| CPC G16H 20/10 (2018.01) [G06N 20/00 (2019.01); G06Q 20/0855 (2013.01)] | 20 Claims |
|
1. A computer-implemented method, comprising:
receiving, at a computing system of an enterprise and via a user interface of an electronic device corresponding to a patient, an indication of a medication prescribed for the patient;
responsive to the receiving, utilizing, by the computing system, a trained machine-learning model to determine respective indications of a plurality of candidate out-of-pocket costs for a prescription of the medication prescribed for the patient;
obtaining, by the computing system, a selection, from among the respective indications of the plurality of candidate out-of-pocket costs, of a particular candidate out-of-pocket cost;
initiating digital processing of the prescription, by at least one computing device, in order to fulfill the prescription at the selected out-of-pocket cost, including:
(i) storing initial information corresponding to the prescription in a patient profile maintained by the enterprise;
(ii) submitting coverage-related data to an insurance provider or payor for verification; and
(iii) electronically conveying a fulfillment instruction to pharmacy personnel so the prescription is ready for physical distribution, all in accordance with the selected out-of-pocket cost;
updating, by the computing system, historical data that is stored in a data store of the computing system and that was utilized to train the machine-learning model, the updating including adding, to the historical data, data that corresponds to a completed filling of the prescription of the patient having the selected out-of-pocket cost;
re-training, by the computing system, the trained machine-learning model by utilizing the updated historical data;
storing, by the computing system, the re-trained machine-learning model at the computing system;
utilizing, by the computing system, the stored, re-trained machine-learning model to determine a respective out-of-pocket cost for at least one of another prescription prescribed for the patient or a prescription prescribed for another patient;
initiating digital processing, by at least one computing device, for another prescription prescribed for the patient or for a prescription prescribed for another patient, the digital processing culminating in fulfillment of the prescription at the respective out-of-pocket cost, including:
(i) electronically storing initial prescription information in a patient profile to reflect the determined out-of-pocket cost;
(ii) submitting coverage-verification data to a payor or insurance provider; and
(iii) conveying a digital fulfillment request to a pharmacy system so that the prescription is dispensed in accordance with the respective out-of-pocket cost; and
filling, by the computing system, the prescription in accordance with the respective out-of-pocket cost determined by the re-trained machine-learning model.
|