Predictive Complexity Based Diagnostics of Bipolar Disorder
We present and validate biomarkers able to differentiate between pathogenic processes (manic, mixed, depressed episode) and the euthymic phase in Bipolar Disorder with the aim to detect responses to therapeutical intervention(s) of patients using non-disruptive sensory wearables resulting in improved conditions of patients due to prediction of manic states occurrence. We strive to objectively differentiate the phases of bipolar disorder in order to detect therapeutical response or relapse and to identify bipolar disorder subtype(s). The “predictive” adjective in the title is meant to indicate the possibility to monitor fine changes during treatment yielding a personalized approaches to Bipolar Disorder. The predictive tool allows to treat patients early in the episode(s) resulting in lesser functional impact on patients, and to avoid some side-effects of Bipolar Disorder.
Not yet available
Khazaal Y, Elowe J, Kloucek P, Preisig M, Tadri M, Vandeleur C, Vandenberghe F, Verloo H, Ros T, Von Guntenb A. Psychiatrie [Psychiatry]. Rev Med Suisse. 2021 Jan 13;17(720-1):85-89. French. PMID: 33443837. (2021)
The Covid-19 pandemic has a major impact on psychiatry by its social consequences and possible direct effect of certain forms of Covid-19 on mental health. During this crisis, the accessibility of technology meets a state of necessity, which has propelled tele-psychiatry from the shadows into the light. The contribution of several technologies (i.e. virtual reality, actigraphy, computational psychiatry) combining clinical data and neuroscience underlines the great neurobehavioral variability even within the same diagnostic category, calling for greater precision in therapeutic offers as suggested e.g. by developments in neuro-feedback. The place of intranasal esketamin in the panoply of antidepressant drug treatments for resistant depression has not yet been defined.
La pandémie de Covid-19 bouleverse la psychiatrie par ses conséquences sociales et par de possibles séquelles psychiatriques. La crise actuelle révèle l’accessibilité de technologies digitales telles que la télépsychiatrie. Des technologies comme la réalité virtuelle, l’actigraphie, la psychiatrie computationnelle combinées aux données cliniques et aux neurosciences révèlent une importante variabilité neurocomportementale même au sein d’une catégorie diagnostique donnée, invitant à une plus grande précision des traitements comme suggéré par les recherches en neurofeedback. La place de l’eskétamine intranasale dans la panoplie thérapeutique médicamenteuse de la dépression résistante doit encore être définie.
The Configuration Energy of Social Organization
Petr Kloucek and Armin von Gunten, (2021)
Multi-scale theory approach to modeling of social organization based on surrogate measures of human vital signes multi-channel sensors is introduced. The approach is based on implementation of complexity coarse-graining of sensory time-series using the Hurst exponent. The notion of Congruence Energy and Entropy forming Configuration Energy of Social Organization is presented. The social attraction/repulsion inter-subject forces are described. Examples of applications of the introduced theory are presented using synthetic data generated by Brownian motion with different self-similarities.
Not yet available
The geometric approach to human stress based on stress-related surrogate measures
Petr Kloucek and Armin von Gunten, (2021)
PLoS ONE 16(1), Copyright: © 2021 Kloucek, von Gunten. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Data Availability Statement: All relevant data are within the manuscript and its Supporting information files: .
We present a predictive Geometric Stress Index (pGSI) and its relation to behavioural Entropy. It is a measure of the complexity of an organism’s reactivity to stressors yielding patterns based on different behavioural and physiological variables selected as Surrogate Markers of Stress (SMS). We present a relationship between pGSI and $b\E$ in terms of a power law model. This nonlinear relationship describes congruences in complexity derived from analyses of observable and measurable SMS based patterns interpreted as stress. The adjective geometric refers to subdivision(s) of the domain derived from two SMS (heart rate variability and steps frequency) with respect to a positive/negative binary perceptron based on a third SMS (blood oxygenation). The presented power law allows for both quantitative and qualitative evaluations of the consequences of stress measured by pGSI. In particular, we show that elevated stress levels in terms of pGSI leads to a decrease of the Entropy of the blood oxygenation, measured by peripheral blood oxygenation SpO2 as a model of SMS .
Modeling Training Adaptation in Swimming Using Artificial Neural Network Geometric Optimization
J. Currard, P. Kloucek, B. Gojanovic (2020)
MDPI/Sports 8,8, Copyright © 2020 by authors and MDPI
This study aims to model training adaptation using Artificial Neural Network (ANN) geometric optimisation. Over 26 weeks, 38 swimmers recorded their training and recovery data on a web platform. Based on these data, ANN geometric optimisation was used to model and graphically separate adaptation from maladaptation (to training). Geometric Activity Performance Index (GAPI), defined as the ratio of the adaptation to the maladaptation area, was introduced. The techniques of jittering and ensemble modeling were used to reduce overfitting of the model. Correlation (Spearman rank) and independence, Blomqvist, tests were run between GAPI and performance measures to check the relevance of the collected parameters. Thirteen out of 38 swimmers met the prerequisites for the analysis and were included in the modeling. The GAPI based on external load (distance) and internal load (session-Rating of Perceived Exertion) showed the strongest correlation with performance measures. ANN geometric optimisation seems to be a promising technique to model training adaptation and GAPI could be an interesting numerical surrogate to track during a season.
The Compound Spectral Indices of Human Stress
Petr Kloucek, Armin von Gunten, (2018)
Applied Mathematics, 9, 1378-1394. Copyright © 2018 by authors and Scientific Research Publishing Inc.
Temporally fine-grained and objective measures of mental states or their surrogate states are desperately needed in clinical psychiatry. Stress, both acute and especially chronic stress, is an important mental and physiological state observed in many mental disorders. It is a potential precipitant of acute psychiatric decompensation, be they anxious, affective, psychotic, or behavioural. Thus, being able to objectively follow stress or its surrogate parameters over time in a clinician-friendly way would help predict and prevent decompensation and monitor subsequent treatment success. Thus, we introduce the Compound Spectral Stress Indices (CSSI) that are derived from sensing data of various physiological and physiological and behavioural parameters we use as surrogate stress measures. To obtain the CSSI we use a hierarchical approach provided by adaptability, congruency and derived stress coefficient matrices. Adaptability is defined as a macroscopic characterization of physiological and physiological and behavioural performance constructed as a product of the total variation of time-segmented complexity indices multiplied by the frequency of the time-varying distribution of complexity indices of the measured physiological or physiological and behavioural parameters, where complexity is expressed in terms of the Hurst exponent. Congruency is expressed by a constant characterizing a demand-resource balance and it is then expressed in the form of a stress coefficient matrix. The CSSI is given by the spectral distance of the stress coefficient matrices from the ideal demand-resource matrix.
On the Possibility of Identifying Human Subjects Using Behavioral Complexity Analyses
Petr Kloucek, Armin von Gunten, (2016)
Quantitative Biology 2016, 4(4): 261–269
The approach is based on capturing behavioural time-series that can be characterized by a fractional dimension using non-invasive longer-time acquisitions of heart rate, perfusion, blood oxygenation, skin temperature, relative movement and steps frequency. The geometry based approach consists in the analysis of the area and centroid of convex hulls encapsulating the behavioural data represented in Euclidian index spaces based on the scaling properties of the self-similar normally distributed behavioural time-series of the above mentioned quantities. An example demonstrating the presented approach of behavioural fingerprinting is provided using sensory data of eight healthy human subjects based on approximately fifteen hours of data acquisition. Our results show that healthy subjects can be factorized to different similarity groups based on a particular choice of a convex hull in the corresponding Euclidian space. One of the results indicates that healthy subjects share only a small part of the convex hull pertaining to a highly trained individual from the geometric comparison point of view. Similarly, the presented pair-wise individual geometric similarity measure indicates large differences among the subjects suggesting the possibility of neuro-finger-printing.
The Compound Indexing of Human Self-Similar Behavioral Patterns,
Petr Kloucek, Pavel Zakharov and Armin von Gunten, (2016)
J. Applied Mathematics, 7, 2212-2228. Copyright © 2016 by authors and Scientific Research Publishing Inc. This work is licensed under the Creative Commons Attribution International License (CC BY 4.0).
Applications of a constitutive framework providing compound complexity analysis and indexing of coarse-grained self-similar time series representing behavioural data is presented. A notion of behavioural entropy and hysteresis is introduced as two different forms of compound measures. These measures provide clinically applicable complexity analysis of behavioural patterns yielding scalar characterization of time-varying behaviours registered over an extended period of time. The behavioural data are obtained using body attached sensors providing non-invasive readings of heart rate, skin blood perfusion, blood oxygenation, skin temperature, movement and steps frequency. The results using compound measures of behavioural patterns of fifteen healthy individuals are presented. The application of the compound measures is shown to correlate with complexity analysis. The correlation is demonstrated using two healthy subjects compared against a control group. This indicates a possibility to use these measures in place of fractional dimensions to provide a finer characterization of behavioural patterns observed using sensory data acquired over a long period of time.