Methods, systems, and computer program products for alternative dispensing

Abstract

The method, system, and computer program product for substitute dispensing includes obtaining claims data associated with a claim for a prescription associated with a patient, determining a universal identifier for the prescription based on the claims data, obtaining medication diagnostic data associated with known diagnoses for the universal identifier associated with the prescription, determining possible diagnoses associated with the prescription based on the universal identifier and the medication diagnostic data, determining costs associated with the possible diagnoses based on the claims data, determining potential alternative prescriptions for the prescription using a machine learning model trained based on a training dataset for the possible diagnoses, updating the training dataset to include possible diagnoses associated with the alternative prescription based on user input, and training the machine learning model based on the updated training dataset.

Description

[Technical Field]

[0001] The present disclosure relates to pharmacy substitutions and, in some non-limiting embodiments or aspects, to methods, systems, and computer program products for training and updating machine learning processes for determining substitutions for prescriptions for diagnoses. [Background technology]

[0002] [CROSS-REFERENCE TO RELATED APPLICATIONS] This application claims priority to U.S. Provisional Patent Application No. 63 / 106,214, entitled "Method, System, and Computer Program Product for Alternative Dispensing," filed October 27, 2020, the entire disclosure of which is incorporated by reference in its entirety.

[0003] [Technical Considerations] The pharmacist may recommend substituting one or more prescriptions for one or more other prescriptions prescribed for the patient's condition / disease in order to realize a cost savings with the one or more prescriptions compared to the one or more other prescriptions. Summary of the Invention

[0004] Thus, improved systems, devices, products, apparatus, and / or methods for alternative dispensing are provided.

[0005] According to some non-limiting embodiments or aspects, a computer-implemented method is provided that includes the steps of: obtaining claims data associated with at least one claim for at least one prescription associated with at least one patient, determining at least one universal identifier for the at least one prescription associated with the at least one patient based on the claims data, obtaining medication diagnostic data associated with one or more known diagnoses for the one or more universal identifiers associated with the one or more prescriptions, determining at least one possible diagnosis associated with the at least one prescription for the at least one patient based on the at least one universal identifier and the medication diagnostic data, determining at least one cost associated with the at least one possible diagnosis associated with the at least one prescription based on the claims data, and using a machine learning model trained based on a training dataset. determining, for at least one possible diagnosis, at least one potential alternative prescription for at least one prescription associated with the at least one possible diagnosis using the at least one potential alternative prescription; providing at least one user with savings information associated with the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis; receiving user input from the at least one user associated with the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis; updating a training dataset to include, based on the user input, the at least one possible diagnosis associated with the at least one potential alternative prescription as at least one trained diagnosis; and training a machine learning model based on the updated training dataset.

[0006] In some non-limiting embodiments or aspects, the method further includes one of the following steps: determining whether the at least one possible diagnosis matches one or more confirmed diagnoses in the confirmed dataset, and in response to determining that the at least one possible diagnosis matches one or more confirmed diagnoses in the confirmed dataset, (i) updating the training dataset to include the at least one possible diagnosis associated with the at least one prescription as one or more trained diagnoses, and (ii) updating the trained dataset by adjusting a weight associated with at least one existing trained diagnosis in the training dataset.

[0007] In some non-limiting embodiments or aspects, the method further includes determining a severity level associated with the at least one possible diagnosis based on the at least one possible diagnosis and the confirmed dataset, wherein the severity level is input into at least one machine learning model to determine at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis.

[0008] In some non-limiting embodiments or aspects, the at least one potential alternative prescription is associated with the same severity level as the at least one prescription for the at least one possible diagnosis.

[0009] In some non-limiting embodiments or aspects, the method further includes determining at least one probability associated with the at least one possible diagnosis based on the at least one possible diagnosis and the training dataset, wherein the at least one probability is input into at least one machine learning model to determine at least one potential alternative prescription to the at least one prescription associated with the at least one possible diagnosis.

