# Decoding phantom limb movements from intraneural recordings

## TL;DR

This study explores using neural signals from amputees' sciatic nerves to control prosthetics, showing that phantom limb movements can be decoded with advanced neural networks.

## Contribution

The study introduces a spiking neural network decoder that outperforms conventional methods for decoding phantom limb movements from intraneural signals.

## Key findings

- Multiunit activity associated with phantom knee, ankle, and toe movements was identified in transfemoral amputees.
- A spiking neural network decoder outperformed traditional methods in predicting attempted phantom limb movements.
- Motor and sensory maps showed minimal overlap, suggesting early segregation within the sciatic nerve.

## Abstract

Limb loss causes severe sensorimotor deficits and often necessitates prosthetic devices, particularly in lower-limb amputees. Although direct neural recording from residual nerves offers a biomimetic route for prosthetic control, low signal amplitudes and challenges in nerve interfacing have limited adoption. Intraneural multichannel electrodes provide a potential solution by enabling access to motor signals from muscles lost after amputation. Here, we report intraneural recordings from two transfemoral amputees using transversal intrafascicular multichannel electrodes implanted in distal branches of the sciatic nerve. We identified multiunit activity associated with volitional phantom movements of the knee, ankle, and toes, exhibiting joint- and direction-specific modulation distributed across electrodes. A Spiking Neural Network–based decoder outperformed conventional methods in predicting attempted movements, with further gains achieved by integrating intraneural and intermuscular signals. Motor and sensory maps showed minimal overlap, indicating early segregation within the sciatic nerve. These findings pave the way for bidirectional, neurally-controlled prosthetic systems.

Decoding motor intents from peripheral nerves remains challenging. The authors record intraneural sciatic activity in transfemoral amputees and use a spiking neural network to decode phantom leg movements. These findings support bidirectional, neurally-controlled prosthetic systems.