US 11,887,724 B2
Estimating uncertainty in predictions generated by machine learning models
Tathagata Banerjee, Waltham, MA (US); Matthew Edward Kollada, Deerfield, IL (US); Amirsina Torfi, Fairfax, VA (US); and Peter Crocker, Huntington Beach, CA (US)
Assigned to Neumora Therapeutics, Inc., San Francisco, CA (US)
Filed by NEUMORA THERAPEUTICS, INC., San Francisco, CA (US)
Filed on Oct. 5, 2022, as Appl. No. 17/960,759.
Claims priority of provisional application 63/413,150, filed on Oct. 4, 2022.
Claims priority of provisional application 63/400,250, filed on Aug. 23, 2022.
Claims priority of provisional application 63/337,753, filed on May 3, 2022.
Claims priority of provisional application 63/328,189, filed on Apr. 6, 2022.
Claims priority of provisional application 63/294,751, filed on Dec. 29, 2021.
Claims priority of provisional application 63/292,115, filed on Dec. 21, 2021.
Claims priority of provisional application 63/252,500, filed on Oct. 5, 2021.
Claims priority of provisional application 63/252,523, filed on Oct. 5, 2021.
Claims priority of provisional application 63/252,539, filed on Oct. 5, 2021.
Claims priority of provisional application 63/252,562, filed on Oct. 5, 2021.
Prior Publication US 2023/0109108 A1, Apr. 6, 2023
Int. Cl. G16H 50/70 (2018.01); G16H 50/20 (2018.01); G06N 3/02 (2006.01); G06V 10/82 (2022.01); G06V 10/774 (2022.01); G06N 3/08 (2023.01); G16H 30/40 (2018.01); G16H 40/20 (2018.01); G06N 3/045 (2023.01); G06V 10/77 (2022.01); G06T 7/00 (2017.01); G06N 20/00 (2019.01)
CPC G16H 40/20 (2018.01) [G06N 3/02 (2013.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06T 7/0016 (2013.01); G06V 10/774 (2022.01); G06V 10/7715 (2022.01); G06V 10/82 (2022.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G16H 50/70 (2018.01); G06N 20/00 (2019.01); G06T 2207/10088 (2013.01); G06T 2207/10104 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30016 (2013.01); G06T 2207/30104 (2013.01); G06V 2201/03 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method performed by one or more computers, the method comprising:
receiving multi-modal data characterizing a patient, wherein the multi-modal data comprises a respective feature representation for each of a plurality of modalities;
processing the multi-modal data characterizing the patient using a machine learning model, in accordance with values of a set of machine learning model parameters, to generate a patient classification that classifies the patient as being included in a patient category from a set of patient categories, comprising:
processing the multi-modal data characterizing the patient using an encoder neural network of the machine learning model to generate an embedding of the multi-modal data in a latent space; and
generating the patient classification based on the embedding of the multi-modal data in the latent space;
wherein the encoder neural network has been trained on a plurality of training examples by a machine learning training technique, the training comprising, for each training example:
processing training multi-modal data included in the training example using the encoder neural network to generate an embedding of the training multi-modal data;
processing the embedding of the training multi-modal data using a decoder neural network to generate a reconstruction of the training multi-modal data; and
updating current values of a set of encoder neural network parameters using gradients of an objective function that measures an error in the reconstruction of the training multi-modal data;
determining an uncertainty measure that characterizes an uncertainty of the patient classification generated by the machine learning model; and
generating a clinical recommendation for medical treatment of the patient based on: (i) the patient classification, and (ii) the uncertainty measure that characterizes the uncertainty of the patient classification.