[0010] In some non-limiting embodiments or aspects, the at least one potential alternative formulation includes at least one of the following: a different drug than the drug associated with the at least one formulation, a different dosage than the dose associated with the at least one formulation, an indication to discontinue use of the drug associated with the at least one formulation, a different formulation of the same drug associated with the at least one formulation, different packaging of the same drug associated with the at least one formulation, or any combination thereof.

[0011] In some non-limiting embodiments or aspects, the at least one cost is further determined based on a current cost associated with the at least one prescription and a future cost associated with the at least one prescription, wherein the future cost differs from the current cost.

[0012] According to some non-limiting embodiments or aspects, a system is provided that includes one or more processors programmed and / or configured to: obtain claims data associated with at least one claim for at least one prescription associated with at least one patient, determine at least one universal identifier for the at least one prescription associated with the at least one patient based on the claims data, obtain medication diagnostic data associated with one or more known diagnoses for the one or more universal identifiers associated with the one or more prescriptions, determine at least one possible diagnosis associated with the at least one prescription for the at least one patient based on the at least one universal identifier and the medication diagnostic data, determine at least one cost associated with the at least one possible diagnosis associated with the at least one prescription based on the claims data, and implement a machine learning model trained based on a training dataset. determining, for at least one possible diagnosis, at least one potential alternative prescription for at least one prescription associated with the at least one possible diagnosis using the at least one potential alternative prescription; providing savings information associated with the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis to at least one user; receiving user input from the at least one user associated with the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis; updating a training dataset to include the at least one possible diagnosis associated with the at least one potential alternative prescription as at least one trained diagnosis based on the user input; and training a machine learning model based on the updated training dataset.

[0013] In some non-limiting embodiments or aspects, the one or more processors are further programmed and / or configured to: determine whether the at least one possible diagnosis matches one or more confirmed diagnoses in the confirmed dataset, and in response to determining that the at least one possible diagnosis matches one or more confirmed diagnoses in the confirmed dataset, one of: (i) updating the trained dataset to include at least one possible diagnosis associated with the at least one prescription as one or more trained diagnoses, and (ii) updating the trained dataset by adjusting a weight associated with at least one existing trained diagnosis in the trained dataset.

[0014] In some non-limiting embodiments or aspects, the one or more processors are further programmed and / or configured to: determine, based on the at least one possible diagnosis and the confirmed dataset, a severity level associated with the at least one possible diagnosis, wherein the severity level is input into at least one machine learning model to determine at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis.

[0015] In some non-limiting embodiments or aspects, the at least one potential alternative prescription is associated with the same severity level as the at least one prescription for the at least one possible diagnosis.

[0016] In some non-limiting embodiments or aspects, the one or more processors determine at least one probability associated with the at least one possible diagnosis based on the at least one possible diagnosis and the training dataset, and the at least one probability is input to at least one machine learning model to determine at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis. The method is further programmed and / or configured to:

[0017] In some non-limiting embodiments or aspects, the at least one potential alternative formulation includes at least one of the following: a different drug than the drug associated with the at least one formulation, a different dosage than the dose associated with the at least one formulation, instructions to discontinue use of the drug associated with the at least one formulation, a different formulation of the same drug associated with the at least one formulation, different packaging of the same drug associated with the at least one formulation, or any combination thereof.

[0018] In some non-limiting embodiments or aspects, the at least one cost is further determined based on a current cost associated with the at least one prescription and a future cost associated with the at least one prescription, wherein the future cost differs from the current cost.

[0019] According to some non-limiting embodiments or aspects, a computer program product is provided that includes at least one non-transitory computer-readable medium including program instructions that, when executed by at least one processor, cause the at least one processor to: obtain claims data associated with at least one claim for at least one prescription associated with at least one patient, determine at least one universal identifier for the at least one prescription associated with the at least one patient based on the claims data, obtain medication diagnostic data associated with one or more known diagnoses for the one or more universal identifiers associated with the one or more prescriptions, determine at least one possible diagnosis associated with the at least one prescription for the at least one patient based on the at least one universal identifier and the medication diagnostic data, determine at least one cost associated with the at least one possible diagnosis associated with the at least one prescription based on the claims data, and implement a machine learning model trained based on a training dataset. determining, for at least one possible diagnosis, at least one potential alternative prescription for at least one prescription associated with the at least one possible diagnosis using the at least one potential alternative prescription; providing savings information associated with the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis to at least one user; receiving user input from the at least one user associated with the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis; updating a training dataset to include the at least one possible diagnosis associated with the at least one potential alternative prescription as at least one trained diagnosis based on the user input; and training a machine learning model based on the updated training dataset.

