Back to results
US 11,887,713 B2Granted
Non-invasive determination of likely response to anti-diabetic therapies for cardiovascular disease
AssigneeElucid Bioimaging Inc.
InventorsAndrew J. Buckler, Ulf Hedin, Ljubica Matic, Matthew Phillips
Life of this patent
Estimating the term…
Abstract
Provided herein are methods and systems for making patient-specific therapy recommendations of an anti-diabetic therapy for patients with known or suspected cardiovascular disease, such as atherosclerosis.
Claims24
A method of providing a recommendation of an anti-diabetic therapy for a patient with known or suspected atherosclerotic cardiovascular disease, the method comprising:
- receiving a first input of non-invasively obtained imaging data related to a plaque from a set of test subjects;
- receiving a second input of molecular expression data from the set of test subjects;
- creating a training set comprising the first input and the second input;
- training a neural network using the training set, the neural network configured to predict molecule levels based on the non-invasively obtained imaging data from the set of test subjects;
- receiving non-invasively obtained imaging data related to a plaque from the patient;
- generating virtual ′omics data that include predicted molecule levels of the patient, by applying the neural network to the non-invasively obtained imaging data from the patient;
- providing the virtual ′omics data to a systems biology model of atherosclerotic cardiovascular disease to generate a patient-specific systems biology model, wherein
- (i) the systems biology model represents a plurality of pathways associated with atherosclerotic cardiovascular disease,
- (ii) each pathway in the plurality of pathways corresponds to one or more of MTOR, NFκβ1, ICAM1, or VCAM1,
- (iii) the systems biology model includes a disease-associated molecule level for each molecule in the systems biology model, and
- (iv) the patient-specific systems biology model includes predicted molecule levels that are updated from the disease-associated molecule level;
- updating the patient-specific systems biology model with information relating to an effect on glucose levels by an anti-diabetic agent based on a known mechanism of action of the anti-diabetic agent;
- and
- simulating a therapeutic response by the patient to the anti-diabetic agent in the updated patient-specific systems biology model to obtain a simulated therapeutic effect, wherein the simulated therapeutic effect is based on change in the predicted molecule levels in the updated patient-specific systems biology model with and without the anti-diabetic agent.
11 more elements
A method of identifying one or more contraindications associated with an anti-diabetic therapy for a patient diagnosed with atherosclerotic cardiovascular disease, the method comprising:
- receiving a first input of non-invasively obtained imaging data related to a plaque from a set of test subjects;
- receiving a second input of molecular expression data from the set of test subjects;
- creating a training set comprising the first input and the second input;
- training a neural network using the training set, the neural network configured to predict molecule levels based on the non-invasively obtained imaging data from the set of test subjects;
- receiving non-invasively obtained imaging data related to a plaque from the patient;
- generating virtual ′omics data that include predicted molecule levels of the patient, by applying the neural network to the non-invasively obtained imaging data from the patient;
- providing the virtual ′omics data to a systems biology model of atherosclerotic cardiovascular disease to generate a patient-specific systems biology model, wherein
- (i) the systems biology model represents a plurality of pathways associated with atherosclerotic cardiovascular disease,
- (ii) each pathway in the plurality of pathways corresponds to one or more of MTOR, NFκβ1, ICAM1, or VCAM1,
- (iii) the systems biology model includes a disease-associated molecule level for each molecule in the systems biology model, and
- (iv) the patient-specific systems biology model includes predicted molecule levels that are updated from the disease-associated molecule level;
- updating the patient-specific systems biology model with information relating to an effect on glucose levels by an anti-diabetic agent based on a known mechanism of action of the anti-diabetic agent;
- simulating a therapeutic response by the patient to the anti-diabetic agent in the updated patient-specific systems biology model to obtain a simulated therapeutic effect, wherein the simulated therapeutic effect is based on change in the predicted molecule levels in the updated patient-specific systems biology model with and without the anti-diabetic agent;
- and
- identifying one or more contraindications associated with the anti-diabetic agent based on change in the predicted molecule levels in the patient-specific systems biology model with and without the anti-diabetic agent.
