Machine learning-based systems and methods for breath monitoring and assistance of a patient

A system comprising:

• one or more processors;
• and
• at least one memory storing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to:
• receive breathing pattern sensory data generated based at least in part on output of a breathing sensor monitoring a breathing of a monitored individual;
• generate breathing waveform data reflecting a breathing cycle of the monitored individual comprising an actual inspiration portion and an actual expiration portion, based at least in part on the breathing pattern sensory data for the monitored individual;
• determine a splinting occurrence reflected within the breathing waveform data, wherein:
• (i) the splinting occurrence is defined by a shortened inspiration portion of the breathing cycle relative to an expected inspiration portion of an expected breathing waveform for the monitored individual, and
• (ii) the shortened inspiration portion of the breathing cycle is determined based on a difference measure between (a) a measured time between an actual start of the actual inspiration portion and an actual peak of the actual inspiration portion and (b) an expected time between an expected start of the expected inspiration portion and an expected peak of the expected inspiration portion;
• in response to the splinting occurrence, map a stimulation schedule to the breathing waveform data, wherein the stimulation schedule defines a plurality of stimulation triggers reflected within the breathing waveform data and detectable within the breathing pattern sensory data for stimulating nerves of the monitored individual;
• and
• in response to detecting a stimulation trigger of the plurality of stimulation triggers within the breathing pattern sensory data, cause a stimulator configured to be in contact with the monitored individual to emit a stimulation signal to the monitored individual, wherein the stimulation signal is characterized by stimulation parameters.

One or more non-transitory computer-readable storage media including instructions that, when executed by one or more processors, cause the one or more processors to:

• receive breathing pattern sensory data generated based at least in part on output of a breathing sensor monitoring a breathing of a monitored individual;
• generate breathing waveform data reflecting a breathing cycle of the monitored individual comprising an actual inspiration portion and an actual expiration portion, based at least in part on the breathing pattern sensory data for the monitored individual;
• determine a splinting occurrence reflected within the breathing waveform data, wherein:
• (i) the splinting occurrence is defined by a shortened inspiration portion of the breathing cycle relative to an expected inspiration portion of an expected breathing waveform for the monitored individual, and
• (ii) the shortened inspiration portion of the breathing cycle is determined based on a difference measure between (a) a measured time between an actual start of the actual inspiration portion and an actual peak of the actual inspiration portion and (b) an expected time between an expected start of the expected inspiration portion and an expected peak of the expected inspiration portion;
• in response to the splinting occurrence, map a stimulation schedule to the breathing waveform data, wherein the stimulation schedule defines a plurality of stimulation triggers reflected within the breathing waveform data and detectable within the breathing pattern sensory data for stimulating nerves of the monitored individual;
• and
• in response to detecting a stimulation trigger of the plurality of stimulation triggers within the breathing pattern sensory data, cause a stimulator configured to be in contact with the monitored individual to emit a stimulation signal to the monitored individual, wherein the stimulation signal is characterized by stimulation parameters.