Large-scale brain dynamics are characterized by repeating spatiotemporal connectivity patterns that reflect a range of putative different brain states that underlie the dynamic repertoire of brain functions. The role of transition between brain networks is poorly understood, and whether switching between these states is important for behavior has been little studied. Our aim was to model switching between functional brain networks using multilayer network methods and test for associations between model parameters and behavioral measures. We calculated time-resolved fMRI connectivity in 1,003 healthy human adults from the Human Connectome Project. The time-resolved fMRI connectivity data were used to generate a spatiotemporal multilayer modularity model enabling us to quantify network switching, which we define as the rate at which each brain region transits between different networks. We found (i) an inverse relationship between network switching and connectivity dynamics, where the latter was defined in terms of time-resolved fMRI connections with variance in time that significantly exceeded phase-randomized surrogate data; (ii) brain connectivity was lower during intervals of network switching; (iii) brain areas with frequent network switching had greater temporal complexity; (iv) brain areas with high network switching were located in association cortices; and (v) using cross-validated elastic net regression, network switching predicted intersubject variation in working memory performance, planning/reasoning, and amount of sleep. Our findings shed light on the importance of brain dynamics predicting task performance and amount of sleep. The ability to switch between network configurations thus appears to be a fundamental feature of optimal brain function.

Artificial intelligence is one of the most exciting methodological shifts in our era. It holds the potential to transform healthcare as we know it, to a system where humans and machines work together to provide better treatment for our patients. It is now clear that cutting edge artificial intelligence models in conjunction with high-quality clinical data will lead to improved prognostic and diagnostic models in neurological disease, facilitating expert-level clinical decision tools across healthcare settings. Despite the clinical promise of artificial intelligence, machine and deep-learning algorithms are not a one-size-fits-all solution for all types of clinical data and questions. In this article, we provide an overview of the core concepts of artificial intelligence, particularly contemporary deep-learning methods, to give clinician and neuroscience researchers an appreciation of how artificial intelligence can be harnessed to support clinical decisions. We clarify and emphasize the data quality and the human expertise needed to build robust clinical artificial intelligence models in neurology. As artificial intelligence is a rapidly evolving field, we take the opportunity to iterate important ethical principles to guide the field of medicine is it moves into an artificial intelligence enhanced future.

Magnetoencephalography with optically pumped magnometers (OPM‐MEG) is an emerging and novel, cost‐effective wearable system that can simultaneously record neuronal activity with high temporal resolution ("when" neuronal activity occurs) and spatial resolution ("where" neuronal activity occurs). This paper will first outline recent methodological advances in OPM‐MEG compared to conventional superconducting quantum interference device (SQUID)‐MEG before discussing how OPM‐MEG can become a valuable and noninvasive clinical support tool in epilepsy surgery evaluation. Although OPM‐MEG and SQUID‐MEG share similar data features, OPM‐MEG is a wearable design that fits children and adults, and it is also robust to head motion within a magnetically shielded room. This means that OPM‐MEG can potentially extend the application of MEG into the neurobiology of severe childhood epilepsies with intellectual disabilities (e.g., epileptic encephalopathies) without sedation. It is worth noting that most OPM‐MEG sensors are heated, which may become an issue with large OPM sensor arrays (OPM‐MEG currently has fewer sensors than SQUID‐MEG). Future implementation of triaxial sensors may alleviate the need for large OPM sensor arrays. OPM‐MEG designs allowing both awake and sleep recording are essential for potential long‐term epilepsy monitoring.

Approximate entropy (ApEn) and sample entropy (SampEn) are widely used for temporal complexity analysis of real-world phenomena. However, their relationship with the Hurst exponent as a measure of self-similarity is not widely studied. Additionally, ApEn and SampEn are susceptible to signal amplitude changes. A common practice for addressing this issue is to correct their input signal amplitude by its standard deviation. In this study, we first show, using simulations, that ApEn and SampEn are related to the Hurst exponent in their tolerance r and embedding dimension m parameters. We then propose a modification to ApEn and SampEn called range entropy or RangeEn. We show that RangeEn is more robust to nonstationary signal changes, and it has a more linear relationship with the Hurst exponent, compared to ApEn and SampEn. RangeEn is bounded in the tolerance r-plane between 0 (maximum entropy) and 1 (minimum entropy) and it has no need for signal amplitude correction. Finally, we demonstrate the clinical usefulness of signal entropy measures for characterisation of epileptic EEG data as a real-world example.

It has been hypothesized that resting state networks (RSNs), extracted from resting state functional magnetic resonance imaging (rsfMRI), likely display unique temporal complexity fingerprints, quantified by their multiscale entropy patterns (McDonough and Nashiro, 2014). This is a hypothesis with a potential capacity for developing digital biomarkers of normal brain function, as well as pathological brain dysfunction. Nevertheless, a limitation of McDonough and Nashiro (2014) was that rsfMRI data from only 20 healthy individuals was used for the analysis. To validate this hypothesis in a larger cohort, we used rsfMRI datasets of 987 healthy young adults from the Human Connectome Project (HCP), aged 22-35, each with four 14.4-min rsfMRI recordings and parcellated into 379 brain regions. We quantified multiscale entropy of rsfMRI time series averaged at different cortical and sub-cortical regions. We performed effect-size analysis on the data in 8 RSNs. Given that the morphology of multiscale entropy is affected by the choice of its tolerance parameter (r) and embedding dimension (m), we repeated the analyses at multiple values of r and m including the values used in McDonough and Nashiro (2014). Our results reinforced high temporal complexity in the default mode and frontoparietal networks. Lowest temporal complexity was observed in the subcortical areas and limbic system. We investigated the effect of temporal resolution (determined by the repetition time TR) after downsampling of rsfMRI time series at two rates. At a low temporal resolution, we observed increased entropy and variance across datasets. Test-retest analysis showed that findings were likely reproducible across individuals over four rsfMRI runs, especially when the tolerance parameter r is equal to 0.5. The results confirmed that the relationship between functional brain connectivity strengths and rsfMRI temporal complexity changes over time scales. Finally, a non-random correlation was observed between temporal complexity of RSNs and fluid intelligence suggesting that complex dynamics of the human brain is an important attribute of high-level brain function.