Linking cohorts and expert knowledge through categorical representations for improved knowledge extraction from longitudinal data (B03)

• Subject Area: Epidemiology and Medical Biometry/Statistics
• Term: since 2023
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 499552394

For transferring information from sub-cohorts of patients where only limited information is available to sub-cohorts of patients with comprehensive longitudinal characterization, we leverage that some types of assessments are categorical per-se, and that for others there are medically meaningful categorical representations. Specifically, we will learn the much simpler joint distribution of the categorical data in a pre-training step, and subsequently train a model again at the level of the quantitative measurements. Such simpler distributions will also be used to formalize and incorporate medical expert knowledge.

• DFG Programme: Collaborative Research Centres
• Subproject of: SFB 1597: Small Data
• Applicant Institution: Albert-Ludwigs-Universität Freiburg
• Project Heads: Professorin Dr. Cristina Has; Dr. Moritz Hess