Iead Rezek

Stochastic complexity measures for physiological signal analysis

Traditional feature extraction methods describe signals in terms of amplitude and frequency. This paper takes a paradigm shift and investigates four stochastic-complexity features. Their advantages are demonstrated on synthetic and physiological signals; the latter recorded during periods of Cheyne-Stokes respiration, anesthesia, sleep, and motor-cortex investigation.

Fast transient networks in spontaneous human brain activity.

To provide an effective substrate for cognitive processes, functional brain networks should be able to reorganize and coordinate on a sub-second temporal scale. We used magnetoencephalography recordings of spontaneous activity to characterize whole-brain functional connectivity dynamics at high temporal resolution. Using a novel approach that identifies the points in time at which unique patterns of activity recur, we reveal transient (100–200 ms) brain states with spatial topographies similar to those of well-known resting state networks. By assessing temporal changes in the occurrence of these states, we demonstrate that within-network functional connectivity is underpinned by coordinated neuronal dynamics that fluctuate much more rapidly than has previously been shown. We further evaluate cross-network interactions, and show that anticorrelation between the default mode network and parietal regions of the dorsal attention network is consistent with an inability of the system to transition directly between two transient brain states. DOI: http://dx.doi.org/10.7554/eLife.01867.001

Signal quality indices and data fusion for determining clinical acceptability of electrocardiograms

A completely automated algorithm to detect poor-quality electrocardiograms (ECGs) is described. The algorithm is based on both novel and previously published signal quality metrics, originally designed for intensive care monitoring. The algorithms have been adapted for use on short (5-10 s) single- and multi-lead ECGs. The metrics quantify spectral energy distribution, higher order moments and inter-channel and inter-algorithm agreement. Seven metrics were calculated for each channel (84 features in all) and presented to either a multi-layer perceptron artificial neural network or a support vector machine (SVM) for training on a multiple-annotator labelled and adjudicated training dataset. A single-lead version of the algorithm was also developed in a similar manner. Data were drawn from the PhysioNet Challenge 2011 dataset where binary labels were available, on 1500 12-lead ECGs indicating whether the entire recording was acceptable or unacceptable for clinical interpretation. We re-annotated all the leads in both the training set (1000 labelled ECGs) and test dataset (500 12-lead ECGs where labels were not publicly available) using two independent annotators, and a third for adjudication of differences. We found that low-quality data accounted for only 16% of the ECG leads. To balance the classes (between high and low quality), we created extra noisy data samples by adding noise from PhysioNets noise stress test database to some of the clean 12-lead ECGs. No data were shared between training and test sets. A classification accuracy of 98% on the training data and 97% on the test data were achieved. Upon inspection, incorrectly classified data were found to be borderline cases which could be classified either way. If these cases were more consistently labelled, we expect our approach to achieve an accuracy closer to 100%.

Inferring social network structure in ecological systems from spatio- temporal data streams

We propose a methodology for extracting social network structure from spatio-temporal datasets that describe timestamped occurrences of individuals. Our approach identifies temporal regions of dense agent activity and links are drawn between individuals based on their co-occurrences across these ‘gathering events’. The statistical significance of these connections is then tested against an appropriate null model. Such a framework allows us to exploit the wealth of analytical and computational tools of network analysis in settings where the underlying connectivity pattern between interacting agents (commonly termed the adjacency matrix) is not given a priori. We perform experiments on two large-scale datasets (greater than 106 points) of great tit Parus major wild bird foraging records and illustrate the use of this approach by examining the temporal dynamics of pairing behaviour, a process that was previously very hard to observe. We show that established pair bonds are maintained continuously, whereas new pair bonds form at variable times before breeding, but are characterized by a rapid development of network proximity. The method proposed here is general, and can be applied to any system with information about the temporal co-occurrence of interacting agents.

Maximum certainty data partitioning

Abstract Problems in data analysis often require the unsupervised partitioning of a dataset into clusters. Many methods exist for such partitioning but most have the weakness of being model-based (most assuming hyper-ellipsoidal clusters) or computationally infeasible in anything more than a three-dimensional data space. We re-consider the notion of cluster analysis in information-theoretic terms and show that minimisation of partition entropy can be used to estimate the number and structure of probable data generators.

Temporal and spatial complexity measures for electroencephalogram based brain-computer interfacing

There has been much interest recently in the concept of using information from the motor cortex region of the brain, recorded using non-invasive scalp electrodes, to construct a crude interface with a computer. It is known that movements of the limbs, for example, are accompanied by desynchronisations and synchronisations within the scalp-recorded electroencephalogram (EEG). These event-related desynchronisations and synchronisations (ERD and ERS), however, appear to be present when volition to move a limb occurs, even when actual movement of the limb does not in fact take place. The determination and classification of the ERD/S offers many exciting possibilities for the control of peripheral devices via computer analysis. To date most effort has concentrated on the analysis of the changes in absolute frequency content of signals recorded from the motor cortex. The authors present results which tackle the issues of both the interpretation of changes in signals with time and across channels with simple methods which monitor the temporal and spatial ‘complexity’ of the data. Results are shown on synthetic and real data sets.

