Peripheral Nerve Activation Evokes Machine-Learnable Signals in the Dorsal Column Nuclei

The brainstem dorsal column nuclei (DCN) are essential to inform the brain of tactile and proprioceptive events experienced by the body. However, little is known about how ascending somatosensory information is represented in the DCN. Our objective was to investigate the usefulness of high-frequency and low-frequency DCN signal features in predicting the nerve from which signals were evoked. We also aimed to explore the robustness of DCN signal features and map their relative information content across the brainstem surface. DCN surface potentials were recorded from urethane-anaesthetised Wistar rats during sural and peroneal nerve electrical stimulation. Five salient signal features were extracted from each recording electrode of a seven-electrode array. We used a machine learning approach to quantify and rank information content contained within DCN surface-potential signals following peripheral nerve activation. Machine-learning of signal feature and electrode position combinations was quantified to determine a hierarchy of information importance for resolving the peripheral origin of nerve activation. A supervised back-propagation artificial neural network could predict the nerve from which a response was evoked with up to 96.8 ± 0.8% accuracy. Guided by machine-learnability, we maintained high prediction accuracy after reducing artificial neural network algorithm inputs from 35 (5 signal features from 7 electrodes) to 6 (4 signal features from 2 electrodes). When the number of input features were reduced, the best performing input combinations included high- and low-frequency features. Machine-learnability also revealed that signals recorded from the same midline electrode can be accurately classified when evoked from bilateral nerve pairs, suggesting DCN surface activity asymmetry. Here we demonstrate a novel method for mapping the information content of signal patterns across the DCN surface and show that DCN signal features are robust across a population. Finally, we also show that the DCN is functionally asymmetrically organised, which challenges our current understanding of somatotopic symmetry across the midline at sub-cortical levels.