Volker Roth | University of Basel, Switzerland (original) (raw)

Papers by Volker Roth

Machine Learning, Jul 17, 2015

We present a novel probabilistic clustering model for objects that are represented via pairwise d... more We present a novel probabilistic clustering model for objects that are represented via pairwise distances and observed at different time points. The proposed method utilizes the information given by adjacent time points to find the underlying cluster structure and obtain a smooth cluster evolution. This approach allows the number of objects and clusters to differ at every time point, and no identification on the identities of the objects is needed. Further, the model does not require the number of clusters being specified in advance-they are instead determined automatically using a Dirichlet process prior. We validate our model on synthetic data showing that the proposed method is more accurate than state-of-the-art clustering methods. Finally, we use our dynamic clustering model to analyze and illustrate the evolution of brain cancer patients over time.

bioRxiv (Cold Spring Harbor Laboratory), Nov 1, 2022

Psychedelics have emerged as promising candidate treatments for various psychiatric conditions, a... more Psychedelics have emerged as promising candidate treatments for various psychiatric conditions, and given their clinical potential, there is a need to identify biomarkers that underlie their effects. Here, we investigate the neural mechanisms of lysergic acid diethylamide (LSD) using regression dynamic causal modelling (rDCM), a novel technique that assesses whole-brain effective connectivity (EC) during resting-state functional magnetic resonance imaging (fMRI). We modelled data from two randomized, placebo-controlled, double-blind, cross-over trials, in which 45 participants were administered 100µg LSD and placebo in two resting-state fMRI sessions. We compared EC against whole-brain functional connectivity (FC) using classical statistics and machine learning methods. Multivariate analyses of EC parameters revealed widespread increases in interregional connectivity and reduced self-inhibition under LSD compared to placebo, with the notable exception of primarily decreased interregional connectivity and increased self-inhibition in occipital brain regions. This finding suggests that LSD perturbs the Excitation/Inhibition balance of the brain. Moreover, random forests classified LSD vs. placebo states based on FC and EC with comparably high accuracy (FC: 85.56%, EC: 91.11%) suggesting that both EC and FC are promising candidates for clinically-relevant biomarkers of LSD effects.

Frontiers in Psychology

Speaker diarization is the practice of determining who speaks when in audio recordings. Psychothe... more Speaker diarization is the practice of determining who speaks when in audio recordings. Psychotherapy research often relies on labor intensive manual diarization. Unsupervised methods are available but yield higher error rates. We present a method for supervised speaker diarization based on random forests. It can be considered a compromise between commonly used labor-intensive manual coding and fully automated procedures. The method is validated using the EMRAI synthetic speech corpus and is made publicly available. It yields low diarization error rates (M: 5.61%, STD: 2.19). Supervised speaker diarization is a promising method for psychotherapy research and similar fields.

Psychedelics have emerged as promising candidate treatments for various psychiatric conditions, a... more Psychedelics have emerged as promising candidate treatments for various psychiatric conditions, and given their clinical potential, there is a need to identify biomarkers that underlie their effects. Here, we investigate the neural mechanisms of lysergic acid diethylamide (LSD) using regression dynamic causal modelling (rDCM), a novel technique that assesses whole-brain effective connectivity (EC) during resting-state functional magnetic resonance imaging (fMRI). We modelled data from two randomized, placebo-controlled, double-blind, cross-over trials, in which 45 participants were administered 100μg LSD and placebo in two resting-state fMRI sessions. We compared EC against whole-brain functional connectivity (FC) using classical statistics and machine learning methods. Multivariate analyses of EC parameters revealed widespread increases in interregional connectivity and reduced self-inhibition under LSD compared to placebo, with the notable exception of primarily decreased interreg...

