we see these types of transformations in healthcare, it creates an expectation among patients and providers that these types of digital tools are already impacting clinical trials and drug development. Patients and providers look at clinical research as cutting-edge science being introduced into the healthcare system.

We can live up to these expectations by bringing those digital and data-driven innovations into the clinical research process to improve efficiency and make research participation more accessible.

The future of clinical trials

HT: What does the future of clinical trials look like?

Craig Lipset: The future of clinical trials looks simplified, intelligent, and rational. It is a space where there’s less friction between healthcare delivery and clinical research.

Currently, research participation is demanding and disruptive for physicians and patients alike. The burdens are evident, from time away from personal commitments to financial strain to the abrupt change in routine and systems.

Simplifying clinical trials provides a bridge between research and healthcare. Erasing hurdles and resistance will be very important as we move forward. This will result in enhanced accessibility for both patients and providers, addressing the current challenges they face.

The future of clinical trials exhibits increased intelligence. It leverages data and digital tools to intricately design studies from the outset. A shift from learning as we go to getting it right the first time leads to collaborations that streamline research efforts.

The master protocols employed during the pandemic showcase the efficiency of such cooperative studies, testing multiple interventions under a single, comprehensive framework.  Current norms involve individual studies testing single interventions in specific patient groups, much like setting up elaborate phone lines across the country just to make one phone call, and then breaking it all down at the end of it. A more sustainable approach employs lasting and shared infrastructure for smarter research.

The future of clinical trials thrives on efficiency. Digital measurements bolster study precision, providing profound insights into patient responses to interventions, while rational engagement with patients ensures randomized clinical trials only when necessary. Leveraging existing data and innovative simulations paves the way for more judicious study arms, making better use of resources and thoughtfully determining patient involvement.

Incorporating synthetic control arms into this rational approach, real-world data and emerging AI capabilities can be used to simulate patient progress without interventions. An example of this would be using a digital twin for potential enrollees in control arms while the real participant receives active therapy.

Such transformations promise a more coherent clinical research landscape, where patient inclusion is a strategic decision guided by astute data strategies, rather than simply increasing the number of trial participants for the sake of it. The future of clinical trials will be a blend of simplicity, intelligence, and rationality, fostering efficiency, accessibility, and precision in research participation and outcomes.

The importance of real-world data in digital transformation

HT: One of the major challenges surrounding clinical trials is global access. How will changing our approach to these trials help us overcome the challenge and allow us to gain more real-world data from larger and more varied patient groups?

Craig Lipset: Meeting the needs of all patients requires a global perspective for clinical research studies. The goal extends beyond patient recruitment. It encompasses fostering diversity and representation among participants while generating consistently high-quality evidence across different national populations.

Global development programs play a pivotal role. The data and evidence they generate serve a dual purpose: supporting the global registration of medicines and ensuring their availability on an international scale.

We talk a lot about clinical trial data and real-world data. Real-world data, in essence, encompasses all data pertaining to a patient’s health state, excluding data sourced from clinical trials. A clinical trial is seen as an artificial construct that is created for the purpose of generating evidence.

Gaining valuable insights within patient-generated real-world data is central to comprehending the trajectory of patients’ health, tracking their progress under specific interventions, and refining the strategies of precision medicine.

Craig Lipset: The utility of real-world data hinges on the availability and accessibility of diverse interventions across the globe. A continuous spectrum of evidence comes into play, wherein global studies are carefully designed and executed to facilitate not only international medicine registration but also the cultivation of diverse patient experiences and real-world data.

In the ethical and compliant utilization of this data lies the potential to fully understand how different patient populations around the world may be responding when they’re receiving that new intervention in their local markets.

Variable policies, privacy regulations, and cultural norms that govern the use of real-world data are creating challenges. This disparity is evident when comparing regions like the United States and Europe. Europe operates under the General Data Protection Regulation (GDPR), while the US embraces a more lenient data accessibility approach.

The variance in data governance will likely escalate, not just between countries, but also within specific markets, such as the US where individual states might impose their own regulations. So, we need to make sure our strategies for accessing real-world data are thoughtful of local markets and encompass policy, privacy, and cultural expectations.

It is critical that these new strategies are agile, considerate, and adaptable to the nuanced fabric of each market.

Using AI effectively and without bias

HT: What potential role could Artificial Intelligence (AI) play in these trials, and how do we overcome the inherent bias that may be associated with the use of AI?

Craig Lipset: AI is already leaving its mark on clinical trials and drug development, with the potential for further impact on efficiency, accessibility, and study execution.

Prioritization – The ability to prioritize which medicines to include in our clinical trial portfolios. AI enables data-driven decisions to allocate limited resources most effectively, optimizing the selection of medicines for clinical trials.

Study design – AI is improving study design, feasibility, and planning, incorporating diverse data sources to leverage electronic health records, competitive intelligence, and investigator and patient insight. This data-driven approach makes study recommendations more actionable, enhancing the study development process.

Patient recruitment – AI, with patient consent, can expedite chart reviews and restrictive eligibility screenings, even with complex criteria or medical histories. This not only accelerates the process but also keeps patients up-to-date on their eligibility and enrollment status.

Automation, quality, and process improvement – AI supports automation throughout the clinical trial process, facilitating seamless data flow from one stage to the next. This end-to-end digitization enhances protocol design and ensures high-quality regulatory submissions.

Generative AI, such as secure versions of ChatGPT and Bard, is finding its place in digital clinical trials, offering speedy and high-quality solutions for tasks like drafting patient narratives and regulatory submissions. This approach reduces costs while improving overall efficiency and lowering costs in the process.

AI provides real-time quality control by using predictive intelligence and algorithms to detect potential issues early in the study. This not only enhances the quality of ongoing studies but also improves safety by allowing for timely interventions.

Cutting-edge AI applications are emerging, such as the creation of synthetic data and digital twins, which offer intriguing possibilities for research participation and control arms in future studies.

As AI continues to intersect with patient data, there is a need to mitigate bias. For example, AI may be employed to modernize endpoint measurement, but it must be trained on a comprehensive range of diverse patient data to ensure fair representation. An example case of this is skin analysis where cameras or machines and algorithms have to be trained on the full range of diverse skin tones.