Abstract: A computer system includes processor hardware configured to execute instructions from memory hardware. The instructions include training a machine learning model to generate an entity expiration likelihood output, obtaining a set of multiple database entities, and processing, by the machine learning model, feature vector inputs associated with each database entry to generate an entity expiration likelihood output. The instructions include determining a subset of the database entities having the highest entity expiration likelihood outputs, and, for each database entity in the subset, determining output impact scores for parameters of the feature vector input associated with the database entity, generating a feature list based on the determined output impact scores, and automatically selecting an executable sequence according to the entity expiration likelihood output associated with the database entity.

Abstract: A method for determining a social health score for a region includes (i) receiving first data for a geographical area including values for a plurality of features corresponding to a plurality of domains; (ii) for a first domain of the plurality of domains, selecting a first set of features that correspond to the first domain, and determining first feature weights for the first set of features based on a quantile g-computation of the values of the first data for the first set of features; (iii) receiving second data for the region including values for a subset of the plurality of features and the first domain, (iv) determining a first region domain score based on the second data and the first feature weights; and (v) determining a total score for the region based on the first region domain score indicating a level of resource access for a population of the region.

Abstract: A method for determining a defection probability includes receiving user data. The method also includes determining, from the user data, a set of features characterizing a likelihood of the user to change from the initial service channel to an alternative service channel. The method further includes generating an input encoding for the set of features. The method additionally includes determining, using a predictive model, a probability that indicates how likely the user is to change from the initial service channel, wherein the predictive model is trained to receive, as input, the input encoding and to generate, as output, a respective probability that indicates how likely a respective user is to change from the initial service channel to the alternative service channel. The method also includes determining whether the probability from the predictive model satisfies a defection threshold and selectively generating a remedial action based on the probability.

Abstract: Methods and systems for classifying and editing insurance claims records are described. In one embodiment, a method, which can be performed by a processor, includes identifying that a first prescription drug prescribed to a first patient, identifying a first date and a second date related to the first prescription, the second date occurring after the first date, both the first and second dates depending on a previous fill of the first prescription drug, identifying, at the processor, a third date associated with a second prescription, comparing, at the processor, the third date to the first and second dates to determine whether the third date occurs after the first date and before the second date, and filling and dispensing the first prescription drug and the second prescription drug on the same dispense date when the third date occurs after the first date and before the second date.

Abstract: A modeling computing device for predicting relative patient hazards based on predicted patient pharmaceutical adherence is provided. The modeling computing device includes a processor configured to receive a set of adherence data associated with adherence to a pharmaceutical prescription by a patient. The processor is also configured to determine a set of predictive adherence scores and determine a variability score associated with the set of predictive adherence scores. The processor is further configured to integrate the set of predictive adherence scores and the variability score into a feature value. The processor is also configured to identify a hazard regression model and to apply the feature value to the hazard regression model to generate an integrated patient hazard model. The processor is also configured to process the integrated patient hazard model to determine a risk level associated with the patient, and transmit an alert based on the risk level.

Abstract: A method includes receiving historical data collected from a client associated with members. The historical data includes per-member metrics for the client and demographic information for the members. The method includes identifying therapeutic classes for the client based on the per-member metrics and the demographic information. The method includes segmenting the historical data into a data set for each therapeutic class. The method includes, for each therapeutic class of the set of therapeutic classes, determining a pattern for the per-member metrics corresponding to the respective therapeutic class, generating a respective predictive model based on the pattern, and training a neural network of the respective predictive model using a two-stage training process. The predictive model is configured to generate, as output for the therapeutic class, a per-member metric prediction for an input period of future time.

Abstract: Methods and systems for classifying and editing insurance claims records are described. In one embodiment, a method, which can be performed by a processor, includes identifying that a first prescription drug prescribed to a first patient, identifying a first date and a second date related to the first prescription, the second date occurring after the first date, both the first and second dates depending on a previous fill of the first prescription drug, identifying, at the processor, a third date associated with a second prescription, comparing, at the processor, the third date to the first and second dates to determine whether the third date occurs after the first date and before the second date, and filling and dispensing the first prescription drug and the second prescription drug on the same dispense date when the third date occurs after the first date and before the second date.

