US 12,278,015 B2
Application-specific processing of a disease-specific semantic model instance
Gilan El Saadawi, Pittsburgh, PA (US); Aaron Brauser, Gibsonia, PA (US); and Gary Wallace, Harrisville, PA (US)
Assigned to Realyze Intelligence, Inc., Pittsburgh, PA (US)
Filed by Realyze Intelligence, Inc., Pittsburgh, PA (US)
Filed on Apr. 12, 2024, as Appl. No. 18/633,994.
Application 18/633,994 is a continuation of application No. 18/489,437, filed on Oct. 18, 2023, granted, now 11,961,622.
Claims priority of provisional application 63/418,099, filed on Oct. 21, 2022.
Prior Publication US 2024/0266070 A1, Aug. 8, 2024
Int. Cl. G06F 40/30 (2020.01); G06F 7/00 (2006.01); G06F 16/28 (2019.01); G06F 16/903 (2019.01); G06F 17/00 (2019.01); G06F 18/10 (2023.01); G06F 18/22 (2023.01); G06F 40/20 (2020.01); G06F 40/40 (2020.01); G16H 10/20 (2018.01); G16H 10/60 (2018.01); G16H 15/00 (2018.01); G16H 50/20 (2018.01); G16H 50/50 (2018.01); G16H 50/70 (2018.01)
CPC G16H 50/50 (2018.01) [G06F 16/28 (2019.01); G06F 16/90335 (2019.01); G06F 17/00 (2013.01); G06F 18/10 (2023.01); G06F 18/22 (2023.01); G06F 40/20 (2020.01); G06F 40/30 (2020.01); G06F 40/40 (2020.01); G16H 10/20 (2018.01); G16H 10/60 (2018.01); G16H 15/00 (2018.01); G16H 50/20 (2018.01); G16H 50/70 (2018.01)] 16 Claims
OG exemplary drawing
 
1. A method performed by at least one computer processor executing computer program instructions stored on at least one non-transitory computer-readable medium, the computer program instructions being executable by the at least one computer processor to perform the method, the method comprising:
(A) receiving first original medical data associated with a first patient over time;
(B) generating, based on the first original medical data, first semantically annotated medical data associated with the first patient, comprising applying a Natural Language Processing (NLP) engine that uses at least one medical ontology to generate the first semantically annotated medical data based on the first original medical data, wherein applying the NLP engine to the first medical data comprises applying rules to at least some of the first original medical data to generate at least some of the first semantically annotated medical data;
(C) applying a reasoning engine to the first semantically annotated medical data to generate a first instance of a first disease-specific semantic model;
wherein the first instance of the first disease-specific semantic model includes data representing a medical history of the first patient; and
wherein the first instance of the first disease-specific semantic model includes data explicitly representing a medical condition of the first patient, wherein the first original medical data does not include data explicitly representing the medical condition of the first patient; and
wherein applying the reasoning engine to the first semantically annotated medical data to generate the first instance of the first disease-specific semantic model comprises generating the data explicitly representing the medical condition of the first patient based on the first semantically annotated medical data;
(D) updating an NLP model in the NLP module to produce an updated NLP module;
(E) generating a new version of the first instance of the first disease-specific semantic model based on the updated NLP module;
(F) evaluating the new version of the first instance of the first disease-specific semantic model against a plurality of criteria associated with a first clinical trial,
wherein the first disease-specific semantic model has a plurality of attributes, each of which has a corresponding range of permissible values;
wherein the new version of the first instance of the first disease-specific semantic model has the plurality of attributes, and wherein each of the plurality of attributes in the new version of the first instance of the first disease-specific semantic model has a corresponding value within the corresponding range of permissible values;
the evaluating comprising calculating a semantic distance between the new version of the first instance of the first disease-specific semantic model and the plurality of criteria associated with the first clinical trial; and
(G) determining, based on the evaluation, whether the new version of the first instance of the first disease-specific semantic model satisfies the plurality of criteria associated with the first clinical trial.