[0020] In some non-limiting embodiments or aspects, the instructions, when executed by at least one processor, further cause the at least one processor to do one of: determine whether the at least one possible diagnosis matches one or more confirmed diagnoses in the confirmed dataset, and in response to determining that the at least one possible diagnosis matches one or more confirmed diagnoses in the confirmed dataset, (i) update the trained dataset to include at least one possible diagnosis associated with the at least one prescription as one or more trained diagnoses, and (ii) update the trained dataset by adjusting a weight associated with at least one existing trained diagnosis in the trained dataset.

[0021] In some non-limiting embodiments or aspects, the instructions, when executed by at least one processor, further cause the at least one processor to determine, based on the at least one potential diagnosis and the confirmed dataset, a severity level associated with the at least one potential diagnosis, wherein the severity level is input into at least one machine learning model to determine at least one potential alternative prescription for the at least one prescription associated with the at least one potential diagnosis.

[0022] In some non-limiting embodiments or aspects, the at least one potential alternative prescription is associated with the same severity level as the at least one prescription for the at least one possible diagnosis.

[0023] In some non-limiting embodiments or aspects, the instructions, when executed by the at least one processor, further cause the at least one processor to: determine at least one probability associated with the at least one possible diagnosis based on the at least one possible diagnosis and the training dataset, wherein the at least one probability is input into at least one machine learning model to determine at least one potential alternative prescription to the at least one prescription associated with the at least one possible diagnosis.

[0024] In some non-limiting embodiments or aspects, the at least one potential alternative formulation includes at least one of the following: a different drug than the drug associated with the at least one formulation, a different dosage than the dose associated with the at least one formulation, instructions to discontinue use of the drug associated with the at least one formulation, a different formulation of the same drug associated with the at least one formulation, different packaging of the same drug associated with the at least one formulation, or any combination thereof.

[0025] In some non-limiting embodiments or aspects, the at least one cost is further determined based on a current cost associated with the at least one prescription and a future cost associated with the at least one prescription, wherein the future cost differs from the current cost.

[0026] Further non-limiting embodiments or aspects are described in the following numbered clauses:

[0027] Clause 1. A method for detecting a patient's condition using a machine learning model trained based on a training dataset, comprising: obtaining claims data associated with at least one claim for at least one prescription associated with at least one patient; determining, based on the claims data, at least one universal identifier for the at least one prescription associated with the at least one patient; obtaining medication diagnostic data associated with one or more known diagnoses for the one or more universal identifiers associated with the one or more prescriptions; determining, based on the at least one universal identifier and the medication diagnostic data, at least one possible diagnosis associated with the at least one prescription for the at least one patient; determining, based on the claims data, at least one cost associated with the at least one possible diagnosis associated with the at least one prescription; and using a machine learning model trained based on a training dataset, 1. A computer-implemented method comprising: determining, for at least one possible diagnosis, at least one potential alternative prescription for at least one prescription associated with the at least one possible diagnosis; providing at least one user with savings information associated with the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis; receiving user input from the at least one user associated with the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis; updating a training dataset to include, based on the user input, the at least one possible diagnosis associated with the at least one potential alternative prescription as at least one trained diagnosis; and training a machine learning model based on the updated training dataset.

[0028] Clause 2. The computer-implemented method of Clause 1, further comprising one of the steps of: determining whether the at least one possible diagnosis matches one or more confirmed diagnoses in the confirmed dataset; and in response to determining that the at least one possible diagnosis matches one or more confirmed diagnoses in the confirmed dataset, (i) updating the training dataset to include at least one possible diagnosis associated with the at least one prescription as one or more trained diagnoses; and (ii) updating the trained dataset by adjusting a weighting associated with at least one existing trained diagnosis in the trained dataset.

