Pharmaceutical companies need innovative approaches to effectively analyse data from clinical trials. Until now, these analyses have mainly been carried out using traditional statistical methods, which are often unable to recognise complex correlations and applications.

We supported Novartis in exploring the potential of artificial intelligence in clinical research.

The AI4ANNA study to predict treatment outcomes and tolerability in HR+, HER2- advanced breast cancer was presented at the San Antonio Breast Cancer Symposium in December 2023. The aim of the study was to evaluate the predictive potential of machine learning (ML) methods in terms of tumor control and safety outcomes using German study data (RIBECCA, RIBANNA) and to identify the most important baseline factors for prediction.

The publication can be found on ResearchGate Abstract P4-01-05.

By implementing these innovative approaches, our customers benefit from

• Discovery of unknown correlations and applications through the use of machine learning.
• Improved prediction of treatment outcomes and safety by analysing critical features.
• Use of Explainable AI methods to identify important features and optimise study results