There’s little doubt that 2023 will be remembered as the breakout year for generative artificial intelligence (AI) and machine learning (ML) within both tech and pharma. Much like the surge in digital and decentralized trials in 2020, AI and ML have sparked a paradigm shift in what is possible in the development of drugs and treatments.
With the FDA’s recent publications providing a future framework, sponsors and CROs everywhere are researching how best to bolster drug development. With all these advancements happening at an unprecedented pace, we’re providing an overview of the uses of AI and ML in clinical conduct below.
Transforming clinical trial design with AI and ML
AI and ML's potential in clinical trials extends to optimizing trial design, management, and overall outcomes. By leveraging historical clinical trial data, algorithms can identify areas for protocol optimization, including appropriate endpoint selection, sample sizes, and study durations. The result is more efficient and informative trials, reducing costs, expediting timelines, and ultimately increasing the likelihood of successful outcomes. Additionally, the ability to analyze complex data enables researchers to design trials that minimize patient burden and enhance participant retention.
AI and ML and study design
In the build stage, automation can play a crucial role in creating case report forms (CRFs) and building databases. Traditionally, data managers manually generate numerous CRFs for data collection, which can be time-consuming and prone to errors. AI and ML significantly accelerate the process as the technology reads the clinical trial protocol and automatically generates eCRFs and matrices.
FDA's initiatives: Embracing AI and ML in drug development
The FDA has taken a proactive stance in adopting AI and ML in drug development, as evident from its comprehensive discussion paper titled "Artificial Intelligence and Machine Learning (AI and ML) in Drug Development."
This paper outlines the multifaceted applications of the technology across the industry, encompassing target identification, compound screening, clinical research, safety surveillance, and advanced pharmaceutical manufacturing.
By actively engaging stakeholders and seeking industry input, the FDA fosters responsible implementation to ensure safer, more efficient drug development processes.
AI and ML accelerate patient recruitment and screening
Patient recruitment has long been a major challenge in clinical trials. AI and ML technologies are rising to the occasion, providing innovative solutions for identifying suitable participants based on specific medical characteristics aligned with trial criteria.
Through data analysis from diverse sources, including clinical trial databases, medical literature, social media, and electronic health records (EHRs), automation streamlines the process of matching patients to relevant trials. This breakthrough ensures early identification of potential participants and promotes inclusivity, diversifying clinical research participant pools.
Enhancing real-time monitoring and safety assessment
AI and ML's capabilities are not limited to trial design and patient recruitment. Automated systems enable continuous real-time monitoring of patients during clinical trials, providing valuable insights into their health status and potential adverse reactions.
This proactive approach enhances patient safety and allows for timely intervention, mitigating risks and optimizing study outcomes. Furthermore, the technology can predict drug interactions and analyze pharmacokinetics profiles, leading to a deeper understanding of drug efficacy and potential adverse events.
AI and ML's pivotal role in drug discovery and development
By facilitating rational drug design, drug repurposing, and lead compound optimization, AI and ML can expedite the drug development process while optimizing costs and increasing the likelihood of regulatory approval.
Additionally, sponsors and CROs now have the ability to analyze vast amounts of data, enabling the identification of novel drug targets, simulation of drug interactions, and prediction of drug properties such as solubility, bioavailability, and toxicity. The result is a transformative impact on the drug development landscape, offering a faster, more efficient approach to bringing life-saving medications to market.
Real-world use cases
Recently, IQVIA’s Director of Data Analytics, Betsy Wagner, showcased three use cases on how AI and ML have helped advance trials in the real world.
Traditional methods for assessing trial feasibility are resource-intensive and inefficient, leading to inconsistencies and delays in site selection and study acceptance. By implementing AI and ML-powered technology, a clinical research site achieved a 90% time savings on feasibility survey completions.
The technology improved accuracy, streamlined data collection, and helped select studies that were truly feasible for enrollment, thus optimizing resource allocation and strengthening relationships with trial sponsors.
Patient Enrollment Optimization:
Patient recruitment is a significant administrative burden in clinical research. An oncology clinic partnered with a tech-enabled solutions provider to identify eligible patients for a breast cancer study using AI and ML algorithms. The platform ingested and analyzed relevant patient data, leading to a 200% increase in enrollment during the initial months of the COVID-19 pandemic, and continued success over the following year.
Clinical Research Rescue:
Unexpected barriers can arise during clinical trials, leading to high costs and potential failure. By applying and automating algorithms, a healthcare center was able to salvage two underperforming clinical trials.
Patients were placed on a "watch list" while receiving first-line treatments, and when their disease progressed, they became eligible for the trials. This approach brought therapy access to patients and strengthened the center's credibility with sponsors.
Closing Thoughts: The new frontier is fast approaching
The advancements of AI and ML are being brought to clinical research, igniting a profound transformation in the pharmaceutical industry. The FDA's proactive stance in embracing this technology and the articles published all across pharma underscore the significance of these technologies in reshaping the future of clinical research.
Harnessing the potential of AI and ML, pharmaceutical companies can accelerate drug development, optimize clinical trials, enhance patient outcomes, and usher in a new era of healthcare innovation. As the technology continues to evolve, its integration into clinical research promises a future of boundless possibilities, propelling the industry toward groundbreaking discoveries and a more efficient, patient-centric approach to drug development and clinical trials.