RAI – Reliable AI for Biomedicine

As many molecular biology labs and clinical research groups leverage modern AI systems in their workflows, we need tools that quantify their uncertainty to uphold scientific standards. In the past, we relied on statistical uncertainty quantification in the form of p-values and confidence intervals. Almost every paper reported those quantities and allowed us to judge the credibility of a research discovery. This common statistical language – although not without its critics – allowed us to focus our resources towards the most promising discoveries. How can we quantify our level of surprise of a discovery from prediction models in a similar fashion?

In this project, we will build a platform that will help researchers in biomedicine to quantify uncertainty for their prediction models. We will use recent advances in statistics and machine learning – the so-called conformal prediction framework – to add prediction intervals to their models. The researchers will upload their models and part of their data on our platform website. We will then build prediction intervals for their models and deliver them back to the researchers as a download.

Project duration: 01.09.2024 – 31.08.2026

Contact: Prof. Dr. Christof Seiler

Website: RAI – Reliable AI for Biomedicine

Project Team

Prof. Dr. Christof Seiler is a Group Leader in the Department of Rheumatology at USZ and UZH, and Assistant Professor of Statistics in the Department of Advanced Computing Sciences at Maastricht University. His group focuses on biomedical data science.

Prof. Dr. Oliver Distler  is the Director of the Department of Rheumatology and Professor of Rheumatology at USZ and UZH. His group focuses on systemic sclerosis, interstitial lung diseases associated with connective tissue diseases, and systemic autoimmune diseases.

Prof. Dr. Michael Krauthammer is the Principal Investigator of the Krauthammer Lab and Professor of Medical Informatics in the Department of Quantitative Biomedicine at UZH. His lab focuses on clinical data science and translational bioinformatics.

Prof. Dr. Bjoern Menze is the Principal Investigator of the Menze Group and Professor of Biomedical Image Analysis and Machine Learning in the Department of Quantitative Biomedicine at UZH. His group focuses on biomedical image computing.