The techniques of the disclosure describe example medical devices, systems, and methods for interleaving a plurality of low-frequency electrical stimulation pulse trains delivered by a plurality of sets of electrodes of an implantable medical device (IMD) to effectively deliver a combined high-frequency electrical pulse train to a target tissue area. In one example, each set of the plurality of sets of electrodes has a unique anode and cathode. In another example, a clinician adjusts the size or shape of the target tissue area receiving the combined high-frequency electrical pulse train by selecting different combinations of the plurality of sets of electrodes.

A neurostimulator is configured to activate a set of N electrodes, which are each adapted to stimulate at least a portion of a population of neurons when activated and applied in an invasive manner, at respective onset times T.sub.1 . . . T.sub.N throughout a cycle period T. N is an integer larger than two and the cycle period T is defined as a time period within which each of the N electrodes is activated exactly once. The onset times T.sub.1 . . . T.sub.N are not arranged substantially uniformly throughout the cycle period T.

Stimulation of neural activity in a nerve supplying the spleen, wherein the nerve is associated with a neurovascular bundle, can modulate pro- and anti-inflammatory molecules levels, thereby reducing inflammation and providing ways of treating inflammatory disorders. The invention provides improved ways of treating inflammatory disorders which minimize off-target effects.

Stimulation of neural activity in a nerve supplying the spleen, wherein the nerve is adjacent to the splenic artery at a position where the splenic artery is not in direct contact with the pancreas, can modulate pro- and anti-inflammatory molecules levels, thereby reducing inflammation and providing ways of treating disorders, such as disorders associated with inflammation. The invention provides improved ways of reducing inflammation with minimized off-target effects, in particular surgical trauma.

Information relevant to making clinical decisions for a patient is identified based on electrical activity records of the patient's brain and electrical activity records of other patients' brains. A deep learning algorithm is applied to an electrical activity record of the 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.

Simulation electrode assemblies for applying bilateral stimulation, for example stimulating both the left and right hypoglossal nerves of a patient in the treatment of sleep disordered breathing. In some methods, a stimulation electrode assembly is inserted through an incision at a side of the patient and implanted at a location extending across the patient's mid-line.

An example of a system for programming a neurostimulator may include a storage device and a user interface. The storage device may be configured to store waveform building blocks. The user interface may include a display screen, a user input device, and an interface control circuit. The interface control circuit may include a waveform composer configured to allow for composition of one of more building blocks and composition of a pattern of neurostimulation pulses using selected one or more waveform building blocks. The waveform composer may include a library controller and waveform building block editors. The library controller may be configured to display a library management area on the screen. The displayed library management area allows a user to manage the stored waveform building blocks. The waveform building block editors may each be configured to allow the user to compose a type of the waveform building blocks.

An example of a system for delivering neurostimulation using a stimulation device and controlling the delivery of the neurostimulation may include a programming control circuit and a stimulation control circuit. The programming control circuit may be configured to program the stimulation device for delivering the neurostimulation according to a pattern of neurostimulation pulses defined by one or more stimulation waveforms. The stimulation control circuit may be configured to determine the pattern of neurostimulation pulses with the one or more stimulation waveforms constrained by one or more thresholds, and may include threshold circuitry that may be configured to receive one or more known values of the one or more thresholds and to determine needed values of the one or more thresholds by executing an algorithm allowing for prediction of the needed values of the one or more thresholds based on the one or more known values.

Modulation of the neural activity of a nerve adjacent to the left gastro epiploic artery (LGEA) and/or a nerve adjacent to a short gastric artery (SGA) can modulate the neural activity of the sympathetic nerves that impact splenic function. This is useful for reducing inflammation and providing ways of treating inflammatory disorders.

Electrical stimulation of neural activity in the neural innervation of the spleen that is associated with neurovascular bundles provides a useful way to treat acute medical conditions, such as trauma, hemorrhaging, shock, acute respiratory distress syndrome (ARDS), severe respiratory distress syndrome (SARS), and coronavirus disease 19 (COVID-19).