Daniel Durstewitz

Daniel Durstewitz

Auto-generated profile, based on publicly available information

Daniel Durstewitz

Department of Theoretical Neuroscience, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2010 in Neuron
Verified
Journal Article
Closed access
DDDaniel Durstewitz
Daniel Durstewitz
NVNicole M. Vittoz
Nicole M. Vittoz
SFStan B. Floresco
Stan B. Floresco
JSJeremy K. Seamans
Jeremy K. Seamans

15 February 2019 in Molecular Psychiatry
Verified
Journal Article
Open access
DDDaniel Durstewitz
Daniel Durstewitz
GKGeorgia Koppe
Georgia Koppe
AMAndreas Meyer-Lindenberg
Andreas Meyer-Lindenberg
Machine and deep learning methods, today's core of artificial intelligence, have been applied with increasing success and impact in many commercial and research settings. They are powerful tools for large scale data analysis, prediction and classification, especially in very data-rich environments ("big data"), and have started to find their way into medical applications. Here we will first give an overview of machine learning methods, with a focus on deep and recurrent neural networks, their relation to statistics, and the core principles behind them. We will then discuss and review directions along which (deep) neural networks can be, or already have been, applied in the context of psychiatry, and will try to delineate their future potential in this area. We will also comment on an emerging area that so far has been much less well explored: by embedding semantically interpretable computational models of brain dynamics or behavior into a statistical machine learning context, insights into dysfunction beyond mere prediction and classification may be gained. Especially this marriage of computational models with statistical inference may offer insights into neural and behavioral mechanisms that could open completely novel avenues for psychiatric treatment.

15 July 2020 in Neuropsychopharmacology
Verified
Journal Article
Open access
PDF file
GKGeorgia Koppe
Georgia Koppe
AMAndreas Meyer-Lindenberg
Andreas Meyer-Lindenberg
DDDaniel Durstewitz
Daniel Durstewitz
Psychiatry today must gain a better understanding of the common and distinct pathophysiological mechanisms underlying psychiatric disorders in order to deliver more effective, person-tailored treatments. To this end, it appears that the analysis of ‘small’ experimental samples using conventional statistical approaches has largely failed to capture the heterogeneity underlying psychiatric phenotypes. Modern algorithms and approaches from machine learning, particularly deep learning, provide new hope to address these issues given their outstanding prediction performance in other disciplines. The strength of deep learning algorithms is that they can implement very complicated, and in principle arbitrary predictor-response mappings efficiently. This power comes at a cost, the need for large training (and test) samples to infer the (sometimes over millions of) model parameters. This appears to be at odds with the as yet rather ‘small’ samples available in psychiatric human research to date (n < 10,000), and the ambition of predicting treatment at the single subject level (n = 1). Here, we aim at giving a comprehensive overview on how we can yet use such models for prediction in psychiatry. We review how machine learning approaches compare to more traditional statistical hypothesis-driven approaches, how their complexity relates to the need of large sample sizes, and what we can do to optimally use these powerful techniques in psychiatric neuroscience.

4 October 2023 in Nature Reviews Neuroscience
Verified
Journal Article
Closed access
PDF file
DDDaniel Durstewitz
Daniel Durstewitz
GKGeorgia Koppe
Georgia Koppe
MTMax Ingo Thurm
Max Ingo Thurm

