Skip to main content Skip to main navigation

Project | adBoard

Duration:

Therapeutic Assistance and Decision Algorithms for Hepatobiliary Tumor Boards

Interdisciplinary tumour conferences with doctors from different disciplines are the key to the best possible diagnosis and therapy of cancer. The information about the patient and the tumour that is necessary for the therapy decision is often not available to those treating the patient in full or in sufficient quality. This sometimes leads to a significant delay in the treatment of those affected. Researchers in the ADBoard project want to contribute to further improving therapy decisions with the help of artificial intelligence (AI).

The aim of the project is the exemplary use of a novel decision support system for liver tumours. 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 the project within the framework of a study. For this purpose, the therapy recommendations suggested by the system will be compared with the decisions of the tumour conferences actually carried out.

The therapy recommendations prepared using AI are intended to support doctors in the future in making timely and optimal therapy decisions for liver tumours. The long-term goal is to apply the new system in clinical practice and to transfer the system to other tumour types.

Partners

Charité ̶ Universitätsmedizin Berlin

Publications about the project

  1. Retrieval-Augmented Knowledge Integration into Language Models: A Survey

    Yuxuan Chen; Daniel Röder; Justus-Jonas Erker; Leonhard Hennig; Philippe Thomas; Sebastian Möller; Roland Roller

    In: Sha Li; Manling Li; Michael JQ Zhang; Eunsol Choi; Mor Geva; Peter Hase; Heng Ji (Hrsg.). Proceedings of the 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024). Workshop on Towards Knowledgeable Language Models (KnowLLM-2024), Bangkok, Thailand, Pages 45-63, Association for Computational Linguistics, 2024.

Sponsors

Gemeinsamer Bundesausschuss