US 12,280,258 B2
Systems and methods for providing neurostimulation therapy according to machine learning operations
Nicole R. Hughes, Plano, TX (US); Robert Nobles, Frisco, TX (US); Daran DeShazo, Lewisville, TX (US); and Betty Mark, Sunnyvale, TX (US)
Assigned to Advanced Neuromodulation Systems, Inc., Plano, TX (US)
Filed by ADVANCED NEUROMODULATION SYSTEMS, INC., Plano, TX (US)
Filed on Dec. 30, 2021, as Appl. No. 17/566,636.
Claims priority of provisional application 63/133,205, filed on Dec. 31, 2020.
Prior Publication US 2022/0323766 A1, Oct. 13, 2022
Int. Cl. A61N 1/36 (2006.01); A61B 5/00 (2006.01); A61B 5/11 (2006.01); A61N 1/05 (2006.01); G16H 40/67 (2018.01)
CPC A61N 1/36146 (2013.01) [A61B 5/11 (2013.01); A61B 5/7267 (2013.01); A61N 1/0551 (2013.01); A61N 1/36132 (2013.01); A61N 1/36139 (2013.01); G16H 40/67 (2018.01)] 9 Claims
OG exemplary drawing
 
1. A method of providing a neurostimulation therapy to a patient, comprising:
applying electrical pulses to a neural target of a patient according to a plurality of stimulation parameters;
obtaining patient data from one or more sensors implanted in or worn by the patient while electrical pulses are applied to the patient;
obtaining video data of the patient;
calculating, based on the video data, kinematic data corresponding to time intervals in which the electrical pulses are applied to the patient;
obtaining patient reported pain levels from the patient using one or more patient applications on a patient therapy controller device, the patient reported pain levels corresponding to time intervals in which the electrical pulses are applied to the patient;
training a machine learning (ML) model using the plurality of stimulation parameters, the patient data, the kinematic data, and the patient reported pain levels, wherein the training comprises receiving user input from a user interface of an external controller device to select one or more patient features from a plurality of available patient features for training of the ML model;
controlling, based on the trained ML model, application of electrical pulses to the patient to treat pain of the patient in accordance with patient data from the one or more sensors.