Systems and methods for using machine learning algorithms to identify care gaps
In some instances, a method is provided. The method comprises obtaining one or more care gap machine learning-artificial intelligence (ML-AI) models; obtaining individual information of an individual, wherein the individual information indicates one or more medical conditions of the individual and personal information of the individual; determining care gap information of the individual based on using the one or more care gap ML-AI models and the individual information, wherein the care gap information indicates one or more predictions for expectancy of a care gap of the individual, and wherein the care gap is associated with a gap in time that the individual has a lapse in receiving medical care for the one or more medical conditions; and performing one or more care gap interventions based on the care gap information.
1 . A method, comprising:
obtaining population information for a plurality of individuals associated with an enterprise organization;
filtering the population information using a plurality of care gap cohorts to determine a subset of the population information for each of the plurality of care gap cohorts;
training a plurality of care gap machine learning-artificial intelligence (ML-AI) models based on the subset of the population information such that each of the plurality of care gap ML-AI models is associated with one or more care gap cohorts from the plurality of care gap cohorts;
determining to retrain a first care gap ML-AI model, of the plurality of care gap ML-AI models, based on a first care gap cohort, of the plurality of care gap cohorts, having insufficient data to train the first care gap ML-AI model;
based on the determination, combining a first subset of the population information associated with the first care gap cohort with a second subset of the population information associated with a second care gap cohort from the plurality of care gap cohorts to obtain combined population information;
retraining the first care gap ML-AI model based on the combined population information;
obtaining individual information of an individual, wherein the individual information indicates one or more medical conditions of the individual and a care gap of the individual indicating a gap in time that the individual has a lapse in receiving medical care for the one or more medical conditions;
selecting the first care gap ML-AI model, from the plurality of care gap ML-AI models, based on comparing the gap in time that the individual has the lapse in receiving medical care for the one or more medical conditions with the plurality of care gap cohorts;
determining care gap information of the individual based on using the first care gap ML-AI model and the individual information; and
performing one or more care gap interventions based on the care gap information.
2 . The method of claim 1 , wherein each of the plurality of care gap ML-AI models is further associated with a particular medical condition, and
wherein selecting the first care gap ML-AI model is further based on comparing the one or more medical conditions of the individual with the particular medical condition associated with each of the plurality of care gap ML-AI models.
3 . The method of claim 1 , wherein the plurality of care gap ML-AI models are a plurality of closed care gap ML-AI models associated with probabilities that individuals with an open care gap will close the open care gap.
4 . The method of claim 1 , wherein selecting the first care gap ML-AI model is further based on the one or more medical conditions of the individual.
5 . The method of claim 1 , wherein the individual information of the individual indicates a business segment associated with the individual, and
wherein selecting the first care gap ML-AI model is further based on the business segment associated with the individual.
6 . The method of claim 1 , wherein obtaining the individual information of the individual comprises:
receiving the individual information of the individual from an external source, wherein the individual information comprises financial information associated with the individual and prescription information of the individual.
7 . The method of claim 1 , wherein the first care gap ML-AI model is a closed care gap ML-AI model, and
wherein performing the one or more care gap interventions based on the care gap information comprises:
displaying a plurality of probabilities indicating a likelihood of the individual closing the care gap within a time span.
8 . The method of claim 1 , wherein the first care gap ML-AI model is an open care gap ML-AI model, and
wherein performing the one or more care gap interventions based on the care gap information comprises:
displaying a plurality of probabilities indicating a likelihood of the individual opening the care gap within a time span.
9 . The method of claim 1 ,
wherein determining to retrain the first care gap ML-AI model is based on a triggering event.
10 . The method of claim 1 , wherein filtering the population information is further based on
a plurality of medical conditions.
11 . The method of claim 1 , wherein filtering the population information comprises:
performing data manipulation on the population information comprising removal of nulls, feature filtration, or outlier removal.
12 . The method of claim 1 , wherein the plurality of care gap ML-AI models comprises a survival analysis ML-AI model.