[0029] Clause 3. The computer-implemented method of any one of clauses 1 and 2, further comprising the step of determining a severity level associated with the at least one possible diagnosis based on the at least one possible diagnosis and the confirmed dataset, wherein the severity level is input into at least one machine learning model to determine at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis.

[0030] Clause 4. The computer-implemented method of any one of clauses 1 to 3, wherein at least one potential alternative prescription is associated with the same severity level as at least one prescription for at least one possible diagnosis.

[0031] Clause 5. The computer-implemented method of any one of clauses 1 to 4, further comprising the step of determining at least one probability associated with the at least one possible diagnosis based on at least one possible diagnosis and a training dataset, wherein the at least one probability is input into at least one machine learning model to determine at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis.

[0032] Clause 6. The computer-implemented method of any one of clauses 1 to 5, wherein the at least one potential alternative prescription includes at least one of: a different drug than the drug associated with the at least one prescription; a different dose than the dose associated with the at least one prescription; instructions to discontinue use of the drug associated with the at least one prescription; a different formulation of the same drug associated with the at least one prescription; different packaging of the same drug associated with the at least one prescription; or any combination thereof.

[0033] Clause 7. The computer-implemented method of any one of clauses 1 to 6, wherein the at least one cost is further determined based on a current cost associated with the at least one prescription and a future cost associated with the at least one prescription, the future cost being different from the current cost.

[0034] Clause 8. A system comprising one or more processors programmed and / or configured to: obtain claims data associated with at least one claim for at least one prescription associated with at least one patient; determine at least one universal identifier for the at least one prescription associated with the at least one patient based on the claims data; obtain medication diagnostic data associated with one or more known diagnoses for the one or more universal identifiers associated with the one or more prescriptions; determine at least one possible diagnosis associated with the at least one prescription for the at least one patient based on the at least one universal identifier and the medication diagnostic data; determine at least one cost associated with the at least one possible diagnosis associated with the at least one prescription based on the claims data; and implement a machine learning model trained based on a training dataset. determining, for at least one possible diagnosis, at least one potential alternative prescription for at least one prescription associated with the at least one possible diagnosis using the at least one potential alternative prescription; providing savings information associated with the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis to at least one user; receiving user input from the at least one user associated with the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis; updating a training dataset to include the at least one possible diagnosis associated with the at least one potential alternative prescription as at least one trained diagnosis based on the user input; and training a machine learning model based on the updated training dataset.

[0035] Clause 9. The system of Clause 8, wherein the one or more processors are further programmed and / or configured to determine whether the at least one possible diagnosis matches one or more confirmed diagnoses in the confirmed dataset, and in response to a determination that the at least one possible diagnosis matches one or more confirmed diagnoses in the confirmed dataset, do one of: (i) update the trained dataset to include at least one possible diagnosis associated with the at least one prescription as one or more trained diagnoses; and (ii) update the trained dataset by adjusting a weighting associated with at least one existing trained diagnosis in the trained dataset.

[0036] Clause 10. The system of clause 8 or 9, wherein the one or more processors are further programmed and / or configured to: determine, based on the at least one possible diagnosis and the confirmed dataset, a severity level associated with the at least one possible diagnosis, wherein the severity level is input into at least one machine learning model to determine at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis.

[0037] Clause 11. A system according to any one of clauses 8 to 10, wherein at least one potential alternative prescription is associated with the same severity level as at least one prescription for at least one possible diagnosis.

[0038] Clause 12. The system of any one of clauses 8 to 11, wherein the one or more processors are further programmed and / or configured to: determine at least one probability associated with the at least one possible diagnosis based on the at least one possible diagnosis and the training dataset, wherein the at least one probability is input into at least one machine learning model to determine at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis.