&lt;p&gt;Soil erosion in Alpine grassland areas is an ecological threat caused by... more &lt;p&gt;Soil erosion in Alpine grassland areas is an ecological threat caused by the extreme topography, prevailing climate conditions and land-use practices but enhanced by climate change (e.g., heavy precipitation events, changing snow dynamics) in combination with changing land-use practices (e.g, more intensely used pastures). To increase our understanding of ongoing soil erosion processes in Alpine grasslands, there is a need to acquire detailed information on spatial extension and temporal trends.&lt;/p&gt;&lt;p&gt;In the past, we have successfully applied a semi-automatic method using an object-based image analysis (OBIA) framework with high-resolution aerial images (0.25-0.5m) and a digital terrain model (2m) to map erosion features in the Central Swiss Alps (Urseren Valley, Canton Uri, Switzerland). Degraded sites are classified according to the major erosion process (shallow landslides; sites with reduced vegetation cover affected by sheet erosion) or triggering factors (trampling by livestock; management effects) (Zweifel et al. 2019). We now aim to apply a deep learning (DL) model with the purpose of fast and efficient spatial upscaling(e.g., alpine-wide analysis). While OBIA yields high quality results, there are multiple constraints, such as labor-intensive steps and the requirement of expert knowledge, which make the method unsuitable for larger scale applications. The results of OBIA are used as a training dataset for our DL model. The DL approach uses fully-convolutional networks with the U-Net architecture and is capable of rapid segmentation and classification to identify areas with reduced vegetation cover and bare soil sites.&lt;/p&gt;&lt;p&gt;Results for the Urseren Valley (Canton Uri, Switzerland) show an increase in total area affected by soil degradation of 156 &amp;#177;18% during a 16-year observation period (2000-2016). A comparison of the two methods (OBIA and DL) shows that DL results for the Urseren Valley follow similar trends for the 16-year period and that the segmentations of eroded sites are in good agreement (IoU = 0.83). First transferability tests to other valleys not considered during training of the DL model are very promising, confirming that DL is a well-suited and efficient method for future projects to map and assess soil erosion processes in grassland areas at regional scales.&lt;/p&gt;&lt;p&gt;&amp;#160;&lt;/p&gt;&lt;p&gt;&lt;strong&gt;References&lt;/strong&gt;&lt;/p&gt;&lt;p&gt;L. Zweifel, K. Meusburger, and C. Alewell. Spatio-temporal pattern of soil degradation in a Swiss Alpine grassland catchment. Remote Sensing of Environment, 235, 2019.&lt;/p&gt;

Zeitschrift für Physik A Hadrons and Nuclei, 1997

Measurements of transient magnetic fields (TF) were performed for the first time in the amorphous... more Measurements of transient magnetic fields (TF) were performed for the first time in the amorphous compounds of Fe 80 B 20 and Fe 85 B 15 for 24 Mg(2 +), 28 Si(2 +), 48 Ti(2 +) and 56 Fe(2 +) probe ions employing light and heavy ion beams. The motivation for these experiments was to investigate whether ion beam induced attenuations of TF are substantially weaker in these materials than in crystalline Fe. This expectation was indeed satisfied. The attenuations observed were found to be smaller at least by a factor of 2.

Paranoid delusions or unfounded beliefs that others intend to deliberately cause harm are a frequ... more Paranoid delusions or unfounded beliefs that others intend to deliberately cause harm are a frequent and burdensome symptom in early psychosis, but their emergence and consolidation still remains opaque. Recent theories suggest that aberrant prediction errors lead to a brittle model of the world providing a breeding ground for delusions. Here, we employ a Bayesian approach to test for a more unstable model of the world and investigate the computational mechanisms underlying emerging paranoia.We modelled behaviour of 18 first-episode psychosis patients (FEP), 19 individuals at clinical high-risk for psychosis (CHR-P), and 19 healthy controls (HC) during an advice-taking task, designed to probe learning about others’ changing intentions. We formulated competing hypotheses comparing the standard Hierarchical Gaussian Filter (HGF), a Bayesian belief updating scheme, with a mean-reverting HGF to model an altered perception of volatility.There was a significant group-by-volatility interac...

arXiv (Cornell University), Apr 14, 2015

Clinical Neurophysiology, Aug 1, 2018

dementia in PD (PDD), it is likely that adding information about EEG frequency might increase pre... more dementia in PD (PDD), it is likely that adding information about EEG frequency might increase predictive accuracy of cognitive decline. Objective: The present study aims at (1) investigating whether quantitative EEG (qEEG) measures could identify differences between PD patients at high risk and PD patients at low risk of cognitive decline and at (2) analysing whether the inclusion of qEEG parameters improve predictive accuracy of cognitive decline within 3 years. Methods: In a total of 44 non-demented PD patients (disease duration: median = 2 years), a prediction algorithm for cognitive decline developed by Liu et al. (2017) was applied. At baseline, according to the defined cutoff score by Liu et al. (2017), n ¼ 23 patients were identified at high risk and n ¼ 21 patients at low risk of cognitive decline. Resting state EEG was recorded from 256 electrodes. Relative power spectra and median frequency (4-14 Hz) were compared between groups using ANOVA. Receiver-operator-characteris tic (ROC) was used to demonstrate prediction of global cognitive decline after 3 years (dementia vs. non dementia) using clinical risk score only and in combination with qEEG variable. Results: At baseline after correction for multiple comparisons, differences in global theta power and theta power in all brain regions (p < 0.05, most pronounced: temporal leftp < 0.004) and global alpha2 power and alpha2 power in temporo-posterior regions (p < 0.05) between groups were detected. After 3 years, 4 patients had progressed to dementia. Dementia was predicted by cognitive risk score with an area under the curve (AUC) of 71%. Prediction slightly increased when best predicting variable (theta temporal left) was added (AUC: 83%, p = 0.06). Conclusion: PD patients at high risk of cognitive decline are characterized by pronounced slowing as compared to PD patients at low risk. Even at a very short time span, cognitive risk scores are indicative of dementia in PD patients. Adding information about qEEG enhances prediction. Combined marker (qEEG and clinicalonly risk score) may help to improve prediction of cognitive decline in PWD patients.