Abstract: Methods and systems for classifying and editing insurance claims records are described. In one embodiment, a method, which can be performed by a processor, includes determining that a first prescription drug prescribed to a first patient should be filled by a pharmacy, determining a first guidepost date and a second guidepost date related to the first prescription, determining a third guidepost date associated with a second prescription, comparing the third guidepost date to the first and second guidepost dates to determine whether the third guidepost date occurs after the first guidepost date and before the second guidepost date, and filling and dispensing the first prescription drug as a full prescription supply and the second prescription drug as a full prescription supply on the same dispense date when the third guidepost date occurs after the first guidepost date and before the second guidepost date.

Abstract: A method includes receiving historical data collected from a client associated with members. The historical data includes per-member metrics for the client and demographic information for the members. The method includes identifying therapeutic classes for the client based on the per-member metrics and the demographic information. The method includes segmenting the historical data into a data set for each therapeutic class. The method includes, for each therapeutic class of the set of therapeutic classes, determining a pattern for the per-member metrics corresponding to the respective therapeutic class, generating a respective predictive model based on the pattern, and training a neural network of the respective predictive model using a two-stage training process. The predictive model is configured to generate, as output for the therapeutic class, a per-member metric prediction for an input period of future time.

Abstract: A method for determining a defection probability includes receiving user data. The method also includes determining, from the user data, a set of features characterizing a likelihood of the user to change from the initial service channel to an alternative service channel. The method further includes generating an input encoding for the set of features. The method additionally includes determining, using a predictive model, a probability that indicates how likely the user is to change from the initial service channel, wherein the predictive model is trained to receive, as input, the input encoding and to generate, as output, a respective probability that indicates how likely a respective user is to change from the initial service channel to the alternative service channel. The method also includes determining whether the probability from the predictive model satisfies a defection threshold and selectively generating a remedial action based on the probability.

Abstract: A method for generating predictions for year-over-year change in drug spending and per member per month spending and for providing the predictions via a web portal includes receiving data collected from a health plan. The data includes per member per month costs of the health plan and demographic information of members of the health plan. The method includes selecting therapeutic classes based on the per member per month costs and demographic information, segmenting the data by the therapeutic classes, and detecting patterns by analyzing the segmented data. The method includes generating models for the therapeutic classes based on the patterns, and generating predictions for year-over-year change in drug spending and per member per month spending for the therapeutic classes by utilizing the models. The method includes providing the predictions via a web portal in at least one of a displayable graphical format and a downloadable data structure.

Abstract: Methods and systems for classifying and editing insurance claims records are described. In one embodiment, a method, which can be performed by a processor, includes determining that a first prescription drug prescribed to a first patient should be filled by a pharmacy, determining a first guidepost date and a second guidepost date related to the first prescription, determining a third guidepost date associated with a second prescription, comparing the third guidepost date to the first and second guidepost dates to determine whether the third guidepost date occurs after the first guidepost date and before the second guidepost date, and filling and dispensing the first prescription drug as a full prescription supply and the second prescription drug as a full prescription supply on the same dispense date when the third guidepost date occurs after the first guidepost date and before the second guidepost date.

Abstract: A computer system includes processor hardware configured to execute instructions from memory hardware. The instructions include training a machine learning model to generate an entity expiration likelihood output, obtaining a set of multiple database entities, and processing, by the machine learning model, feature vector inputs associated with each database entry to generate an entity expiration likelihood output. The instructions include determining a subset of the database entities having the highest entity expiration likelihood outputs, and, for each database entity in the subset, determining output impact scores for parameters of the feature vector input associated with the database entity, generating a feature list based on the determined output impact scores, and automatically selecting an executable sequence according to the entity expiration likelihood output associated with the database entity.

Abstract: Methods and systems for classifying and editing insurance claims records are described. In one embodiment, a method, which can be performed by a processor, includes determining that a first prescription drug prescribed to a first patient should be filled by a pharmacy, determining a first guidepost date and a second guidepost date related to the first prescription, determining a third guidepost date associated with a second prescription, comparing the third guidepost date to the first and second guidepost dates to determine whether the third guidepost date occurs after the first guidepost date and before the second guidepost date, and filling and dispensing the first prescription drug as a full prescription supply and the second prescription drug as a full prescription supply on the same dispense date when the third guidepost date occurs after the first guidepost date and before the second guidepost date.