Neuromonitoring data analysis apparatuses and methods
Aspects of embodiments pertain to systems configured to perform neuromonitoring data analysis, by employing the following: receiving patient data comprising data that are descriptive of at least one physical stimulus applied to a mammalian subject for responsively generating at least one signal in a plurality of neural structures of the subject's nervous system; and sensor data descriptive of at least one neurophysiological response signal generated in response the applied physical stimulus. The systems are further configured to determine, based on the received patient data descriptive of the at least one physical stimulus and the generated response signal, at least one characteristic with respect to at least one of the plurality of neural structures of the patient.
1 . A neuromonitoring data analysis apparatus configured to monitor a nervous system of a subject, the apparatus comprising a processor executing a machine learning model having a plurality of levels of hierarchically arranged machine learning sub-models configured for:
(a) analyzing each of a plurality of neurophysiological signals generated by at least two channels associated with at least one neural structure in response to application of a plurality of physical stimuli to the subject;
(b) identifying at least one neurophysiological response signal of said plurality of neurophysiological response signals indicative of injury in said at least one neural structure.
2 . The apparatus of claim 1 , wherein said at least two channels are associated with at least two neural structures.
3 . The apparatus of claim 1 , wherein said plurality of neurophysiological response signals are generated in response to simultaneous application of physical stimuli.
4 . The apparatus of claim 1 , wherein (b) includes distinguishing between a first anomalous event relating to injury of said at least one neural structure and a second anomalous event not relating to injury of at least one neural structure.
5 . The apparatus of claim 4 , wherein said second anomalous event relates to a systemic factor.
6 . The apparatus of claim 5 , wherein said systemic factor includes at least one from the group consisting of patient anesthesia, blood pressure, patient position and patient posture.
7 . The apparatus of claim 1 , wherein (b) includes comparing said plurality of neurophysiological response signals against corresponding baseline signals.
8 . The apparatus of claim 1 , wherein said processor is further configured for analyzing patient data including at least one from the group consisting of demographic data, anesthesia data, physiological data, surgical data, baseline motor evoked potential signal data, baseline EMG signal data, baseline EEG signal data, baseline somatosensory evoked potential signal data and reflex data.
9 . The apparatus of claim 1 , wherein a first level of said machine learning model is configured to associate each of said plurality of neurophysiological response signals to a specific signal modality and produce a plurality of signal modality outputs distinguishing between normal and abnormal activity.
10 . The apparatus of claim 9 , wherein a second level of said machine learning model is configured to analyze each signal modality output to provide an analysis output descriptive of said signal modality.
11 . The apparatus of claim 10 , wherein said second level is further configured to detect an occurrence of patterns of changes in aggregated signals of each signal modality.
12 . The apparatus of claim 10 , wherein a third level of said machine learning model interprets said analysis output as a clinical interpretation of each of said plurality of neurophysiological response signals.
13 . The apparatus of claim 9 , wherein each of said plurality of neurophysiological response signals is processed for feature extraction indicative of said specific signal modality.
14 . The apparatus of claim 13 , wherein said feature is of an MEP signal, an SSEP signal.
15 . The apparatus of claim 1 , wherein said processor configured for analyzing at least one non-stimulated neurophysiological signal.
16 . The apparatus of claim 15 , wherein said at least one non-stimulated neurophysiological signal is an EEG signal or an EMG signal.
17 . The apparatus of claim 1 , wherein (a) also takes into consideration data descriptive of said plurality of physical stimuli.