US 11,864,944 B2
Systems and methods for a deep neural network to enhance prediction of patient endpoints using videos of the heart
Brandon K. Fornwalt, Lewisburg, PA (US); Christopher Haggerty, Lewisburg, PA (US); Alvaro Ulloa Cerna, Danville, PA (US); and Christopher Good, Fairview, PA (US)
Assigned to Geisinger Clinic, Danville, PA (US)
Filed by Geisinger Clinic, Danville, PA (US)
Filed on Nov. 16, 2020, as Appl. No. 17/099,743.
Claims priority of provisional application 62/936,377, filed on Nov. 15, 2019.
Prior Publication US 2021/0145404 A1, May 20, 2021
Int. Cl. A61B 8/08 (2006.01); G16H 50/20 (2018.01); G16H 50/30 (2018.01); G16H 30/40 (2018.01); G16H 15/00 (2018.01); G16H 50/70 (2018.01); G16H 70/60 (2018.01); G16H 30/20 (2018.01); G16H 10/40 (2018.01); G16H 20/40 (2018.01); G06T 7/00 (2017.01); A61B 8/14 (2006.01); G16H 10/60 (2018.01); A61B 8/04 (2006.01); A61B 8/06 (2006.01); G06N 3/08 (2023.01); G06N 3/045 (2023.01)
CPC A61B 8/0883 (2013.01) [A61B 8/04 (2013.01); A61B 8/065 (2013.01); A61B 8/14 (2013.01); A61B 8/5223 (2013.01); A61B 8/5246 (2013.01); A61B 8/5292 (2013.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06T 7/0002 (2013.01); G06T 7/0012 (2013.01); G16H 10/40 (2018.01); G16H 10/60 (2018.01); G16H 15/00 (2018.01); G16H 20/40 (2018.01); G16H 30/20 (2018.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G16H 50/30 (2018.01); G16H 50/70 (2018.01); G16H 70/60 (2018.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30048 (2013.01)] 30 Claims
OG exemplary drawing
 
1. A method comprising:
receiving an echocardiographic video of a heart associated with a patient;
providing the echocardiographic video to a trained neural network, the trained neural network being trained to generate a mortality risk score based on input echocardiographic video;
receiving a mortality risk score associated with the patient from the trained neural network; and
outputting the mortality risk score associated with the patient to at least one of a memory or a display for viewing by a medical practitioner or healthcare administrator,
wherein the trained neural network includes at least a first layer and a second layer, the first layer trained to generate, based on input echocardiographic video having first video dimensions, a first layer output having output dimensions that are different from the first video dimensions, and the second layer trained to generate, at least partially based on the first layer output, a mortality risk score.