Toward automated interpretation of electromyography for intraoperative neurophysiological monitoring using machine learning

Intraoperative neurophysiological monitoring is used during neurosurgery to assess the functional integrity of nerves and alert the surgeon to prevent damage. In current clinical IONM, the neurophysiological data are interpreted in real time by a specialist. This processing by humans is subjective and introduces inter-subject variability into the process. In order to standardize this process and reduce cognitive load on human users, this paper presents a preliminary investigation of the use of machine learning techniques for automated detection of nerve irritation during neurosurgery.