Improved stability and interpretability of motor modules computed with an autoencoder

Motor module analysis is an important tool in the study of movement, particularly in people with impaired neural control. The most common method for computing motor modules is non-negative matrix factorization (NMF), which identifies a matrix of motor modules and their corresponding time-series activity from electromyography data. NMF has several limitations, including dependence of the muscle weightings on the number of modules selected. Approaches for selecting the number of modules vary between studies, making it difficult to compare and reproduce results. Some metrics of motor control complexity use the variance accounted for when extracting a single motor module (VAF₁), yet that module's structure offers little biomechanical interpretability. In this work, we present a method for computing motor modules using an autoencoder, a neural network architecture that can find latent representations of data. Using a single-layer autoencoder, we extracted motor modules from data in able-bodied individuals and poststroke individuals. The structure of autoencoder-computed modules was significantly less sensitive to the selected number of modules. With the autoencoder-computed modules, increasing the number of modules added new information, instead of splitting previous modules. Autoencoder-computed modules, especially at low module counts, had more distinct and interpretable biomechanical functions. Lastly, the autoencoder-computed modules are consistent with previous NMF studies in persons with stroke, which found fewer modules needed to explain the muscle activity of paretic limbs. Our autoencoder-based method offers a new approach for computing motor modules, with advantages of better stability in module structure across module counts, and a more biomechanically relevant interpretation of VAF₁.NEW & NOTEWORTHY This work presents an approach for computing motor modules using an autoencoder and comprehensively compares the stability of motor module structure, functional significance at low module counts, and interpretation of VAF₁ to the current state of the art. The AE-computed module structures were more stable at different module counts. The AE has the potential to improve confidence in module structure and make analysis less dependent on the specific number of modules selected.