Brain communications, 2020

Parkinson's disease is a neurodegenerative disorder requiring motor signs for diagnosis, but show... more Parkinson's disease is a neurodegenerative disorder requiring motor signs for diagnosis, but showing more widespread pathological alterations from its beginning. Compared to age-matched healthy individuals, patients with Parkinson's disease bear a 6-fold lifetime risk of dementia. For individualized counselling and treatment, prognostic biomarkers for assessing future cognitive deterioration in early stages of Parkinson's disease are needed. In a case-control study, 42 cognitively normal patients with Parkinson's disease were compared with 24 healthy control participants matched for age, sex and education. Tsallis entropy and band power of the d, h, a, b and c-band were evaluated in baseline EEG at eyes-open and eyes-closed condition. As the h-band showed the most pronounced differences between Parkinson's disease and healthy control groups, further analysis focussed on this band. Tsallis entropy was then compared across groups with 16 psychological test scores at baseline and follow-ups at 6 months and 3 years. In group comparison, patients with Parkinson's disease showed lower Tsallis entropy than healthy control participants. Cognitive deterioration at 3 years was correlated with Tsallis entropy in the eyes-open condition (P < 0.00079), whereas correlation at 6 months was not yet significant. Tsallis entropy measured in the eyes-closed condition did not correlate with cognitive outcome. In conclusion, the lower the EEG entropy levels at baseline in the eyes-open condition, the higher the probability of cognitive decline over 3 years. This makes Tsallis entropy a candidate prognostic biomarker for dementia in Parkinson's disease. The ability of the cortex to execute complex functions underlies cognitive health, whereas cognitive decline might clinically appear when compensatory capacity is exhausted.

Scientific Reports, Mar 29, 2023

changes and longitudinal cognitive deterioration in PD 2,4. Previous research indicates that chan... more changes and longitudinal cognitive deterioration in PD 2,4. Previous research indicates that changes in power and signal complexity as well as reduced functional connectivity in the θ-frequency band (Theta) are risk factors for the development of cognitive decline in PD 5,11. Furthermore, another relevant requirement for the development of prognostic markers for cognitive decline in PD patients is the generalizability to newly diagnosed and mildly affected PD patients. The aim of this study was to apply a prospective method (QEEG-connectivity) to detect neurophysiological risk factors for cognitive decline in patients with PD. We tested the hypothesis that P PD scores discriminate between PD Patients and healthy controls, when measured by CPM (connectome-based predictive modeling).

Clinical Neurophysiology, Oct 1, 2019

This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Clinical Neurophysiology, May 1, 2018

Clinical Neurophysiology, Aug 1, 2019

Clinical Neurophysiology, Aug 1, 2018

Frontiers in Neuroscience, Aug 11, 2021

An individual's brain functional organization is unique and can reliably be observed using modali... more An individual's brain functional organization is unique and can reliably be observed using modalities such as functional magnetic resonance imaging (fMRI). Here we demonstrate that a quantification of the dynamics of functional connectivity (FC) as measured using electroencephalography (EEG) offers an alternative means of observing an individual's brain functional organization. Using data from both healthy individuals as well as from patients with Parkinson's disease (PD) (n = 103 healthy individuals, n = 57 PD patients), we show that "dynamic FC" (DFC) profiles can be used to identify individuals in a large group. Furthermore, we show that DFC profiles predict gender and exhibit characteristics shared both among individuals as well as between both hemispheres. Furthermore, DFC profile characteristics are frequency band specific, indicating that they reflect distinct processes in the brain. Our empirically derived method of DFC demonstrates the potential of studying the dynamics of the functional organization of the brain using EEG.

