Patent Issued for Machine learning techniques for detecting splinting activity (USPTO 11864925): UnitedHealth Group Incorporated

2024 JAN 31 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- A patent by the inventors Boss, Gregory J. (Saginaw, MI, US), Gordon, Marilyn L. (Cherry Hill, NJ, US), Khatri, Komal (Cedar Park, TX, US), Muse, Jon Kevin (Thompsons Station, TN, US), filed on July 14, 2021, was published online on January 9, 2024, according to news reporting originating from Alexandria, Virginia, by NewsRx correspondents.

Patent number 11864925 is assigned to UnitedHealth Group Incorporated (Minnetonka, Minnesota, United States).

The following quote was obtained by the news editors from the background information supplied by the inventors: “Various embodiments of the present invention address technical challenges related to performing health-related detection. Various embodiments of the present invention disclose innovative techniques for efficiently and effectively performing health-related detection using various predictive data analysis techniques.”

In addition to the background information obtained for this patent, NewsRx journalists also obtained the inventors’ summary information for this patent: “In general, various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing splinting activity detection. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform splinting activity detection using at least one of splinting activity detection machine learning models, observed inspiration-expiration waveform pattern, and expected inspiration-expiration waveform patterns.

“In accordance with one aspect, a method is provided. In one embodiment, the method comprises: identifying observed breathing pattern sensory data for a monitored individual; determining an observed inspiration-expiration waveform pattern based at least in part on the observed breathing pattern sensory data; generating, by utilizing a splinting activity detection machine learning model, a predicted interruption score for the observed breathing pattern sensory data, wherein: (i) the splinting activity detection machine learning model is characterized by one or more expected inspiration-expiration waveform patterns, and (ii) the predicted interruption score is generated at least in part by comparing the observed inspiration-expiration waveform pattern with the one or more expected inspiration-expiration waveform patterns; and performing one or more prediction-based actions based at least in part on the predicted interruption score.

“In accordance with another aspect, a computer program product is provided. The computer program product may comprise at least one computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising executable portions configured to: identify observed breathing pattern sensory data for a monitored individual; determine an observed inspiration-expiration waveform pattern based at least in part on the observed breathing pattern sensory data; generate, by utilizing a splinting activity detection machine learning model, a predicted interruption score for the observed breathing pattern sensory data, wherein: (i) the splinting activity detection machine learning model is characterized by one or more expected inspiration-expiration waveform patterns, and (ii) the predicted interruption score is generated at least in part by comparing the observed inspiration-expiration waveform pattern with the one or more expected inspiration-expiration waveform patterns; and perform one or more prediction-based actions based at least in part on the predicted interruption score.

“In accordance with yet another aspect, an apparatus comprising at least one processor and at least one memory including computer program code is provided. In one embodiment, the at least one memory and the computer program code may be configured to, with the processor, cause the apparatus to: identify observed breathing pattern sensory data for a monitored individual; determine an observed inspiration-expiration waveform pattern based at least in part on the observed breathing pattern sensory data; generate, by utilizing a splinting activity detection machine learning model, a predicted interruption score for the observed breathing pattern sensory data, wherein: (i) the splinting activity detection machine learning model is characterized by one or more expected inspiration-expiration waveform patterns, and (ii) the predicted interruption score is generated at least in part by comparing the observed inspiration-expiration waveform pattern with the one or more expected inspiration-expiration waveform patterns; and perform one or more prediction-based actions based at least in part on the predicted interruption score.”

The claims supplied by the inventors are:

“1. A computer-implemented method comprising: identifying, by one or more processors, observed breathing pattern sensory data for a monitored individual; determining, by the one or more processors, an observed inspiration-expiration waveform pattern based at least in part on the observed breathing pattern sensory data; generating, by the one or more processors and utilizing a splinting activity detection machine learning model, a predicted interruption score for the observed breathing pattern sensory data, wherein: the predicted interruption score (i) is generated based at least in part on the observed inspiration-expiration waveform pattern and one or more expected inspiration-expiration waveform patterns, and (ii) represents a likelihood that the observed inspiration-expiration waveform pattern represents splinting activity; and initiating, by the one or more processors, the performance of one or more prediction-based actions based at least in part on the predicted interruption score.

“2. The computer-implemented method of claim 1, wherein the observed breathing pattern sensory data comprises a first sensory indicator of a diaphragm expansion for the monitored individual and a second sensory indicator of a diaphragm contraction for the monitored individual.

“3. The computer-implemented method of claim 1, wherein: the one or more expected inspiration-expiration waveform patterns comprise one or more activity severity subsets of the one or more expected inspiration-expiration waveform patterns; each activity severity subset is associated with an activity severity level of one or more activity severity levels; the one or more expected inspiration-expiration waveform patterns are selected from the one or more activity severity subsets based at least in part on a target activity severity level for the observed breathing pattern sensory data; and the target activity severity level is determined based at least in part on biometric data associated with the observed breathing pattern sensory data.

“4. The computer-implemented method of claim 1, wherein: each expected inspiration-expiration waveform pattern represents a substantially triangular pattern; each expected inspiration-expiration waveform pattern comprises a left half-triangular pattern that is associated with a detected inspiration pattern of the observed breathing pattern sensory data; and each expected inspiration-expiration waveform pattern comprises a right half-triangular pattern that is associated with a detected expiration pattern of the observed breathing pattern sensory data.

