How AI is Revolutionizing Pharmaceutical Research & Development

Exploring AI's Role in Drug Discovery, Clinical Trials, and Future Healthcare with Expert Insights from Renee Iacona, Vice President of Oncology Biometrics at AstraZeneca

Add bookmark
Joanna Edwards
Joanna Edwards
07/03/2024

Researchers in a high-tech laboratory utilizing AI and robotics for drug discovery and development. The image features advanced computer screens, robotic arms, and a holographic display of a human figure surrounded by scientific data and molecular structures.

Introduction

In the pharmaceutical industry, the integration of Artificial Intelligence (AI) is transforming the R&D process. From speeding up the identification of new targets, and repurposing existing molecules, to improving patient recruitment and retention, and optimising trial design, AI offers unprecedented efficiency and precision. Pharma IQ sat down with Renee Iacona, Vice President of Oncology Biometrics at AstraZeneca, to discuss how AI is revolutionising these processes and its broader implications for the future of healthcare. Renee oversees biometrics across early and late development stages of the oncology portfolio, focusing on the design, delivery, and interpretation of clinical trials, regulatory activity, and data science support.

Transforming R&D with AI: Insights from Renee Iacona

AI in Drug Discovery and Development

Q1: How is AI being leveraged in the discovery and development of new molecules?

Renee Iacona: AI and machine learning have replaced some wet lab experiments with in-silico experiments, significantly speeding up the creation and testing of new molecules. For example, AI-driven platforms enable us to test and create new molecules in a fraction of the time it would take using traditional methods, saving weeks to months in the development timeline.

Q2: Can you share a case study where AI helped repurpose an existing molecule?

Renee Iacona: Absolutely. We had a molecule that was shelved years ago due to lack of efficacy in its initial target. By using AI to analyse knowledge graphs that include data from past and external clinical trials, we identified a new application for this molecule. It has now been repurposed and is showing promising results in a different therapeutic area, demonstrating how AI can breathe new life into previously abandoned compounds.

Q3: What role does AI play in detecting biomarkers and enhancing predictive analytics?

Renee Iacona: AI is crucial for detecting biomarkers at levels beyond human capabilities, particularly in precision oncology. We have a major project focused on AI-assisted pathology, where machine learning helps pathologists detect biomarkers with greater accuracy and precision. This enhanced detection can influence patient response predictions and treatment plans, leading to more personalised and effective treatments.

Enhancing Efficiency and Optimising Trial Design

Q4: How has AI improved efficiency in clinical trial site selection and operations?

Renee Iacona: AI has significantly enhanced our site selection strategies, especially for rare diseases or specific oncology tumour types. By analysing historical and real-world data, AI identifies the best sites for clinical trials, ensuring we target locations with the highest probability of recruiting eligible patients. This targeted approach reduces wastage by minimising non-productive trial sites, conserving resources, and streamlining operations.

Q5: Can you provide an example of how AI optimises trial design?

Renee Iacona: While traditional modelling and simulation are still prevalent, AI allows us to conduct more complex analyses, particularly when integrating biomarkers and genomic data. For instance, AI-driven predictive models help us refine control arms in trials, increasing our chances of success and reducing the likelihood of negative trials. This integration of advanced data analytics enhances our trial designs, making them more robust and efficient.

Overcoming Challenges in Implementing AI

Q6: What are the challenges of implementing AI effectively and safely in clinical trials?

Renee Iacona: Implementing AI effectively and safely comes with several challenges. Ensuring the accuracy and fairness of AI algorithms is critical, as bias in AI models can lead to skewed results and potentially exclude certain patient groups. We are committed to continuously refining our AI models to eliminate bias, which includes diversifying the datasets we use and collaborating with experts in AI ethics. Additionally, regulatory compliance is essential. We work closely with regulatory bodies to ensure our AI applications meet all necessary standards and guidelines, ensuring they are legitimate and verifiable.

Q7: How is generative AI being used in routine tasks, and what are the associated challenges?

Renee Iacona: Generative AI, like ChatGPT, is currently useful for tasks such as summarising emails and improving personal efficiency. However, its role in conducting complex analyses remains limited due to concerns about accuracy and reliability. Bias is another significant challenge, as AI systems are influenced by the historical data and user demographics they are trained on. At AstraZeneca, we are actively working to increase the diversity of our input data to mitigate these biases and ensure more representative and accurate AI outcomes.

Q8: What are the regulatory and validation challenges of using AI in drug development?

Renee Iacona: Ensuring AI-derived results comply with regulatory requirements is critical. We collaborate closely with regulatory bodies, such as the FDA, to establish guidelines for AI usage and validation. This collaboration helps us ensure that AI applications are legitimate, verifiable, and aligned with industry standards, ultimately supporting the development of safe and effective treatments.

The Future of AI in Healthcare

Q9: How do you foresee AI impacting the patient perspective and the future of healthcare?

Renee Iacona: AI tools can empower patients by providing them with more information about their conditions, helping them make informed decisions about their healthcare. In the next 20 years, AI is expected to become an integral part of both scientific discovery and patient care, improving efficiency and accuracy in drug development and treatment personalisation. This will lead to better patient outcomes and more personalised healthcare experiences.

Conclusion

AI is undeniably transforming the landscape of drug discovery & development and clinical trials. By enhancing patient recruitment and retention, optimising trial design, accelerating target identification, and repurposing existing molecules, AI offers significant benefits to the pharmaceutical industry. The insights shared by Renee Iacona illustrate the potential of AI to revolutionise these processes, paving the way for more efficient, accurate, and personalised treatments.

Join the Conversation at the AI for Pharma & Healthcare Conference

Taking place from September 24-26, 2024, in Amsterdam, AI for Pharma & Healthcare [https://www.pharma-iq.com/events-ai-pharma-healthcare] – Pharma IQ’s groundbreaking new conference - will go beyond the hype, presenting real-world AI use cases in drug discovery, clinical trials, supply chain, and manufacturing.

Don't miss this chance to explore practical applications of AI, share insights, and discover the innovations shaping the future of pharma and healthcare.

Visit AI for Pharma & Healthcare to learn more about how to be at the forefront of AI implementation in the pharmaceutical industry.

 


RECOMMENDED