9 March 2021 in European Psychiatry
Verified
Journal Article
Open access
PDF file
CRChristian Rauschenberg
Christian Rauschenberg
ASAnita Schick
Anita Schick
CGChristian Goetzl
Christian Goetzl
SRSusanne Roehr
Susanne Roehr
SRSteffi G. Riedel-Heller
Steffi G. Riedel-Heller
URUlrich Reininghaus
Ulrich Reininghaus
Background: Public health measures to curb SARS-CoV-2 transmission rates may have negative psychosocial consequences in youth. Digital interventions may help to mitigate these effects. We investigated the associations between social isolation, COVID-19-related cognitive preoccupation, worries, and anxiety, objective social risk indicators, and psychological distress, as well as use of, and attitude toward, mobile health (mHealth) interventions in youth.Methods: Data were collected as part of the “Mental Health And Innovation During COVID-19 Survey”—a cross-sectional panel study including a representative sample of individuals aged 16–25 years (N = 666; Mage = 21.3; assessment period: May 5, 2020 to May 16, 2020).Results: Overall, 38% of youth met criteria for moderate or severe psychological distress. Social isolation worries and anxiety, and objective risk indicators were associated with psychological distress, with evidence of dose–response relationships for some of these associations. For instance, psychological distress was progressively more likely to occur as levels of social isolation increased (reporting “never” as reference group: “occasionally”: adjusted odds ratio [aOR] 9.1, 95% confidence interval [CI] 4.3–19.1,p < 0.001; “often”: aOR 22.2, CI 9.8–50.2,p < 0.001; “very often”: aOR 42.3, CI 14.1–126.8,p < 0.001). There was evidence that psychological distress, worries, and anxiety were associated with a positive attitude toward using mHealth interventions, whereas psychological distress, worries, and anxiety were associated with actual use.Conclusions: Public health measures during pandemics may be associated with poor mental health outcomes in youth. Evidence-based digital interventions may help mitigate the negative psychosocial impact without risk of viral infection given there is an objective need and subjective demand.

21 August 2019 in PLOS Computational Biology
Verified
Journal Article
Open access
PDF file
GKGeorgia Koppe
Georgia Koppe
HTHazem Toutounji
Hazem Toutounji
PKPeter Kirsch
Peter Kirsch
SLStefanie Lis
Stefanie Lis
DDDaniel Durstewitz
Daniel Durstewitz
A major tenet in theoretical neuroscience is that cognitive and behavioral processes are ultimately implemented in terms of the neural system dynamics. Accordingly, a major aim for the analysis of neurophysiological measurements should lie in the identification of the computational dynamics underlying task processing. Here we advance a state space model (SSM) based on generative piecewise-linear recurrent neural networks (PLRNN) to assess dynamics from neuroimaging data. In contrast to many other nonlinear time series models which have been proposed for reconstructing latent dynamics, our model is easily interpretable in neural terms, amenable to systematic dynamical systems analysis of the resulting set of equations, and can straightforwardly be transformed into an equivalent continuous-time dynamical system. The major contributions of this paper are the introduction of a new observation model suitable for functional magnetic resonance imaging (fMRI) coupled to the latent PLRNN, an efficient stepwise training procedure that forces the latent model to capture the ‘true’ underlying dynamics rather than just fitting (or predicting) the observations, and of an empirical measure based on the Kullback-Leibler divergence to evaluate from empirical time series how well this goal of approximating the underlying dynamics has been achieved. We validate and illustrate the power of our approach on simulated ‘ground-truth’ dynamical systems as well as on experimental fMRI time series, and demonstrate that the learnt dynamics harbors task-related nonlinear structure that a linear dynamical model fails to capture. Given that fMRI is one of the most common techniques for measuring brain activity non-invasively in human subjects, this approach may provide a novel step toward analyzing aberrant (nonlinear) dynamics for clinical assessment or neuroscientific research. Computational processes in the brain are often assumed to be implemented in terms of nonlinear neural network dynamics. However, experimentally we usually do not have direct access to this underlying dynamical process that generated the observed time series, but have to infer it from a sample of noisy and mixed measurements like fMRI data. Here we combine a dynamically universal recurrent neural network (RNN) model for approximating the unknown system dynamics with an observation model that links this dynamics to experimental measurements, taking fMRI data as an example. We develop a new stepwise optimization algorithm, within the statistical framework of state space models, that forces the latent RNN model toward the true data-generating dynamical process, and demonstrate its power on benchmark systems like the chaotic Lorenz attractor. We also introduce a novel, fast-to-compute measure for assessing how well this worked out in any empirical situation for which the ground truth dynamical system is not known. RNN models trained on human fMRI data this way can generate new data with the same temporal structure and properties, and exhibit interesting nonlinear dynamical phenomena related to experimental task conditions and behavioral performance. This approach can easily be generalized to many other recording modalities.