Clinical Neurophysiology, Oct 1, 2017

The vigilance model of affective disorders and ADHS postulate that unstable regulation of vigilan... more The vigilance model of affective disorders and ADHS postulate that unstable regulation of vigilance (''CNS arousal") is observed not only in overtired children, but also in patients with mania and ADHS. Moreover, sensation and novelty seeking, hyperactivity and impulsivity observed in such persons should be interpreted as an autoregulatory attempt to stabilise vigilance by creating a stimulus incentive environment. As in mania, also in ADHD several EEG-based studies indicate an unstable regulation of wakefulness. Using an EEG-based algorithm (Vigilance Algorithm Leipzig, VIGALL) to assess the transition from high wakefulness to drowsiness until sleep onset, paediatric ADHD as well as manic patients showed an unstable vigilance regulation with rapid declines to lower vigilance stages or sleep onset. We investigated whether the vigilance regulation in adult patients with ADHD is less stable than that of healthy controls by exploring the frequency of EEG-vigilance regulation patterns. Methods: Resting EEG recordings of unmedicated adult ADHD patients and healthy controls were analysed. The diagnosis was provided based on the DSM-IV criteria. EEG recordings of 15 min under quiet rest with eyes closed were performed. The computer-based Vigilance Algorithm Leipzig (VIGALL) was used to classify 1-s EEG segments into stages on the continuum ranging from full wakefulness to sleep onset. Results/conclusions: Patients with ADHD showed an unstable vigilance regulation and spent more time in the less vigilance stages compared to the healthy controls. The investigated vigilance regulation model in ADHD could establish new insights into the neurophysiology of ADHD in adulthood and should be the subject of further investigations. An additional pre-post-treatment investigation with view on the suitability of the vigilance regulation as a predictor for response after a treatment with psychostimulants appears also useful.

arXiv (Cornell University), Dec 2, 2018

Recordings of electrical brain activity carry information about a person's cognitive health. For ... more Recordings of electrical brain activity carry information about a person's cognitive health. For recording EEG signals, a very common setting is for a subject to be at rest with its eyes closed. Analysis of these recordings often involve a dimensionality reduction step in which electrodes are grouped into 10 or more regions (depending on the number of electrodes available). Then an average over each group is taken which serves as a feature in subsequent evaluation. Currently, the most prominent features used in clinical practice are based on spectral power densities. In our work we consider a simplified grouping of electrodes into two regions only. In addition to spectral features we introduce a secondary, non-redundant view on brain activity through the lens of Tsallis Entropy S q=2. We further take EEG measurements not only in an eyes closed (ec) but also in an eyes open (eo) state. For our cohort of healthy controls (HC) and individuals suffering from Parkinson's disease (PD), the question we are asking is the following: How well can one discriminate between HC and PD within this simplified, binary grouping? This question is motivated by the commercial availability of inexpensive and easy to use portable EEG devices. If enough information is retained in this binary grouping, then such simple devices could potentially be used as personal monitoring tools, as standard screening tools by general practitioners or as digital biomarkers for easy long term monitoring during neurological studies.

arXiv (Cornell University), Apr 14, 2022

Considering smooth mappings from input vectors to continuous targets, our goal is to characterise... more Considering smooth mappings from input vectors to continuous targets, our goal is to characterise subspaces of the input domain, which are invariant under such mappings. Thus, we want to characterise manifolds implicitly defined by level sets. Specifically, this characterisation should be of a global parametric form, which is especially useful for different informed data exploration tasks, such as building grid-based approximations, sampling points along the level curves, or finding trajectories on the manifold. However, global parameterisations can only exist if the level sets are connected. For this purpose, we introduce a novel and flexible class of neural networks that generalise input-convex networks. These networks represent functions that are guaranteed to have connected level sets forming smooth manifolds on the input space. We further show that global parameterisations of these level sets can be always found efficiently. Lastly, we demonstrate that our novel technique for characterising invariances is a powerful generative data exploration tool in real-world applications, such as computational chemistry. Preprint. Under review.

Machine Learning, Jul 17, 2015

bioRxiv (Cold Spring Harbor Laboratory), Nov 1, 2022

Frontiers in Psychology

Psychedelics have emerged as promising candidate treatments for various psychiatric conditions, a... more Psychedelics have emerged as promising candidate treatments for various psychiatric conditions, and given their clinical potential, there is a need to identify biomarkers that underlie their effects. Here, we investigate the neural mechanisms of lysergic acid diethylamide (LSD) using regression dynamic causal modelling (rDCM), a novel technique that assesses whole-brain effective connectivity (EC) during resting-state functional magnetic resonance imaging (fMRI). We modelled data from two randomized, placebo-controlled, double-blind, cross-over trials, in which 45 participants were administered 100μg LSD and placebo in two resting-state fMRI sessions. We compared EC against whole-brain functional connectivity (FC) using classical statistics and machine learning methods. Multivariate analyses of EC parameters revealed widespread increases in interregional connectivity and reduced self-inhibition under LSD compared to placebo, with the notable exception of primarily decreased interreg...

Zeitschrift für Physik A Hadrons and Nuclei, 1997

arXiv (Cornell University), Apr 14, 2015

Clinical Neurophysiology, Aug 1, 2018

Brain communications, 2020

Scientific Reports, Mar 29, 2023

Clinical Neurophysiology, Oct 1, 2019

Clinical Neurophysiology, May 1, 2018

Clinical Neurophysiology, Aug 1, 2019

Clinical Neurophysiology, Aug 1, 2018

Frontiers in Neuroscience, Aug 11, 2021

Clinical Neurophysiology, Oct 1, 2017

arXiv (Cornell University), Dec 2, 2018

arXiv (Cornell University), Apr 14, 2022