Download
Biometrical J - 2023 - Köber - Deep learning and differential equations for modeling changes in individual‐level latent.pdf 870,66KB
WeightNameValue
1000 Titel
  • Deep learning and differential equations for modeling changes in individual‐level latent dynamics between observation periods
1000 Autor/in
  1. Köber, Göran |
  2. Kalisch, Raffael |
  3. Puhlmann, Lara M.C. |
  4. Chmitorz, Andrea |
  5. Schick, Anita |
  6. Binder, Harald |
1000 Erscheinungsjahr 2023
1000 LeibnizOpen
1000 Publikationstyp
  1. Artikel |
1000 Online veröffentlicht
  • 2023-03-17
1000 Erschienen in
1000 Quellenangabe
  • 65(6):2100381
1000 FRL-Sammlung
1000 Copyrightjahr
  • 2023
1000 Lizenz
1000 Verlagsversion
  • https://doi.org/10.1002/bimj.202100381 |
1000 Publikationsstatus
1000 Begutachtungsstatus
1000 Sprache der Publikation
1000 Abstract/Summary
  • When modeling longitudinal biomedical data, often dimensionality reduction as well as dynamic modeling in the resulting latent representation is needed. This can be achieved by artificial neural networks for dimension reduction and differential equations for dynamic modeling of individual-level trajectories. However, such approaches so far assume that parameters of individual-level dynamics are constant throughout the observation period. Motivated by an application from psychological resilience research, we propose an extension where different sets of differential equation parameters are allowed for observation subperiods. Still, estimation for intra-individual subperiods is coupled for being able to fit the model also with a relatively small dataset. We subsequently derive prediction targets from individual dynamic models of resilience in the application. These serve as outcomes for predicting resilience from characteristics of individuals, measured at baseline and a follow-up time point, and selecting a small set of important predictors. Our approach is seen to successfully identify individual-level parameters of dynamic models that allow to stably select predictors, that is, resilience factors. Furthermore, we can identify those characteristics of individuals that are the most promising for updates at follow-up, which might inform future study design. This underlines the usefulness of our proposed deep dynamic modeling approach with changes in parameters between observation subperiods.
1000 Sacherschließung
lokal General Medicine
lokal Humans
lokal Neural Networks, Computer
lokal Deep Learning [MeSH]
lokal Humans [MeSH]
lokal Deep Learning
lokal Neural Networks, Computer [MeSH]
lokal Statistics and Probability
lokal Statistics, Probability and Uncertainty
1000 Fächerklassifikation (DDC)
1000 Liste der Beteiligten
  1. https://orcid.org/0000-0001-7038-0860|https://frl.publisso.de/adhoc/uri/S2FsaXNjaCwgUmFmZmFlbA==|https://frl.publisso.de/adhoc/uri/UHVobG1hbm4sIExhcmEgTS5DLg==|https://frl.publisso.de/adhoc/uri/Q2htaXRvcnosIEFuZHJlYQ==|https://frl.publisso.de/adhoc/uri/U2NoaWNrLCBBbml0YQ==|https://orcid.org/0000-0002-5666-8662
1000 Label
1000 Förderer
  1. Horizon 2020 |
  2. Projekt DEAL |
1000 Fördernummer
  1. 777084
  2. -
1000 Förderprogramm
  1. DynaMORE
  2. Open Access funding
1000 Dateien
  1. Deep learning and differential equations for modeling changes in individual‐level latent dynamics between observation periods
1000 Förderung
  1. 1000 joinedFunding-child
    1000 Förderer Horizon 2020 |
    1000 Förderprogramm DynaMORE
    1000 Fördernummer 777084
  2. 1000 joinedFunding-child
    1000 Förderer Projekt DEAL |
    1000 Förderprogramm Open Access funding
    1000 Fördernummer -
1000 Objektart article
1000 Beschrieben durch
1000 @id frl:6472671.rdf
1000 Erstellt am 2023-12-14T07:59:58.927+0100
1000 Erstellt von 336
1000 beschreibt frl:6472671
1000 Bearbeitet von 317
1000 Zuletzt bearbeitet Thu Dec 14 13:30:44 CET 2023
1000 Objekt bearb. Thu Dec 14 13:30:31 CET 2023
1000 Vgl. frl:6472671
1000 Oai Id
  1. oai:frl.publisso.de:frl:6472671 |
1000 Sichtbarkeit Metadaten public
1000 Sichtbarkeit Daten public
1000 Gegenstand von

View source