12 more elements
A method of screening a candidate anti-diabetic agent for atherosclerotic cardiovascular disease, the method comprising:
- receiving a first input of non-invasively obtained imaging data related to a plaque from a first set of test subjects;
- receiving a second input of molecular expression data from the first set of test subjects;
- creating a training set comprising the first input and the second input;
- training a neural network using the training set, the neural network configured to predict molecule levels based on the non-invasively obtained imaging data from the first set of test subjects;
- receiving non-invasively obtained imaging data related to a plaque from each of a second set of test subjects who have been diagnosed with atherosclerotic cardiovascular disease;
- for each test subject of the second set of test subjects:
- generating virtual ′omics data that include predicted molecule levels of a respective test subject, by applying the neural network to the non-invasively obtained imaging data from the respective test subject;
- providing the virtual ′omics data to a systems biology model of atherosclerotic cardiovascular disease to generate a test subject-specific systems biology model for the respective test subject, wherein
- (i) the systems biology model represents a plurality of pathways associated with atherosclerotic cardiovascular disease,
- (ii) the plurality of pathways include one or more pathways corresponding to potential targets of the candidate anti-diabetic agent,
- (iii) the systems biology model includes a disease-associated molecule level for each molecule in the systems biology model, and
- (iv) the test subject-specific systems biology model includes predicted molecule levels that are updated from the disease-associated molecule level;
- updating the test subject-specific systems biology model with information relating to an effect on glucose levels by a candidate anti-diabetic agent based on a known mechanism of action of the candidate anti-diabetic agent;
- and
- simulating a therapeutic response by the respective test subject to the anti-diabetic agent in the updated test subject-specific systems biology model to obtain a simulated therapeutic effect, wherein the simulated therapeutic effect is based on change in the predicted molecule levels in the updated test subject-specific systems biology model with and without the candidate anti-diabetic agent.
12 more elements
A method of screening a potential subject for enrollment in a clinical trial testing safety or efficacy, or both, of a candidate anti-diabetic agent for atherosclerotic cardiovascular disease, the method comprising:
- receiving a first input of non-invasively obtained imaging data related to a plaque from a set of test subjects;
- receiving a second input of molecular expression data from the set of test subjects;
- creating a training set comprising the first input and the second input;
- training a neural network using the training set, the neural network configured to predict molecule levels based on the non-invasively obtained imaging data from the set of test subjects;
- receiving non-invasively obtained imaging data related to a plaque from the potential subject;
- generating virtual ′omics data that include predicted molecule levels of the potential subject, by applying the neural network to the non-invasively obtained imaging data from the potential subject;
- providing the virtual ′omics data to a systems biology model of atherosclerotic cardiovascular disease to generate a subject-specific systems biology model, wherein
- (i) the systems biology model represents a plurality of pathways associated with atherosclerotic cardiovascular disease,
- (ii) each pathway in the plurality of pathways corresponds to one or more of MTOR, NFκβ1, ICAM1, or VCAM1,
- (iii) the systems biology model includes a disease-associated molecule level for each molecule in the systems biology model, and
- (iv) the subject-specific systems biology model includes predicted molecule levels that are updated from the disease-associated molecule level;
- updating the subject-specific systems biology model with predicted molecular levels derived from information relating to an effect on glucose by a candidate anti-diabetic agent based on a known mechanism of action of the candidate anti-diabetic agent;
- and
- simulating a therapeutic response by the potential subject to the candidate anti-diabetic agent in the updated subject-specific systems biology model to obtain a simulated therapeutic effect, wherein the simulated therapeutic effect is based on change in the predicted molecule levels in the updated subject-specific systems biology model with and without the candidate anti-diabetic agent.
11 more elements
Dependencies are inferred from the claim text.