Systems, devices, and methods for remote monitoring and managing of patients with chronic pain are discussed. A remote monitoring system comprises one or more sensors to sense physiological or functional information from the patient, a cloud-computing device communicatively coupled to the one or more sensors, and a remote device. The cloud-computing device receives patient data including physiological or functional information, and provides on-demand cloud-based services including storing the received patient data in a cloud storage, detecting a patient behavior, and generating a sensor operation recommendation based on the detected patient behavior. The remote device can access the cloud storage and the cloud-based services, and adjust operations of the one or more sensors in accordance with the sensor operation recommendation.

Systems, devices, and methods for remote monitoring and managing of patients with chronic pain are discussed. A remote monitoring system comprises a cloud-computing device and a remote device. The cloud-computing device receives patient data including physiological or functional information sensed by sensors, and provides on-demand cloud-based services including establishing a correspondence between one or more physiological or functional states and one or more pain levels, detecting patient physiological or functional state, predicting a pain level, detecting a patient behavior, generating a recommendation for adjusting sensor operations based on the patient behavior, and storing patient data and other information in a cloud storage. The remote device can access the cloud storage and the cloud-based services, provide the stored information to an authorized user or the patient, control an implantable device to initiate or adjust a neuromodulation therapy, or adjust sensor operations.

Systems, devices, and techniques are described for adjusting a sensing window for sensing a feature of an evoked compound action potential (ECAP). In one example, a medical device includes processing circuitry configured to determine a value of a stimulation parameter that at least partially defines an electrical stimulation pulse and select, based on the value of the stimulation parameter, a sensing window for detecting one or more features of a sensed evoked compound action potential (ECAP) signal elicited by the electrical stimulation pulse. The processing circuitry can also determine a value of each of the one or more features within the sensing window from the sensed ECAP signal and control, based on the value of each of the one or more features, subsequent electrical stimulation deliverable to a patient.

Embodiments of the disclosure are drawn to implantable stimulator with machine learning based classifier. An implantable system includes sensors which provide sensor information to an implantable unit. The implantable unit uses a classifier on the sensor information to select a stimulation procedure which is applied via a stimulation electrode. The classifier may be generated by a trained machine learning model. The classifier may be trained on an external unit which is not implanted in the subject. The classifier may be trained based on sensor information from the implanted sensors as well as symptom information.

Devices, systems and methods of neurostimulation for treating obstructive sleep apnea. The system is adapted to send an electrical signal from an implanted neurostimulator through a stimulation lead to a patient's nerve at an appropriate phase of the respiratory cycle based on input from a respiration sensing lead. External components are adapted for wireless communication with the neurostimulator. The neurostimulator is adapted to deliver therapeutic stimulation based on inputs.

Various embodiments concern delivering electrical stimulation to the brain at a plurality of different levels of a stimulation parameter and sensing a bioelectrical response of the brain to delivery of the electrical stimulation for each of the plurality of different levels of the stimulation parameter. A suppression window of the stimulation parameter can be identified as having a suppression threshold as a lower boundary and an after-discharge threshold as an upper boundary based on the sensed bioelectrical responses. A therapy level of the stimulation parameter can be set for therapy delivery based on the suppression window. The therapy level of the stimulation parameter may be set closer to the suppression threshold than the after-discharge threshold within the suppression window. Data for hippocampal stimulation demonstrating a suppression window is presented.

A system for mapping neuromuscular junctions for botulinum neurotoxin (BoNT) injections includes a stimulation electrode and an electromyography (EMG) sensor array including EMG sensors configured to be arranged about a person's face. Each EMG sensor detects muscle activity of a facial muscle of a facial muscle group. An EMG amplifier includes a plurality of input channels. Each input channel receives data of facial muscle activity in the facial muscle group from the EMG sensor array. A computer is in communication with the EMG amplifier. A processor of the computer identifies neuromuscular junctions (NMJs) of the facial muscle group based on the data of facial muscle activity received from the EMG sensor array. The plurality of NMJs are mapped with respect to the at least one facial muscle group of the body of the person. At least one NMJ site for BoNT injection is recommended by the computer.

Systems and methods are provided for electrical stimulation using electrical neurostimulators to treat neurological disorders. In exemplary implementations, the systems and methods effectuate selective sensory transmission block by spatially and temporally patterned multichannel, closed-loop electrical stimulation of neural tissue across the intervertebral foramina. The systems and methods optimize stimulation parameters according to the conduction velocity of afferents leading to effective neural transmission block. The systems and methods provide a dramatic improvement of selective transmission block, e.g., in a sub-population of unmyelinated C-fibers and slow-conducting Aδ fibers, by combining spatial, frequency and temporal parameters in the disclosed stimulation paradigm. An optimized start and termination of the stimulation may be implemented, as desired, thereby reducing overall energy consumption by reducing the stimulus strength during the maintenance phase of neural transmission block.

Systems and methods to detect seizures using analog circuitry. One example method generally includes obtaining, at a seizure detection system, one or more electroencephalogram (EEG) signals, detecting a plurality of features associated with each of the one or more EEG signals, generating a bitstream indicating a seizure probability associated with each feature of the plurality of features to yield a plurality of bitstreams indicating a plurality of seizure probabilities, and generating a seizure detection output based on the plurality of bitstreams indicating the plurality of seizure probabilities of the plurality of features.

A method and system are provided for determining a relation between stimulation settings for a brain stimulation probe and a corresponding V-field. The brain stimulation probe comprises multiple stimulation electrodes. The V-field is an electrical field in brain tissue surrounding the stimulation electrodes. The method comprises sequentially applying a test current to n stimulation electrodes, n being a number between 2 and the number of stimulation electrodes of the brain stimulation probe, for each test current at one of the n stimulation electrodes, measuring a resulting excitation voltage at m stimulation electrodes, m being a number between 2 and the number of stimulation electrodes of the brain stimulation probe, from the stimulation settings and the measured excitation voltages, deriving a coupling matrix, an element in the coupling matrix reflecting an amount of electrical impedance between two of the stimulation electrodes, and using the coupling matrix for determining the relation between the stimulation settings and the corresponding V-field.