Understanding Heterogeneity in Clinical Cohorts Using Normative Models: Beyond Case-Control Studies

Background Despite many successes, the case-control approach is problematic in biomedical science. It introduces an artificial symmetry whereby all clinical groups (e.g., patients and control subjects) are assumed to be well defined, when biologically they are often highly heterogeneous. By definition, it also precludes inference over the validity of the diagnostic labels. In response, the National Institute of Mental Health Research Domain Criteria proposes to map relationships between symptom dimensions and broad behavioral and biological domains, cutting across diagnostic categories. However, to date, Research Domain Criteria have prompted few methods to meaningfully stratify clinical cohorts. Methods We introduce normative modeling for parsing heterogeneity in clinical cohorts, while allowing predictions at an individual subject level. This approach aims to map variation within the cohort and is distinct from, and complementary to, existing approaches that address heterogeneity by employing clustering techniques to fractionate cohorts. To demonstrate this approach, we mapped the relationship between trait impulsivity and reward-related brain activity in a large healthy cohort (N = 491). Results We identify participants who are outliers within this distribution and show that the degree of deviation (outlier magnitude) relates to specific attention-deficit/hyperactivity disorder symptoms (hyperactivity, but not inattention) on the basis of individualized patterns of abnormality. Conclusions Normative modeling provides a natural framework to study disorders at the individual participant level without dichotomizing the cohort. Instead, disease can be considered as an extreme of the normal range or as—possibly idiosyncratic—deviation from normal functioning. It also enables inferences over the degree to which behavioral variables, including diagnostic labels, map onto biology.

An automatic, continuous and probabilistic sleep stager based on a hidden markov model

We report about an automatic continuous sleep stager which is based on probabilistic principles employing Hidden Markov Models (HMM). Our sleep stager offers the advantage of being objective by not relying on human scorers, having much finer temporal resolution (one second instead of 30 seconds),and being based on solid probabilistic principles rather than a predefined set of rules (Rechtschaffen and Kales). Results obtained for nine whole night sleep recordings are reported.

Dynamic state allocation for MEG source reconstruction

Our understanding of the dynamics of neuronal activity in the human brain remains limited, due in part to a lack of adequate methods for reconstructing neuronal activity from noninvasive electrophysiological data. Here, we present a novel adaptive time-varying approach to source reconstruction that can be applied to magnetoencephalography (MEG) and electroencephalography (EEG) data. The method is underpinned by a Hidden Markov Model (HMM), which infers the points in time when particular states re-occur in the sensor space data. HMM inference finds short-lived states on the scale of 100 ms. Intriguingly, this is on the same timescale as EEG microstates. The resulting state time courses can be used to intelligently pool data over these distinct and short-lived periods in time. This is used to compute time-varying data covariance matrices for use in beamforming, resulting in a source reconstruction approach that can tune its spatial filtering properties to those required at different points in time. Proof of principle is demonstrated with simulated data, and we demonstrate improvements when the method is applied to MEG.

On similarities between inference in game theory and machine learning

In this paper, we elucidate the equivalence between inference in game theory and machine learning. Our aim in so doing is to establish an equivalent vocabulary between the two domains so as to facilitate developments at the intersection of both fields, and as proof of the usefulness of this approach, we use recent developments in each field to make useful improvements to the other. More specifically, we consider the analogies between smooth best responses in fictitious play and Bayesian inference methods. Initially, we use these insights to develop and demonstrate an improved algorithm for learning in games based on probabilistic moderation. That is, by integrating over the distribution of opponent strategies (a Bayesian approach within machine learning) rather than taking a simple empirical average (the approach used in standard fictitious play) we derive a novel moderated fictitious play algorithm and show that it is more likely than standard fictitious play to converge to a payoff-dominant but risk-dominated Nash equilibrium in a simple coordination game. Furthermore we consider the converse case, and show how insights from game theory can be used to derive two improved mean field variational learning algorithms. We first show that the standard update rule of mean field variational learning is analogous to a Cournot adjustment within game theory. By analogy with fictitious play, we then suggest an improved update rule, and show that this results in fictitious variational play, an improved mean field variational learning algorithm that exhibits better convergence in highly or strongly connected graphical models. Second, we use a recent advance in fictitious play, namely dynamic fictitious play, to derive a derivative action variational learning algorithm, that exhibits superior convergence properties on a canonical machine learning problem (clustering a mixture distribution).