CPC A61B 5/4848 (2013.01) [A61B 5/4824 (2013.01); A61B 5/4836 (2013.01); A61B 5/7264 (2013.01); A61N 1/36071 (2013.01); A61N 1/36135 (2013.01); A61N 1/36139 (2013.01); A61N 1/37241 (2013.01); A61B 5/0075 (2013.01); A61B 5/021 (2013.01); A61B 5/02055 (2013.01); A61B 5/02416 (2013.01); A61B 5/0533 (2013.01); A61B 5/08 (2013.01); A61B 5/0816 (2013.01); A61B 5/0836 (2013.01); A61B 5/14542 (2013.01); A61B 5/318 (2021.01); A61B 5/369 (2021.01); A61B 5/389 (2021.01); A61B 5/398 (2021.01); A61N 1/37247 (2013.01)] | 10 Claims |
1. A system for calibrating spinal cord stimulation (SCS) treatment in a subject, the system comprising a processing module, a sensor module and a classifier module; wherein the processing module is configured to:
receive a first indication from a SCS device that a first SCS treatment is being provided;
wherein the first SCS treatment is characterized by a first value of at least one SCS parameter,
wherein the first value of the at least one SCS parameter is different from that of a second value of the at least one SCS parameter;
initiate the sensor module to conduct a first measurement of at least one physiological signal in response to the first indication from the SCS device;
wherein the at least one physiological signal comprises at least one of a PPG signal or movement (accelerometer) signal;
receive a second indication from the SCS device that a second SCS treatment is being provided; wherein the second SCS treatment is characterized by the second value of the at least one SCS parameter;
initiate the sensor module to conduct a second measurement of the at least one physiological signal in response to the second indication from the SCS device;
initiate the classifier module to, by a non-transitory computer program, extract at least two features from each of the at least one physiological signal obtained from the first and second measurements;
wherein the at least two features comprise PPG amplitude, PPG amplitude variation, pulse rate (PR) interval, PR variability, 3-axis accelerometer data (X, Y, Z, Theta) value, 3-axis accelerometer data (X, Y, Z, Theta (θ)) average value, 3-axis accelerometer data (X, Y, Z, Theta (θ)) variability or any combination thereof;
classify the at least two features by applying a classification algorithm thereon; and output,
based on the classification, whether the first SCS treatment or the second SCS treatment correlates with a higher efficacy.
|