Electrical impedance guides electrode array in cochlear implantation using machine learning and robotic feeder.

Cochlear Implant provides an electronic substitute for hearing to severely or profoundly deaf patients. However, postoperative hearing outcomes significantly depend on the proper placement of electrode array (EA) into scala tympani (ST) during cochlear implant surgery. Due to limited intra-operative methods to access array placement, the objective of the current study was to evaluate the relationship between EA complex impedance and different insertion trajectories in a plastic ST model. A prototype system was designed to measure bipolar complex impedance (magnitude and phase) and its resistive and reactive components of electrodes. A 3-DoF actuation system was used as an insertion feeder. 137 insertions were performed from 3 different directions at a speed of 0.08 mm/s. Complex impedance data of 8 electrode pairs were sequentially recorded in each experiment. Machine learning algorithms were employed to classify both the full and partial insertion lengths. Support Vector Machine (SVM) gave the highest 97.1% accuracy for full insertion. When a real-time prediction was tested, Shallow Neural Network (SNN) model performed better than other algorithms using partial insertion data. The highest accuracy was found at 86.1% when 4 time samples and 2 apical electrode pairs were used. Direction prediction using partial data has the potential of online control of the insertion feeder for better EA placement. Accessing the position of the electrode array during the insertion has the potential to optimize its intraoperative placement that will result in improved hearing outcomes.