Personalized therapy may improve the treatment of many diseases in the future. Cancer medicine in particular has made significant progress in recent years. Applications of artificial intelligence (AI) will allow tailoring of more targeted personalized therapies. New, AI-based therapies require a flexible and secure legal framework to reach patients quickly and safely. In their paper 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 associated regulatory challenges. They stress that the current strict and slow approval requirements hinder technological progress and argue for an adaptation of existing regulations.
The application of AI in precision oncology has so far been limited to the development of new drugs and has had limited impact on the personalization of therapy. New AI-based approaches are increasingly being applied to the planning and implementation of personalized medicine and cell therapy. Therapies can be adapted to the needs of individual patients – for example to improve efficacy and dosage, reduce toxicity, develop combination therapies and even personalize pre-clinical cell therapies based on their molecular characteristics.
AI-based healthcare is developing continuously and at an increasing pace. It can assist doctors in decision making and treatment planning as well as early multi-cancer accuracy diagnosis. Other potential applications include the design of new types of personalized medical products, medication companion apps for patients and the use of so-called “digital twins”. The latter use patient data in near real time through simulation and modeling to enable more precise diagnosis and tailor treatments to individual needs. Advancing these products through the regulatory pathway is extremely challenging. They combine technologies regulated by different legal frameworks and regulatory agencies and are so novel that they are not well addressed in current legislation. It can already be assumed that current approval conditions will quickly make clinical application difficult.
Making the approval process more agile in the future
The publication identifies two major challenges: lawmakers and regulatory agencies underestimate the importance of developing technologies in this field, as well as the extent of regulatory changes needed to make approval processes more agile in the future.
Current Regulations a real Blockers from AI-based personalized medicine. A fundamental change is needed to solve this problem.”
Stephen Gilbert, Professor of Medical Device Regulatory Science at the Else Kroner Fresenius Center for Digital Health at TU Dresden and University Hospital Carl Gustav Carus Dresden
The researchers therefore suggest, among other things, updating risk-benefit assessments for highly personalized treatment approaches. Solutions already established in the US can be adopted for certain classes of low-risk decision support for doctors in the EU. The authors also suggest that digital tools on the market allow for a more flexible approach to security and to establish suitable test platforms for on-market monitoring. A multi-tiered approach will help spread the burden of supervision and make assessments more relevant to patient safety.
Employees of the following institutions were involved in the publication: 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), University of Leipzig Clinical Immunology Institute for, the University Clinic Marburg as well as the University Paris-Saclay (Paris/France) and the life science consultancy ProductLifeGroup.