Back to results
US 2026/0268166 A1Published application
Systems and methods for enhanced user specific predictions using machine learning techniques
AssigneeColor Health, Inc.
InventorsCarmen Lai, Jill Hagenkord, Katsuya Noguchi
Life of this patent
Estimating the term…
Abstract
Data sets can be processed using machine learning or artificial intelligence models to generate outputs predictive of a degree to which performing a protocol can positively modify an expected result associated with a condition. Generating the output may include accessing a user data set, inputting the user data set into a trained machine learning model to generate an output, and selecting an incomplete subset of a set of genes based on the output.
Claims20
A computer-implemented method comprising:
- generating, for each user data set of one or more user data sets, an input data set that corresponds to a particular user of a set of users and that includes two or more user feature values, each user feature value of the two or more user feature values characterizing an aspect of the particular user;
- processing each input data set using a trained machine learning model, the trained machine learning model having been trained to using a training data set associated with a plurality of other users, wherein each execution of the trained machine learning model generates:
- an output corresponding to a prediction of whether or a degree to which an expected event of a particular condition is modifiable by performing, on a particular user, a particular treatment;
- and
- at least one of:
- (i) a set of intermediate values, each intermediate value of the set of intermediate values representing a computed value or (ii) a set of branching paths, each branching path of the set of branching paths representing a path between a top-level node and a final leaf node of the trained machine learning model;
- analyzing the set of intermediate values and/or the set of branching paths to determine one or more user data items that are predictive of the output, wherein the one or more user data items include a subset of the set of branching paths, a subset of the intermediate values, or one or more particular user attributes;
- and
- identifying a gene panel that is specific to a user based on the one or more user data items.
6 more elements
A system, comprising:
- one or more processors;
- and
- a non-transitory computer-readable storage medium containing instructions which, when executed on the one or more processors, cause the one or more processors to perform operations including:
- generating, for each user data set of one or more user data sets, an input data set that corresponds to a particular user of a set of users and that includes two or more user feature values, each user feature value of the two or more user feature values characterizing an aspect of the particular user;
- processing each input data set using a trained machine learning model, the trained machine learning model having been trained to using a training data set associated with a plurality of other users, wherein each execution of the trained machine learning model generates:
- an output corresponding to a prediction of whether or a degree to which an expected event of a particular condition is modifiable by performing, on a particular user, a particular treatment;
- and
- at least one of:
- (i) a set of intermediate values, each intermediate value of the set of intermediate values representing a computed value or (ii) a set of branching paths, each branching path of the set of branching paths representing a path between a top-level node and a final leaf node of the trained machine learning model;
- analyzing the set of intermediate values and/or the set of branching paths to determine one or more user data items that are predictive of the output, wherein the one or more user data items include a subset of the set of branching paths, a subset of the intermediate values, or one or more particular user attributes;
- and
- identifying a gene panel that is specific to a user based on the one or more user data items.
9 more elements
A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause a processing apparatus to perform operations including:
- generating, for each user data set of one or more user data sets, an input data set that corresponds to a particular user of a set of users and that includes two or more user feature values, each user feature value of the two or more user feature values characterizing an aspect of the particular user;
- processing each input data set using a trained machine learning model, the trained machine learning model having been trained to using a training data set associated with a plurality of other users, wherein each execution of the trained machine learning model generates:
- an output corresponding to a prediction of whether or a degree to which an expected event of a particular condition is modifiable by performing, on a particular user, a particular treatment;
- and
- at least one of:
- (i) a set of intermediate values, each intermediate value of the set of intermediate values representing a computed value or (ii) a set of branching paths, each branching path of the set of branching paths representing a path between a top-level node and a final leaf node of the trained machine learning model;
- analyzing the set of intermediate values and/or the set of branching paths to determine one or more user data items that are predictive of the output, wherein the one or more user data items include a subset of the set of branching paths, a subset of the intermediate values, or one or more particular user attributes;
- and
- identifying a gene panel that is specific to a user based on the one or more user data items.
6 more elements
Dependencies are inferred from the claim text.