Talk / Overview

Many diseases, including Alzheimer's and Parkinson's Disease, demonstrate highly dynamic disease trajectories, which impose challenges for the treatment of these patients and the design of successful clinical trials. This stratification problem translates into a complex problem of clustering multivariate and relatively short time series because (i) these diseases are multifactorial and not well described by single clinical outcome variables and (ii) disease progression needs to be monitored over time. Additionally, clinical data often additionally are hindered by the presence of many missing values, further complicating any clustering attempts. In my talk I will show, how our recently developed VADER algorithm (De Jong et al., Giga Science, 2019) can be used to address this issue and identify trajectory clusters in Alzheimer's as well as Parkinson's Disease. These trajectory clusters can subsequently be associated with distinct biological mechanisms, opening the door to more specific treatments.

Talk / Speakers

Holger Fröhlich

Head of AI & Data Science, Deputy Head of Department of Bioinformatics, Fraunhofer SCAI

Talk / Slides

Download the slides for this talk.Download ( PDF, 1411.22 MB)

Talk / Highlights

AI for Modeling and Clustering Multivariate Disease Trajectories with Missing Values

With Holger FröhlichPublished April 27, 2022

AMLD / Global partners