“5. The computer-implemented method of claim 1, wherein comparing the observed inspiration-expiration waveform pattern with a particular expected inspiration-expiration waveform pattern of the one or more expected inspiration-expiration waveform patterns comprises: determining, by the one or more processors, an observed peak amplitude of the observed inspiration-expiration waveform pattern; determining, by the one or more processors, an expected peak amplitude of the particular expected inspiration-expiration waveform pattern; and comparing, by the one or more processors, the observed peak amplitude and the expected peak amplitude to determine a difference measure for the observed inspiration-expiration waveform pattern and the particular expected inspiration-expiration waveform pattern.

“6. The computer-implemented method of claim 5, wherein the predicted interruption score is determined based at least in part on whether a lowest difference measure associated with the observed inspiration-expiration waveform pattern satisfies a difference measure threshold.

“7. The computer-implemented method of claim 1, wherein generating the predicted interruption score includes: detecting an interruption duration of a detected interruption in an upward progression of the observed inspiration-expiration waveform pattern; determining a splinting severity level based at least in part on the interruption duration; and determining the predicted interruption score based at least in part on the splinting severity level.

“8. The computer-implemented method of claim 1, wherein initiating the performance of the one or more prediction-based actions comprises: in response to determining that the predicted interruption score satisfies a predicted interruption score threshold, generating user interface data for one or more therapeutic notifications corresponding to the observed inspiration-expiration waveform pattern, wherein the one or more therapeutic notifications are configured to be displayed using a display device of a computing entity associated with the monitored individual.

“9. An apparatus comprising one or more processors and at least one memory including program code, the at least one memory and the program code configured to, with the one or more processors, cause the apparatus to at least: identify observed breathing pattern sensory data for a monitored individual; determine an observed inspiration-expiration waveform pattern based at least in part on the observed breathing pattern sensory data; generate, utilizing a splinting activity detection machine learning model, a predicted interruption score for the observed breathing pattern sensory data, wherein: the predicted interruption score (i) is generated based at least in part on the observed inspiration-expiration waveform pattern and one or more expected inspiration-expiration waveform patterns, and (ii) represents a likelihood that the observed inspiration-expiration waveform pattern represents splinting activity; and initiate the performance of one or more prediction-based actions based at least in part on the predicted interruption score.

“10. The apparatus of claim 9, wherein the observed breathing pattern sensory data comprises a first sensory indicator of a diaphragm expansion for the monitored individual and a second sensory indicator of a diaphragm contraction for the monitored individual.

“11. The apparatus of claim 9, wherein: the one or more expected inspiration-expiration waveform patterns comprise one or more activity severity subsets of the one or more expected inspiration-expiration waveform patterns; each activity severity subset is associated with an activity severity level of one or more activity severity levels; the one or more expected inspiration-expiration waveform patterns are selected from the one or more activity severity subsets based at least in part on a target activity severity level for the observed breathing pattern sensory data; and the target activity severity level is determined based at least in part on biometric data associated with the observed breathing pattern sensory data.

“12. The apparatus of claim 9, wherein: each expected inspiration-expiration waveform pattern represents a substantially triangular pattern; each expected inspiration-expiration waveform pattern comprises a left half-triangular pattern that is associated with a detected inspiration pattern of the observed breathing pattern sensory data; and each expected inspiration-expiration waveform pattern comprises a right half-triangular pattern that is associated with a detected expiration pattern of the observed breathing pattern sensory data.

“13. The apparatus of claim 9, wherein comparing the observed inspiration-expiration waveform pattern with a particular expected inspiration-expiration waveform pattern of the one or more expected inspiration-expiration waveform patterns comprises: determining an observed peak amplitude of the observed inspiration-expiration waveform pattern; determining an expected peak amplitude of the particular expected inspiration-expiration waveform pattern; and comparing the observed peak amplitude and the expected peak amplitude to determine a difference measure for the observed inspiration-expiration waveform pattern and the particular expected inspiration-expiration waveform pattern.

“14. The apparatus of claim 13, wherein the predicted interruption score is determined based at least in part on whether a lowest difference measure associated with the observed inspiration-expiration waveform pattern satisfies a difference measure threshold.

“15. The apparatus of claim 9, wherein generating the predicted interruption score includes: detecting an interruption duration of a detected interruption in an upward progression of the observed inspiration-expiration waveform pattern; determining a splinting severity level based at least in part on the interruption duration; and determining the predicted interruption score based at least in part on the splinting severity level.

“16. The apparatus of claim 9, wherein initiating the performance of the one or more prediction-based actions comprises: responsive to determining that the predicted interruption score satisfies a predicted interruption score threshold, generating user interface data for one or more therapeutic notifications corresponding to the observed inspiration-expiration waveform pattern, wherein the one or more therapeutic notifications are configured to be displayed using a display device of a computing entity associated with the monitored individual.”

There are additional claims. Please visit full patent to read further.

URL and more information on this patent, see: Boss, Gregory J. Machine learning techniques for detecting splinting activity. U.S. Patent Number 11864925, filed July 14, 2021, and published online on January 9, 2024. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11864925)&db=USPAT&type=ids

(Our reports deliver fact-based news of research and discoveries from around the world.)