Today's Clinical Lab - News, Editorial and Products for the Clinical Laboratory
Graphic illustration of artificial intelligence helping in clinical oncology research.
AI-based health care can support clinicians in decision-making, therapy planning, and designing early multicancer precision diagnostics.

AI-Based Personalized Therapies Need Agile Approval Processes

Commercializing AI-based treatment warrants regulatory changes and multilayered testing and monitoring approaches

Dresden University of Technology
Published:Jan 30, 2024
|2 min read
Register for free to listen to this article
Listen with Speechify

The application of AI in precision oncology has so far been largely confined to the development of new drugs and has had a 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 adapted to patients’ needs—for example, to improve efficacy and dosage, reduce toxicity, develop combination therapies, and even personalize preclinical cell therapies based on their molecular properties. 

AI-based health care is evolving rapidly. It can support clinicians in decision-making and therapy planning as well as in early multicancer precision diagnostics. Other potential applications include designing new types of personalized medical products, building drug companion apps for patients, and using “digital twins”—virtual models of a real system or product that aid in exploring several attributes. Digital twins use patient data in almost real-time to enable more precise diagnosis using simulation and modeling and to adapt treatments to individual requirements. 

Advancing these products through regulatory pathways is challenging. They combine technologies governed by different legal frameworks and regulatory bodies and are so novel that they are not well dealt with in current legislation. The current approval conditions could make rapid clinical application difficult.  

Making approval processes agile

The paper, published recently in Precision Oncology, identifies two prominent challenges: Legislators and regulatory bodies underestimate the importance of developing technologies in medicine and research as well as the extent of required regulatory change to make approval processes more agile 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,” says Stephen Gilbert, PhD, professor of medical device regulatory science at the Else Kröner Fresenius Center for Digital Health at Technische Universität (TU) Dresden and University Hospital Carl Gustav Carus Dresden. 

Therefore, among other things, the researchers suggest updating risk-benefit assessments for highly personalized treatment approaches. Solutions already established in the US could also be adopted in the EU for certain classes of low-risk decision support for clinicians. The authors further suggest approaches to allow digital tools on the market to be safety-adaptable in a more flexible manner and to establish suitable test platforms for on-market monitoring. 

Multilayered approaches would help spread the load of oversight and make evaluation more relevant to patient safety.

- This press release was originally published on the Technische Universität Dresden website