[0039] Clause 13. The system of any one of clauses 8 to 12, wherein the at least one potential alternative prescription includes at least one of a different drug than the drug associated with the at least one prescription, a different dose than the dose associated with the at least one prescription, instructions to discontinue use of the drug associated with the at least one prescription, a different formulation of the same drug associated with the at least one prescription, different packaging of the same drug associated with the at least one prescription, or any combination thereof.

[0040] Clause 14. The system of any one of clauses 8 to 13, wherein the at least one cost is further determined based on a current cost associated with the at least one prescription and a future cost associated with the at least one prescription, the future cost being different from the current cost.

[0041] Clause 15. A computer program product comprising at least one non-transitory computer-readable medium comprising program instructions that, when executed by at least one processor, cause the at least one processor to: obtain claims data associated with at least one claim for at least one prescription associated with at least one patient, determine at least one universal identifier for the at least one prescription associated with the at least one patient based on the claims data, obtain medication diagnostic data associated with one or more known diagnoses for the one or more universal identifiers associated with the one or more prescriptions, determine at least one possible diagnosis associated with the at least one prescription for the at least one patient based on the at least one universal identifier and the medication diagnostic data, determine at least one cost associated with the at least one possible diagnosis associated with the at least one prescription based on the claims data, and implement a machine learning model trained based on a training dataset. determining, for at least one possible diagnosis, at least one potential alternative prescription for at least one prescription associated with the at least one possible diagnosis using the at least one potential alternative prescription; providing savings information associated with the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis to at least one user; receiving user input from the at least one user associated with the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis; updating a training dataset to include the at least one possible diagnosis associated with the at least one potential alternative prescription as at least one trained diagnosis based on the user input; and training a machine learning model based on the updated training dataset.

[0042] Clause 16. The computer program product of Clause 15, wherein the instructions, when executed by at least one processor, further cause the at least one processor to determine whether the at least one potential diagnosis matches one or more confirmed diagnoses in the confirmed dataset, and in response to a determination that the at least one potential diagnosis matches one or more confirmed diagnoses in the confirmed dataset, further perform one of: (i) updating the trained dataset to include at least one potential diagnosis associated with the at least one prescription as one or more trained diagnoses; and (ii) updating the trained dataset by adjusting a weighting associated with at least one existing trained diagnosis in the trained dataset.

[0043] Clause 17. The computer program product of clause 15 or clause 16, wherein the instructions, when executed by the at least one processor, further cause the at least one processor to: determine a severity level associated with the at least one possible diagnosis based on the at least one possible diagnosis and the confirmed dataset, wherein the severity level is input into at least one machine learning model to determine at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis.

[0044] Clause 18. The computer program product of any one of clauses 15 to 17, wherein at least one potential alternative prescription is associated with the same severity level as at least one prescription for at least one possible diagnosis.

[0045] Clause 19. A computer program product as described in any one of clauses 15 to 18, wherein the instructions, when executed by at least one processor, further cause the at least one processor to determine at least one probability associated with the at least one possible diagnosis based on the at least one possible diagnosis and the training dataset, wherein the at least one probability is input into at least one machine learning model to determine at least one potential alternative prescription to the at least one prescription associated with the at least one possible diagnosis.

[0046] Clause 20. The computer program product of any one of clauses 15 to 19, wherein the at least one potential alternative prescription includes at least one of: a different drug than the drug associated with the at least one prescription; a different dose than the dose associated with the at least one prescription; instructions to discontinue use of the drug associated with the at least one prescription; a different formulation of the same drug associated with the at least one prescription; different packaging of the same drug associated with the at least one prescription; or any combination thereof.

[0047] Clause 21. The computer program product of any one of clauses 15 to 20, wherein the at least one cost is further determined based on a current cost associated with the at least one prescription and a future cost associated with the at least one prescription, the future cost being different from the current cost.

