Deep learning and differential equations for modeling changes in individual-level latent dynamics between observation periods

• Verfasst von: Köber, Göran [VerfasserIn]
• Verfasst von: Kalisch, Raffael [VerfasserIn]
• Verfasst von: Puhlmann, Lara M.C. [VerfasserIn]
• Verfasst von: Chmitorz, Andrea [VerfasserIn]
• Verfasst von: Schick, Anita [VerfasserIn]
• Verfasst von: Binder, Harald [VerfasserIn]
• Titel: Deep learning and differential equations for modeling changes in individual-level latent dynamics between observation periods
• Titelzusatz: research article
• Verf.angabe: Göran Köber, Raffael Kalisch, Lara M.C. Puhlmann, Andrea Chmitorz, Anita Schick, Harald Binder
• E-Jahr: 2023
• Jahr: August 2023
• Umfang: 15 S.
• Illustrationen: Illustrationen
• Fussnoten: Online veröffentlicht: 17. März 2023 ; Gesehen am 02.04.2024
• Titel Quelle: Enthalten in: Biometrical journal
• Ort Quelle: Berlin : Wiley-VCH, 1977
• Jahr Quelle: 2023
• Band/Heft Quelle: 65(2023), 6 vom: Aug., Seite 1-15
• ISSN Quelle: 1521-4036
• DOI: doi:10.1002/bimj.202100381
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: deep learning
• Sach-SW: dynamic modeling
• Sach-SW: longitudinal data
• Sach-SW: observational data
• Sach-SW: variable selection
• K10plus-PPN: 1884709796

Abstract

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.