A feasibility study on AI-controlled closed-loop electrical stimulation implants

Miniaturized electrical stimulation (ES) implants show great promise in practice, but their real-time control by means of biophysical mechanistic algorithms is not feasible due to computational complexity. Here, we study the feasibility of more computationally efficient machine learning methods to control ES implants. For this, we estimate the normalized twitch force of the stimulated extensor digitorum longus muscle on n = 11 Wistar rats with intra- and cross-subject calibration. After 2000 training stimulations, we reach a mean absolute error of 0.03 in an intra-subject setting and 0.2 in a cross-subject setting with a random forest regressor. To the best of our knowledge, this work is the first experiment showing the feasibility of AI to simulate complex ES mechanistic models. However, the results of cross-subject training motivate more research on error reduction methods for this setting.

Automated summary

Miniaturized electrical stimulation (ES) implants have great potential, but real-time control using biophysical mechanistic algorithms is computationally complex. This study explores the feasibility of using computationally efficient machine learning methods to control ES implants. By calibrating the stimulated muscle on 11 rats, the study achieves a mean absolute error of 0.03 in an intra-subject setting and 0.2 in a cross-subject setting using a random forest regressor. This work is the first to demonstrate the feasibility of using AI to simulate complex ES mechanistic models, but more research is needed to reduce errors in cross-subject training.