US 12,260,946 B2
Discovery platform
Francesco Paolo Casale, San Francisco, CA (US); Michael Bereket, San Carlos, CA (US); and Matthew Albert, San Francisco, CA (US)
Assigned to INSITRO, INC., South San Francisco, CA (US)
Filed by Insitro, Inc., South San Francisco, CA (US)
Filed on Apr. 24, 2024, as Appl. No. 18/645,100.
Application 18/645,100 is a division of application No. 18/336,905, filed on Jun. 16, 2023, granted, now 12,002,559.
Application 18/336,905 is a continuation of application No. PCT/US2022/075006, filed on Aug. 16, 2022.
Claims priority of provisional application 63/233,707, filed on Aug. 16, 2021.
Prior Publication US 2024/0274255 A1, Aug. 15, 2024
Int. Cl. G16H 20/10 (2018.01); A61B 5/00 (2006.01); G06T 7/00 (2017.01); G16H 15/00 (2018.01); G16H 30/20 (2018.01); G16H 50/70 (2018.01)
CPC G16H 20/10 (2018.01) [A61B 5/4848 (2013.01); G06T 7/0012 (2013.01); G16H 15/00 (2018.01); G16H 30/20 (2018.01); G16H 50/70 (2018.01)] 20 Claims
OG exemplary drawing
 
1. A system of identifying a patient subgroup of interest, the system comprising one or more processors and a memory storing computer instructions, which when executed by the one or more processors, cause the system to:
input a plurality of medical images obtained from a group of clinical subjects into a trained unsupervised machine-learning model to obtain a plurality of embeddings in a latent space;
cluster the plurality of embeddings to generate one or more clusters of embeddings;
identify one or more patient subgroups corresponding to the one or more clusters of embeddings; and
associate each patient subgroup of the one or more patient subgroups with a covariant to identify the patient subgroup of interest.