Posted in | News | Medical Robotics

AI Optimizes Doses, Minimizes Toxicity in Personalized Cancer Care

In the future, personalized therapies may help treat a wide range of illnesses. In particular, cancer medicine has advanced significantly in the last several years.

AI Optimizes Doses, Minimizes Toxicity in Personalized Cancer Care

Image Credit: PantherMedia / everythingposs

Artificial intelligence (AI) applications will make it possible to tailor personalized treatments even more precisely. For new, AI-based therapies to reach patients swiftly and safely, a flexible and secure legal framework is necessary.

Researchers from Dresden, Leipzig, Marburg, and Paris present an overview of potential AI-based applications for personalized cancer medicine as well as the related regulatory challenges in a paper that was published in the Nature Portfolio journal npj Precision Oncology. The researchers highlight how the current, onerous, and slow approval processes impede technological advancement and make the case for changing the current regulations.

Up until now, the majority of AI’s use in precision oncology has gone toward the creation of novel medications; it has had little effect on the customization of treatment plans. Customized drug and cell therapies are being planned and executed with a growing number of new AI-based strategies.

The needs of each patient can be catered to by tailoring the therapy, which can include enhancing dosage and efficacy, lowering toxicity, creating combination treatments, and even modifying the molecular characteristics of preclinical cell therapies.

Healthcare powered by AI is evolving steadily and more quickly. It can assist physicians in early multi-cancer precision diagnostics, therapy planning, and decision-making. Additional possible uses include creating novel kinds of customized medical devices, providing patients with drug companion applications, and utilizing “digital twins.”

The latter employed nearly real-time patient data to enable more accurate diagnosis through modeling and simulation, as well as to customize treatments to meet each patient's needs. It is very difficult to advance these products through regulatory channels.

They combined technologies that are under the jurisdiction of several legal systems and regulatory agencies, and because they are so new, the laws that currently exist do not adequately address them. It is already expected that the current conditions of approval will impede the rapid clinical application.

Making Approval Processes More Agile in the Future

The article highlights two significant issues: lawmakers and regulatory agencies undervalue the significance of emerging technologies in this field and the magnitude of the regulatory adjustments needed to make approval procedures more flexible in the future.

The current regulations are a de facto blocker to AI-based personalized medicine. A fundamental change is needed to solve this problem.

Stephen Gilbert, Professor, Medical Device Regulatory Science, Else Kröner Fresenius Center for Digital Health, TU Dresden

Stephen Gilbert is also associated with the University Hospital Carl Gustav Carus Dresden.

Thus, among other things, the researchers advise updating risk-benefit analyses for highly individualized treatment modalities. Solutions that have already been adopted in the US could also be adopted in the EU for specific categories of low-risk physician decision support.

The authors also offer strategies for creating appropriate test platforms for in-market surveillance and for enabling digital tools to be safer and more flexible when the tools are put on the market. Multi-layered strategies would aid in distributing the supervision load and increase the relevance of evaluation to patient safety.

The publication involved staff members from the following organizations: University Clinic Marburg, Fraunhofer Institute for Cell Therapy and Immunology IZI (Leipzig), University Hospital Carl Gustav Carus Dresden, EKFZ for Digital Health at TU Dresden, University Clinic Marburg, Université Paris-Saclay (Paris/France), and the life science consulting firm ProductLifeGroup. Additional organizations involved in the publication were the following.

Journal Reference

Derraz, B., et al. (2024) New regulatory thinking is needed for AI-based personalized drug and cell therapies in precision oncology. npj Precision Oncology. doi.org/10.1038/s41698-024-00517-w.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.