Modelling interpretable patient-level representationsfrom structured and simple multimodal data
Kazimierz Oksza-Orzechowski, Małgorzata Łazȩcka, Łukasz Koperski, Damian Wójtowicz, Marcin Możejko, Daniel Schulz, Robin Liechti, Flavia Marzetta, Marie Morfouace, Henoch Sangjoon Hong, Stéphanie Tissot-Renaud, Bernd Bodenmiller, Eike Staub, Ewa Szczurek
The paper introduces FACTMx, a variational framework that jointly models structured and simple patient-level data to learn interpretable representations, showing improved performance in simulations and applications to cancer and cardiovascular cohorts.
bioRxiv · Sep 4, 2026 · PreprintBioinformatics