Clinical Trial Modernization
Technological, Operational, and Regulatory Advances
Harry Yang, PhD, VP of Biometrics, Recursion Pharmaceuticals, USA
As the pharmaceutical industry navigates this new era of technological innovation, the integration of AI, big data, and advanced analytics into clinical trials holds immense potential to transform drug development. Clinical Trial Modernization: Technological, Operational, and Regulatory Advances provides a comprehensive overview of the current trends, challenges, and opportunities in modernizing clinical trials, offering a roadmap for stakeholders in this evolving field.
This book serves as a valuable resource for professionals, researchers, and regulators, providing actionable insights into the future of clinical trials and their critical role in bringing new therapies to market faster and more effectively.
1. Your book outlines a clear need to modernize clinical trials. What, in your view, are the most urgent drivers behind this transformation - technological limitations, regulatory shifts, or operational inefficiencies?
Yang: The transformation of clinical trials is driven by a convergence of operational inefficiencies, technological constraints, and evolving regulatory expectations. Among these, operational inefficiencies are the most urgent catalyst. Traditional trials are often slow, expensive, and difficult to execute, with persistent challenges in patient recruitment, data collection, and site coordination. These inefficiencies delay the delivery of effective therapies to patients and stifle innovation, underscoring the critical need for streamlined, data-driven, and patient-centric approaches.
2. “Modernization” is a term often used loosely. How do you specifically define clinical trial modernization in the context of your book? How does this differ from traditional improvements in trial design or management?
Yang: In our book, clinical trial modernization is a fundamental shift—not just optimizing legacy processes, but reimagining trials through systems thinking, digital innovation, and patient-centered design. It integrates real-world data, AI-driven analytics, decentralized models, adaptive designs, and automation to enhance relevance, inclusivity, and speed. Unlike traditional improvements that focus on incremental efficiency gains, modernization addresses structural and philosophical limitations, enabling trials to better reflect real-world practice and patient needs. It's about doing fundamentally better things, not just doing things better.
3. You highlight AI as a major force in clinical trial innovation. Can you elaborate on how AI is being used today beyond patient recruitment and what its most promising applications are in trial execution and data interpretation?
Yang: AI is transforming clinical trials beyond recruitment, with its most promising impact on execution and data interpretation. It optimizes protocol design, predicts feasibility, and enables dynamic site selection and risk monitoring. In decentralized trials, AI automates data capture through wearables and NLP. For data interpretation, AI uncovers patterns in complex datasets, supports early safety signal detection, and enables personalized insights. Large language models also aid in medical coding and documentation, accelerating decisions and making trials more adaptive, efficient, and patient-centric.
4. While big data offers new opportunities, it also poses challenges in harmonization and analysis. What strategies or frameworks do you recommend to ensure high-quality, actionable insights from diverse data sources in clinical trials?
Yang: Big data’s value in clinical trials lies in our ability to harmonize, curate, and interpret diverse sources effectively. Key strategies include adopting common data models such as OMOP or CDISC, establishing robust data governance, and leveraging AI tools for harmonization. Cross-functional collaboration ensures alignment with scientific and regulatory goals, while focusing on contextually relevant data enhances insight generation. The aim isn’t just more data—it’s building a purpose-driven ecosystem to enable timely, rigorous, and patient-centered decisions.
5. Which operational advancements - such as decentralized trials, adaptive designs, or remote monitoring - have had the greatest impact in the past five years, and how do you expect their roles to evolve in the near future?
Yang: Decentralized trials have been the most transformative over the past five years, expanding access, improving retention, and enabling real-time, home-based data collection. Remote monitoring has reduced the site burden, while adaptive designs have enhanced trial efficiency through mid-study modifications. Looking ahead, we expect hybrid models to dominate, adaptive designs to expand in oncology and rare diseases, and remote monitoring to evolve into AI-driven, risk-based oversight. Collectively, these shifts are steering trials toward greater flexibility, responsiveness, and patient centricity.
6. Your book emphasizes regulatory advances. How are regulators adapting to the rapid changes in clinical trial technology, and what regions or agencies are leading this shift?
Yang: Regulators worldwide are actively embracing innovation in clinical trials, moving beyond rigid frameworks toward flexibility and risk-based approaches. The FDA leads with guidance on decentralized trials, RWE, and AI/ML, reinforced by programs like the CID Pilot. Europe’s ACT EU and the UK’s MHRA promote digitalization and patient-centricity. In Asia-Pacific, countries like Japan, China, and Singapore are advancing frameworks for digital tools and RWE. Globally, regulators are not just adapting—they’re shaping a modern, safe, and innovative trial ecosystem.
7. Modernizing clinical trials requires collaboration across biostatistics, technology, operations, and regulatory teams. What cultural or structural barriers do you observe that hinder such integration, and how can organizations overcome them?
