L3S Director Wolfgang Nejdl is co-author of a new white paper from the Learning Systems Platform, which uses practical examples to illustrate the challenges and potential of artificial intelligence (AI) in drug development. Together with the Leibniz AI Lab and the Lower Saxony Center for AI and Causal Methods in Medicine (CAIMed), the L3S is focusing its research on this area.

AI can accelerate the development of drugs and promote personalized medicine on a broad scale. In this way, better and individualized medicines can be brought to market more cost-effectively. However, the prerequisite for this is that patient data of sufficient quality is available for research in addition to active ingredient data and that a legally secure regulatory framework is created.

On average, a doctor prescribes one medicine per visit. Pharmaceuticals are the third largest item of expenditure in the German healthcare system. However, their development is becoming increasingly expensive and time-consuming. It takes around twelve years for a drug to reach the market, with total costs averaging 2.8 billion US dollars. The main reasons for this are increasingly complex products and study designs, increasing documentation and safety requirements during development and the costly recruitment of participants for clinical studies. In many cases, such as with antibiotics, the development of new active ingredients is no longer profitable.

Personalized cancer therapies and innovative active ingredients

The use of AI makes the drug development process more efficient and offers the opportunity to save years of work and costly investments, according to the white paper “Developing drugs with AI”. Artificial intelligence systematically analyzes and evaluates huge amounts of data and extensive knowledge. In this way, suitable drug targets and candidates can be found in a short time, better predictions can be made about the side effects of the drugs and the chemical synthesis, the production of the active ingredient, can be optimized. AI can support the selection and monitoring of test subjects for clinical trials and approval. AI-based data analysis enables the development of personalized therapies, for example for the treatment of cancer, which are tailored to the individual clinical picture of the person affected.

The authors of the white paper also identify the challenges on the path to AI-supported drug research. Large amounts of high-quality drug data must be available for the use of AI. However, this requires the willingness of research-based companies to share their data. Gaps exist particularly in the database on human biology, for example on disease mechanisms and drug effects. It is possible to fill this gap with high-quality data from the population. One means of obtaining data is the electronic patient record. AI analysis of patient data allows statements to be made about the effectiveness and side effects of drugs as well as personalized treatment recommendations.There are currently plans at both European and national level to increase data availability, for example in the form of the draft regulation on the European Health Data Space (EHDS) and the Health Data Utilization Act (GDNG) in Germany. The aim is to make health data available to industry for research purposes. The experts from the Learning Systems Platform recommend that the increased availability of data should not be capped by regulatory restrictions on AI-supported research.

Approval requires binding standards and transparency

The use of AI in drug development must also be taken into account in the approval and reimbursement of medicinal products. The results of AI data analysis must be comprehensible and AI-based statements on medical aspects must be clearly verifiable. In addition, AI also uses synthetically generated data. Binding standards are required for the verification and validity of AI-based data.
The use of AI methods in drug development also means that more applications for approval for new drugs are submitted to the authorities in less time. But AI can also help regulatory authorities to speed up processes in order to keep up with the increased pace of development, according to the white paper.

About the white paper

The whitepaper “Developing drugs with AI: From the idea to approval. Applications, potentials and challenges” was written by members of the Health, Medical Technology, Care working group of the Learning Systems Platform, including L3S Director Prof. Dr. Wolfgang Nejdl. It is available to download free of charge.