Abstract: A neurostimulation system senses electrographic signals from the brain of a patient, extracts features from the electrographic signals, and when the extracted features satisfy certain criteria, detects a neurological event type. A mapping function relates the detected neurological event type to a stimulation parameter subspace and a default stimulation parameter set where the values of the stimulation parameters define an instance of stimulation therapy for the patient. The decision whether to implement a stimulation parameter subspace or a default stimulation parameter set may be informed by integrating other information about a state of the patient. A stimulation parameter subspace or stimulation parameter set may optimized by testing it against various thresholds until certain effectiveness criteria is satisfied. The neurological event type may be one of several electrographic seizure onset types.

Abstract: A sensor of an implantable medical device senses electrical activity of the brain. A data analyzer of the device monitors an electrographic signal corresponding to the electrical activity of the sensed brain signal, and processes the brain signal to obtain a measure of phase-amplitude coupling. For a selected portion of the electrographic signal, the data analyzer detects first features and second features of the electrographic signal. The first features represent oscillations in a low frequency range, while the second features represent oscillations in a frequency range higher than the low frequency range. For example, the low frequency range may correspond to theta frequency and the higher frequency range may correspond to gamma frequency. The data analyzer determines a measure of phase-amplitude coupling between oscillations in the low frequency range and oscillations in the higher frequency range based on occurrences of second features which coincide with first features.

Abstract: Information relevant to making clinical decisions for a subject patient is identified based on electrical activity records of the subject patient's brain and electrical activity records of other patients' brains. A deep learning algorithm is applied to an electrical activity record of the subject patient, i.e., an input record, and to a set of electrical activity records of other patients, i.e., a set of search records, to obtain an input feature vector of the patient and a set of search feature vectors, each including features extracted by the deep learning algorithm. A similarities algorithm is applied to the input feature vector and the set of search feature vectors to identify a subset of search records most like the input record. Clinical information associated with one or more search records in the identified subset of search records is extracted from a database and used to make decisions regarding the patient's neuromodulation therapies, or to make autonomous adjustments to therapies.

Abstract: A neurostimulation system senses electrographic signals from the brain of a patient, extracts features from the electrographic signals, and when the extracted features satisfy certain criteria, detects a neurological event type. A mapping function relates the detected neurological event type to a stimulation parameter subspace and a default stimulation parameter set where the values of the stimulation parameters define an instance of stimulation therapy for the patient. The decision whether to implement a stimulation parameter subspace or a default stimulation parameter set may be informed by integrating other information about a state of the patient. A stimulation parameter subspace or stimulation parameter set may optimized by testing it against various thresholds until certain effectiveness criteria is satisfied. The neurological event type may be one of several electrographic seizure onset types.

Abstract: A neurostimulation system senses electrographic signals from the brain of a patient, extracts features from the electrographic signals, and when the extracted features satisfy certain criteria, detects a neurological event type. A mapping function relates the detected neurological event type to a stimulation parameter subspace and a default stimulation parameter set where the values of the stimulation parameters define an instance of stimulation therapy for the patient. The decision whether to implement a stimulation parameter subspace or a default stimulation parameter set may be informed by integrating other information about a state of the patient. A stimulation parameter subspace or stimulation parameter set may optimized by testing it against various thresholds until certain effectiveness criteria is satisfied. The neurological event type may be one of several electrographic seizure onset types.

Abstract: A neurostimulation system senses electrographic signals from the brain of a patient, extracts features from the electrographic signals, and when the extracted features satisfy certain criteria, detects a neurological event type. A mapping function relates the detected neurological event type to a stimulation parameter subspace and a default stimulation parameter set where the values of the stimulation parameters define an instance of stimulation therapy for the patient. The decision whether to implement a stimulation parameter subspace or a default stimulation parameter set may be informed by integrating other information about a state of the patient. A stimulation parameter subspace or stimulation parameter set may optimized by testing it against various thresholds until certain effectiveness criteria is satisfied. The neurological event type may be one of several electrographic seizure onset types.