Yang: The biggest barrier to clinical trial modernization is often cultural, not technical. Siloed teams and risk-averse mindsets hinder collaboration and innovation. To move forward, organizations must foster early cross-functional integration, invest in education and change management, and empower teams through decentralized decision-making. Aligning incentives around shared goals and innovation—not just compliance—helps shift the culture. Modernization thrives in environments that value trust, transparency, and continuous learning across disciplines.
8. From a design perspective, how are innovations like basket trials, platform trials, and Bayesian methods redefining evidence generation in clinical trials? Are these approaches ready for routine adoption?
Yang: Innovations like basket trials, platform trials, and Bayesian methods are transforming clinical trials into adaptive, data-driven systems. They improve efficiency, reduce costs, and accelerate patient benefit by enabling real-time learning and flexible design. Technically and scientifically, these approaches are ready for routine use, but broader adoption depends on building internal expertise, robust simulation infrastructure, and navigating evolving regulatory frameworks. These designs are no longer experimental—they’re essential tools for modern drug development in a complex therapeutic landscape.
9. What are the most effective ways to incorporate real-world data into trial design and analysis without compromising methodological rigor? Can you share a practical example from the book that illustrates this integration?
Yang: Real-world data (RWD) can enhance trial relevance and efficiency when used with methodological rigor. Effective strategies include informing trial design, augmenting or replacing control arms using matched or Bayesian methods, and integrating real-world endpoints in hybrid designs. Ensuring data quality and transparent analysis is essential. In one oncology trial, RWD from a national registry guided early termination based on low success probability. RWD, when thoughtfully applied, is a powerful complement—not a shortcut—to traditional evidence.
10. How is trial modernization improving the patient experience, and what further innovations are needed to ensure inclusivity, accessibility, and patient trust?
Yang: Clinical trial modernization is improving the patient experience through decentralized models, telemedicine, eConsent, and home-based data collection—making participation more convenient, inclusive, and patient-friendly. These innovations reduce burdens and expand access, especially for underserved and rural populations. To fully realize this promise, we must pair technology with human-centered design: culturally sensitive outreach, plain-language materials, equitable digital access, and patient co-design. True modernization means treating patients as partners, ensuring trials are accessible, respectful, and aligned with real-world needs.
11. Adoption of new technologies in clinical trials can be uneven across organizations and regions. Based on your research, what are the key enablers and inhibitors of successful tech adoption in clinical research?
Yang: Technology adoption in clinical trials varies due to organizational and regional factors. Success depends on leadership support, cross-functional collaboration, digital infrastructure, workforce training, and regulatory clarity. Barriers include siloed teams, risk-averse culture, limited expertise, outdated systems, and regional disparities in infrastructure or policy. Overcoming these challenges requires strategic investment in people and technology, a culture of innovation, and proactive regulatory engagement to ensure new tools are implemented effectively and equitably across diverse settings.
12. As trials become increasingly data-driven and digital, how should sponsors and regulators navigate ethical concerns and patient privacy while maximizing innovation?
Yang: As clinical trials become more digital and data-driven, balancing innovation with ethical responsibility is crucial. Sponsors and regulators should ensure transparency in data use, limit data collection to trial needs, and enforce strong security measures. Engaging ethics committees and incorporating patient input fosters trust. Collaboration on harmonized regulations supports innovation without compromising privacy. Embedding these principles protects patient rights while advancing clinical research.
13. Based on the trends and frameworks discussed in your book, what does the clinical trial ecosystem look like in 2030? What radical changes should stakeholders prepare for?
Yang: By 2030, clinical trials will be decentralized, blending virtual and in-person elements to enhance global access. Real-time, data-driven decisions using AI and continuous monitoring will optimize outcomes. Patient-centricity will shape trial design, with dynamic consent and strong privacy safeguards. Real-world evidence will complement traditional trials, while flexible, harmonized regulatory frameworks will support innovation. Interoperable ecosystems and open collaboration will accelerate progress. Ethical vigilance and privacy protections will remain central, ensuring trials are efficient, inclusive, and personalized.
14. For professionals across pharma, biotech, CROs, and regulatory agencies - what three actionable takeaways from your book would you emphasize to begin or accelerate their modernization journey today?
Yang: To accelerate modernization, integrate diverse data sources—including real-world and patient-generated data—for agile trial designs and robust evidence. Adopt risk-based monitoring and decentralized trials using remote data capture and digital endpoints to enhance patient engagement and speed timelines. Finally, foster early, cross-functional collaboration among clinical, data, regulatory, and external partners to ensure compliance and streamline approvals.
Author Bio
Harry Yang, Ph.D., is Vice President of Biometrics at Recursion Pharmaceuticals, with over 20 years of experience in drug development. He has authored nine books and more than 130 publications. Dr. Yang is an expert in innovative clinical trial design, regulatory strategy, and the application of artificial intelligence and real-world data across multiple therapeutic areas.
