Embodied neurology: an integrative framework for neurological disorders

Abstract

From a systems biology perspective, the brain and spinal cord are interwoven with the body: they are ‘embodied’. Freund et al. propose an integrative framework based on biophysical models that aims to characterize neurological disorders and minimize their impact on patients by considering functional interactions between supra-spinal, spinal and peripheral regions simultaneously.

Keywords: biophysical models; dynamic causal modelling; multiscale interactions; neuroimaging; precision neurology.

From a systems biology perspective, the brain and spinal cord are interwoven with the body: they are ‘embodied’. Freund et al. propose an integrative framework based on biophysical models that aims to characterize neurological disorders and minimize their impact on patients by considering functional interactions between supra-spinal, spinal and peripheral regions simultaneously.

Figure 1

The extensive sequelae following a focal spinal cord lesion. Effects spanning the entire neuroaxis and periphery leading to spinal and cortical atrophy, paralysis, autonomic dysfunction and manifold functional impairments of the body (noticed as symptoms, signs and physical measures) are shown. To optimize functional recovery, treatments cannot be limited to restore the impaired two-way communication between the nervous system and the body but needs also to incorporate means to compensate for changes of the peripheral targets (joints, muscle fibre composition, osteoporosis, etc.).

Figure 2

Integrating multiscale interactions into biophysical models (A) Dynamic causal modelling of neuroimaging data can be used for neuronal system identification to assess distributed changes at several spatial scales across the nervous system. This example presents a very simple model of how the distant effects of a focal spinal lesion on interactions among cortical areas can be modelled. The figure depicts a minimal system involving the primary motor (M1) and primary sensory (S1) cortices as well as cervical (CE) and lumbar (LE) enlargements of the spinal cord. In dynamic causal modelling, this system is described as a weighted, directed graph, where nodes represent regional neuronal population activity (which cannot be observed directly). These ‘hidden neuronal states’ influence each other through directed synaptic connections (effective connectivity, quantified by coupling parameters a₁₁…a₄₄) and may be additionally influenced by external experimental manipulations u, such as sensory stimuli, motor commands, or central and peripheral treatments (B), with parameters u. These mechanisms can be described as a set of ordinary differential equations (Equation 1). Note the directionality of the graph: M1 directly affects spinal cord components due to descending neuronal tracts, while influences in the reverse direction are relayed via S1. The experimental measurement y obtained below and above the lesion is predicted by an observation equation (Equation 2) that maps the hidden neuronal states to observations (blood oxygen level-dependant functional MRI in this case). A model like the one shown above enables one to obtain quantitative indices of cortical plasticity (changes in effective connectivity) in response to a distal spinal cord lesion. These indices not only reveal mechanisms underlying supra-spinal pathology, but might also serve useful as predictors for clinical variables (Brodersen et al. 2011). (B) For example a complete lesion at the thoracic level results in the complete loss of effective connectivity of efferent and afferent information flow (a₄₁ = 0, a₂₄ = 0), but a restorative treatment aiming at the repair of the spinal cord is expected to increase the coupling between these regions (blue asterisk) and beyond (thick lines).