Image

Enhancing Cancer Treatment Decisions with AI: Therapeutic Assistance and Decision Algorithms for Hepatobiliary Tumor Boards

Interdisciplinary tumor conferences, where specialists from multiple medical fields collaborate, are essential for ensuring the best possible diagnosis and treatment of cancer. However, critical patient and tumor information needed for therapy decisions is often incomplete or of insufficient quality. This can lead to significant delays in patient treatment.

The ADBoard project aims to address this challenge by leveraging the power of artificial intelligence (AI) to enhance therapy decision-making. The project develops a novel decision support system for liver tumors. AI methods such as natural language processing and machine learning will provide the technical basis for automated data provision and decision support, including therapy recommendations. The robustness, reproducibility, transparency and explainability of the proposed therapy recommendations will be evaluated in a study. For this purpose, the therapy recommendations proposed by the system will be compared with the decisions of the tumor conferences actually conducted. In the future, the therapy recommendations prepared using AI will support physicians in making timely and optimal therapy decisions for liver tumors. The long-term goal is to apply the new system in clinical practice and to transfer the system to other tumor types, setting a new standard for AI-assisted cancer care.

Info

  • Project lead: Univ.-Prof. Dr. med. Johann Pratschke
  • Team: Priv.-Doz. Dr. Felix Krenzien, Priv.-Doz. Dr. Christian Benzing, Dr. Nora Nevermann, Prof. Dr. Dominik Modest, PD Dr. Uwe Pelzer, Prof. Dr.-Ing. Sebastian Möller, Dr. Roland Roller, Dr. Philippe Thomas
  • Duration 2022 - 2025
  • Funding: Innovationsfonds des Gemeinsamen Bundesausschusses

Partners
© 2025 Prof. Dr. Igor M. Sauer | Charité - Universitätsmedizin Berlin | Disclaimer

This website or its third-party tools use cookies, which are necessary to its functioning and required to achieve the purpose illustrated in the Disclaimer. By closing this banner, scrolling this page, clicking a link or continuing to browse otherwise, you agree to the use of cookies.