13 . A computing platform, comprising:
one or more processors; and
a non-transitory computer-readable medium having processor-executable instructions stored thereon, wherein the processor-executable instructions, when executed by the one or more processors, facilitate:
obtaining population information for a plurality of individuals associated with an enterprise organization;
filtering the population information using a plurality of care gap cohorts to determine a subset of the population information for each of the plurality of care gap cohorts;
training a plurality of care gap machine learning-artificial intelligence (ML-AI) models based on the subset of the population information such that each of the plurality of care gap ML-AI models is associated with one or more care gap cohorts from the plurality of care gap cohorts;
determining to retrain a first care gap ML-AI model, of the plurality of care gap ML-AI models, based on a first care gap cohort, of the plurality of care gap cohorts, having insufficient data to train the first care gap ML-AI model;
based on the determination, combining a first subset of the population information associated with the first care gap cohort with a second subset of the population information associated with a second care gap cohort from the plurality of care gap cohorts to obtain combined population information;
retraining the first care gap ML-AI model based on the combined population information;
obtaining individual information of an individual, wherein the individual information indicates one or more medical conditions of the individual and a care gap of the individual indicating a gap in time that the individual has a lapse in receiving medical care for the one or more medical conditions;
selecting the first care gap ML-AI model, from the plurality of care gap ML-AI models, based on comparing the gap in time that the individual has the lapse in receiving medical care for the one or more medical conditions with the plurality of care gap cohorts;
determining care gap information of the individual based on using the first care gap ML-AI model and the individual information; and
performing one or more care gap interventions based on the care gap information.
14 . The computing platform of claim 13 , wherein each of the plurality of care gap ML-AI models is further associated with a particular medical condition, and
wherein
selecting the first care gap ML-AI model is further based on comparing the one or more medical conditions of the individual with the particular medical condition associated with each of the plurality of care gap ML-AI models.
15 . The computing platform of claim 13 , wherein the plurality of care gap ML-AI models are a plurality of closed care gap ML-AI models associated with probabilities that individuals with an open care gap will close the open care gap.
16 . The computing platform of claim 13 , wherein filtering the population information comprises:
performing data manipulation on the population information comprising removal of nulls, feature filtration, or outlier removal.
17 . The computing platform of claim 13 , wherein determining to retrain the first care gap ML-AI model is based on a triggering event.
18 . The computing platform of claim 13 , wherein the first care gap ML-AI model is a closed care gap ML-AI model, and
wherein performing the one or more care gap interventions based on the care gap information comprises:
displaying a plurality of probabilities indicating a likelihood of the individual closing the care gap within a time span.
19 . The computing platform of claim 13 , wherein the first care gap ML-AI model is an open care gap ML-AI model, and
wherein performing the one or more care gap interventions based on the care gap information comprises:
displaying a plurality of probabilities indicating a likelihood of the individual opening the care gap within a time span.
20 . A non-transitory computer-readable medium having processor-executable instructions stored thereon, wherein the processor-executable instructions, when executed, facilitate:
obtaining population information for a plurality of individuals associated with an enterprise organization;
filtering the population information using a plurality of care gap cohorts to determine a subset of the population information for each of the plurality of care gap cohorts;
training a plurality of care gap machine learning-artificial intelligence (ML-AI) models based on the subset of the population information such that each of the plurality of care gap ML-AI models is associated with one or more care gap cohorts from the plurality of care gap cohorts;
determining to retrain a first care gap ML-AI model, of the plurality of care gap ML-AI models, based on a first care gap cohort, of the plurality of care gap cohorts, having insufficient data to train the first care gap ML-AI model;
based on the determination, combining a first subset of the population information associated with the first care gap cohort with a second subset of the population information associated with a second care gap cohort from the plurality of care gap cohorts to obtain combined population information;
retraining the first care gap ML-AI model based on the combined population information;
obtaining individual information of an individual, wherein the individual information indicates one or more medical conditions of the individual and a care gap of the individual indicating a gap in time that the individual has a lapse in receiving medical care for the one or more medical conditions;
selecting the first care gap ML-AI model, from the plurality of care gap ML-AI models, based on comparing the gap in time that the individual has the lapse in receiving medical care for the one or more medical conditions with the plurality of care gap cohorts;
determining care gap information of the individual based on using the first care gap ML-AI model and the individual information; and
performing one or more care gap interventions based on the care gap information.