Rxivist logo

Individualizing deep dynamic models for psychological resilience data

By Göran Köber, Shakoor Pooseh, Haakon Engen, Andrea Chmitorz, Miriam Kampa, Anita Schick, Alexandra Sebastian, Oliver Tüscher, Michéle Wessa, Kenneth S.L. Yuen, Henrik Walter, Raffael Kalisch, Jens Timmer, Harald Binder

Posted 21 Aug 2020
medRxiv DOI: 10.1101/2020.08.18.20177113

Deep learning approaches can uncover complex patterns in data. In particular, variational autoencoders (VAEs) achieve this by a non-linear mapping of data into a low-dimensional latent space. Motivated by an application to psychological resilience in the Mainz Resilience Project (MARP), which features intermittent longitudinal measurements of stressors and mental health, we propose an approach for individualized, dynamic modeling in this latent space. Specifically, we utilize ordinary differential equations (ODEs) and develop a novel technique for obtaining person-specific ODE parameters even in settings with a rather small number of individuals and observations, incomplete data, and a differing number of observations per individual. This technique allows us to subsequently investigate individual reactions to stimuli, such as the mental health impact of stressors. A potentially large number of baseline characteristics can then be linked to this individual response by regularized regression, e.g., for identifying resilience factors. Thus, our new method provides a way of connecting different kinds of complex longitudinal and baseline measures via individualized, dynamic models. The promising results obtained in the exemplary resilience application indicate that our proposal for dynamic deep learning might also be more generally useful for other application domains.

Download data

  • Downloaded 341 times
  • Download rankings, all-time:
    • Site-wide: 82,576
    • In psychiatry and clinical psychology: 286
  • Year to date:
    • Site-wide: 35,993
  • Since beginning of last month:
    • Site-wide: 25,828

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide