Regression Modeling System Using Activation Rating Values as Inputs to a Regression to Predict Healthcare Utilization and Cost and/or Changes Thereto
AssigneeInsignia Health, LLC
InventorsEldon R. Mahoney, Christopher R. Delaney
Life of this patent
Estimating the term…
Abstract
In a regression modeling system, activation rating values over a plurality of survey participants is used to generate a regression to identify a predictive model that can have a direct explanatory relationship to healthcare utilization and cost. The activation rating for a given individual is thus a predictive variable that can be changed with a known effect on outcomes. For example, healthcare utilization and costs will decline as an activation rating value goes up.
Claims8
A computer-implemented method for modeling, using a computer system, to predict healthcare utilization and cost based upon a person's activation rating, wherein the activation rating is a variable representing, as a number, the person's self-management ability or activation score, the method comprising:
- obtaining activation-rating values over a plurality of survey participants;
- generating a regression to identify a predictive model that can have a direct explanatory relationship to healthcare utilization and cost;
- and
- outputting results.
A computer-implemented method for modeling, using a computer system, to predict healthcare utilization and cost based upon a user activation rating, wherein the activation rating is a variable representing, as a number, a self-management ability of the user or activation score of the user, the method comprising:
- providing a survey of self-management questions to a set of users, to each user of the set of users;
- performing a regression model, employing a Rasch model, linearize survey answers to a measurement, from ordinal to cardinal;
- outputting results of the regression model based at least in part on the results;
- and
- using, at least in part, the results to predict healthcare utilization and cost outcomes for each user, of the set of users.
A non-transitory computer-readable storage medium having stored thereon executable instructions that, when executed by one or more processors of a computer system, cause the computer system to at least:
- provide a survey of self-management ability questions to a population of users, each user of the population of users providing written answers in response to the survey;
- use a Rasch measurement model to linearize the written answers;
- perform a regression analysis on the outcome of the Rasch measurement model;
- and
- output results.
Dependencies are inferred from the claim text.