| CPC G16H 20/10 (2018.01) [G06F 9/542 (2013.01); G06N 7/01 (2023.01); G06N 20/00 (2019.01); G06N 20/10 (2019.01); G06N 20/20 (2019.01); G06Q 10/109 (2013.01); G16H 10/60 (2018.01); G16H 20/00 (2018.01); G16H 40/20 (2018.01); G16H 40/63 (2018.01); G16H 40/67 (2018.01)] | 20 Claims |
|
1. A system comprising:
one or more processors; and
computer-readable media storing first computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving user information including (1) user data associated with users, (2) first user input data indicating prior interactions with the system, (3) a refill schedule associated with medications prescribed to the users, and (4) a refill history associated with medications prescribed to the users;
identifying, based at least in part on the user data, a health indicator associated with a first user of the users, the health indicator including at least one of refill history data, medical history data, social data, or prescription data;
determining, based at least in part on the refill schedule and the first user input data, that a first refill of a first medication prescribed to the first user will occur within a first threshold period of time;
determining, based at least in part on the health indicator, a first probability that the first user will miss refilling the first medication, the first probability associated with a combination of indicators that the first user will miss refilling the first medication;
determining that the first probability exceeds a first probability threshold;
generating a first machine learning model configured to determine a type of reminder;
training the first machine learning model based at least in part on previous interaction data associated with various reminder types such that a first trained machine learning model is generated;
determining, utilizing the first trained machine learning model, the type of reminder to send, wherein the first trained machine learning model utilizes, as input, (1) the health indicator, (2) the refill schedule, (3) the refill history, (4) the first user input data, (5) previous interaction data of the first user with reminder types, (6) computing devices associated with the first user, and (7) software technology associated with the first user;
generating, based at least in part on the determining that the first probability exceeds the first probability threshold, a first reminder to refill the first medication, the first reminder formatted as the type of reminder, wherein generating the first reminder includes generating an interactive link as at least a portion of the first reminder, the interactive link configured to, when selected by the first user:
display a user interface with a list of selectable actions associated with the first reminder, the selectable actions including scheduling a refill, having the medication delivered to the user, arranging transportation of the user to a location associated with the medication, and preparing the medication for an in-person pickup; and
adaptively perform at least one of the selectable actions based at least in part on receiving second user input data indicating selection of the at least one of the selectable actions;
transmitting the first reminder to a device associated with the first user, the first reminder causing an application associated with the device to initiate and cause the user interface to be displayed, the user interface configured to present a visual representation of the first reminder with the interactive link in response to receiving the first reminder at the device;
receiving the second user input data;
generating a second machine learning model configured to predict whether medication fills will be missed;
generating a training dataset corresponding to the health indicator, the first probability, the first reminder, and the second user input data;
training the second machine learning model utilizing at least the training dataset such that a second trained machine learning model is generated by identifying relationships between the health indicator, the first probability, first reminder, and the second user input data;
determining, based at least in part on the refill history, that a second refill of a second medication prescribed to a second user will occur within a second threshold period of time;
generating input data representing health indicators associated with the second user, the input data formatted for input to the second trained machine learning model;
generating, utilizing the second trained machine learning model and the input data, results data indicating the second user will miss refilling the second medication; and
generating, based at least in part on the results data, a second reminder to refill the second medication.
|