Personalized therapies could enhance the treatment of many diseases in the future. Cancer medicine, in particular, has made significant advances in recent years. Applications of artificial intelligence (AI) will allow even more targeted customization of personalized therapies. New, AI-based therapies require a flexible and secure legal framework to reach patients quickly and safely. In an article published today in the Nature Portfolio Journal „npj Precision Oncology,“ researchers from Dresden, Leipzig, Marburg, and Paris provide an overview of potential AI-based applications for personalized cancer medicine and the regulatory challenges associated with them. They emphasize that current rigid and slow approval requirements hinder technological progress and advocate for an adaptation of existing regulations.
The use of AI in precision oncology has largely focused on the development of new drugs and had limited impact on the personalization of therapies. New AI-based approaches are increasingly being applied to the planning and implementation of personalized drug and cell therapies. Therapies can be tailored to individual patient needs – for example, to improve effectiveness and dosage, reduce toxicity, develop combination therapies, and even personalize preclinical cell therapies based on their molecular properties.
The AI-based healthcare system is continually and rapidly evolving. It can assist physicians in decision-making and treatment planning, as well as early diagnosis of multiple cancer diseases. Furthermore, potential applications include the design of innovative personalized medical products, drug companion apps for patients, and the use of so-called „Digital Twins.“ The latter use patient data almost in real-time to enable a more accurate diagnosis through simulation and modeling and to tailor treatments to individual needs. The regulatory development of these products is an enormous challenge. They combine technologies subject to different legal frameworks and regulatory authorities and are so new that they are not adequately addressed in current legislation. It is already foreseeable that the current approval conditions will impede rapid clinical application.
Creating More Agile Approval Processes in the Future
The publication identifies two major challenges: lawmakers and regulators underestimate the importance of evolving technologies in this area and the extent of the necessary regulatory changes to create more agile approval processes in the future.
The current regulations are, in essence, a blockade to AI-based personalized medicine. To solve this problem, fundamental change is required.“
Stephen Gilbert, Professor of Medical Device Regulatory Science at the Else Kröner Fresenius Center for Digital Health, TU Dresden, and the University Hospital Carl Gustav Carus Dresden
Therefore, the authors propose, among other things, to update risk-benefit assessments for highly personalized treatment approaches. For certain classes of low-risk decision support for physicians, solutions already established in the USA could also be adopted in the EU. Furthermore, the authors suggest approaches to flexibly adjust digital tools on the market to safety and establish suitable test platforms for market monitoring. Multilayered approaches would help distribute the oversight burden and make the assessment more relevant to patient safety.
The publication involved staff from the following institutions: EKFZ for Digital Health at TU Dresden, University Hospital Carl Gustav Carus Dresden, Center for Scalable Data Analytics and Artificial Intelligence Dresden/Leipzig, Fraunhofer Institute for Cell Therapy and Immunology IZI (Leipzig), Institute of Clinical Immunology at Leipzig University, Marburg University Hospital, Université Paris-Saclay (Paris/France), and the life science consulting firm ProductLifeGroup.
Technische Universität Dresden
Derraz, B., et al. (2024). A new regulatory mindset is needed for AI-based personalized drug and cell therapies in precision oncology. npj Precision Oncology. doi.org/10.1038/s41698-024-00517-w.