US 12,484,858 B1
Systems and methods for a foundation model for cardiac data
George Mathew, Berkeley, CA (US); John Prince, New York, NY (US); Daniel Barbosa, Newton Upper Falls, MA (US); and Subramaniam Venkatraman, Lafayette, CA (US)
Assigned to EKO HEALTH, INC., Emeryville, CA (US)
Filed by Eko Health, Inc., Emeryville, CA (US)
Filed on Jun. 4, 2024, as Appl. No. 18/733,678.
Int. Cl. A61B 5/00 (2006.01); A61B 5/02 (2006.01); A61B 5/08 (2006.01); A61B 5/361 (2021.01); A61B 7/04 (2006.01); G16H 10/60 (2018.01)
CPC A61B 5/7267 (2013.01) [A61B 5/02028 (2013.01); A61B 5/08 (2013.01); A61B 5/361 (2021.01); A61B 5/7221 (2013.01); A61B 5/742 (2013.01); A61B 7/04 (2013.01); G16H 10/60 (2018.01); A61B 2560/045 (2013.01); A61B 2560/0468 (2013.01); A61B 2562/0204 (2013.01); A61B 2562/0219 (2013.01); A61B 2562/225 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
obtaining an ECG signal and a PCG signal from a patient, wherein the ECG signal and PCG signal are synchronized;
converting the PCG signal to a PCG mel-spectrogram;
partitioning the ECG signal into segments and partitioning the PCG mel-spectrogram into patches;
forming an input sequence from the segments and the patches;
entering the input sequence as input to a trained specialized model configured to output a classification output based on the input sequence, the trained specialized model trained with labeled ECG and PCG signal pairs using a foundation model trained with unlabeled ECG and PCG signal pairs; and
storing the classification output in memory and/or displaying the classification output on a display device.