This repository contains the relevant source code used in the publication
Progression subtypes in Parkinson’s disease identified by a data-driven multicohort analysis (Tom Hähnel, Tamara Raschka, Stefano Sapienza, Jochen Klucken, Enrico Glaab, Jean-Christophe Corvol, Björn H. Falkenburger & Holger Fröhlich. npj parkinson's disease. 2024. DOI: 10.1038/s41531-024-00712-3).
Please refer to this publication for further information.

The repository contains the following code:
model_training: Code for training the latent time joint mixed-effect models (LTJMM) and variational deep embedding with recurrence (VaDER).
metaanalyses: Code for calculating the associations of symptom domains (I) at baseline and (II) progression rates with PD progression subtypes.
samplesize: Code for sample size calculation for cohorts enriched with various fractions of fast-progressing patients.