[0048] These and other features and characteristics of the present disclosure, as well as the method of operation and function of the associated elements of structure, combination of parts and economies of manufacture, will become more apparent from a consideration of the following description and appended claims, taken in conjunction with the accompanying drawings, all of which form a part hereof, and in which like reference numerals indicate corresponding parts in the various views. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of limitations. As used in this specification and claims, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. [Brief explanation of the drawings]

[0049] Further advantages and details are explained in more detail below with reference to exemplary embodiments shown in the accompanying schematic drawings. [Figure 1] FIG. 1 illustrates a non-limiting embodiment or aspect of an environment in which the systems, devices, products, apparatus, and / or methods described herein may be implemented. [Figure 2] FIG. 2 is a diagram of a non-limiting embodiment or aspect of one or more devices and / or components of one or more systems of FIG. 1. [Figure 3A] 1 is a flow chart of a non-limiting embodiment or aspect of a process for substitution dispensing. [Figure 3B] 1 is a flow chart of a non-limiting embodiment or aspect of a process for substitution dispensing. [Figure 4] 1 is a flow chart of a non-limiting embodiment or aspect of a process for substitution dispensing. [Figure 5] 1 is a flow chart of a non-limiting embodiment or aspect of a process for substitution dispensing. [Figure 6] 1 is a flow chart of a non-limiting embodiment or aspect of a process for substitution dispensing. [Figure 7] FIG. 10 illustrates examples of potential rules that may be discovered by a process for substitution dispensing. DETAILED DESCRIPTION OF THE INVENTION

[0050] It is to be understood that the present disclosure may contemplate various alternative modifications and step sequences unless expressly specified to the contrary. It is also to be understood that the specific devices and processes illustrated in the accompanying drawings, and described in the following specification, are merely exemplary and not limiting embodiments or aspects. Hence, specific dimensions and other physical characteristics related to the embodiments or aspects disclosed herein are not to be considered limiting.

[0051] No aspect, component, element, structure, operation, step, function, instruction, etc. used herein should be construed as critical or essential unless expressly stated as such. Also, as used herein, the articles "a" and "an" are intended to include one or more items and may be used interchangeably with "one or more" and "at least one." Furthermore, as used herein, the term "set" is intended to include one or more items (e.g., related items, unrelated items, a combination of related and unrelated items, etc.) and may be used interchangeably with "one or more" or "at least one." Where only one item is intended, the term "one" or similar term is used. Also, as used herein, terms such as "has," "have," and "having" are intended to be open-ended terms. Furthermore, the phrase "based on" is intended to mean "based at least in part on," unless otherwise specified.

[0052] As used herein, the term “communication” may refer to receiving, accepting, sending, forwarding, providing, etc., data (e.g., information, signals, messages, instructions, commands, etc.). A unit (e.g., a device, a system, a component of a device or system, a combination thereof, etc.) communicating with another unit means that the unit can receive information and / or send information directly or indirectly from the other unit. This may refer to a direct connection or an indirect connection (e.g., a direct communication connection, an indirect communication connection, etc.) that is wired and / or wireless in nature. Furthermore, two units can communicate with each other even if the information being transmitted may be modified, processed, relayed, and / or routed between the first and second units. For example, a first unit can communicate with a second unit even if the first unit passively receives information and does not actively transmit information to the second unit. As another example, a first unit can communicate with a second unit if at least one intermediate unit processes information received from the first unit and communicates the processed information to the second unit.

[0053] It will be apparent that the systems and / or methods described herein may be implemented in different forms of hardware, software, or a combination of hardware and software. The actual specialized control hardware or software code used to implement these systems and / or methods is not intended to limit the implementation. Thus, the operation and behavior of the systems and / or methods are described herein without reference to specific software code, and it will be understood that software and hardware can be designed to implement the systems and / or methods based on the description herein.

[0054] Some non-limiting embodiments or aspects are described herein in relation to a threshold value. As used herein, meeting a threshold may refer to a value being greater than the threshold, more than the threshold, higher than the threshold, equal to or greater than the threshold, less than the threshold, less than the threshold, less than the threshold, lower than the threshold, equal to or less than the threshold, etc.

[0055] As used herein, the term "mobile device" may refer to one or more portable electronic devices configured to communicate with one or more networks. By way of example, a mobile device may include a mobile phone (e.g., a smartphone or a standard mobile phone), a portable computer (e.g., a tablet computer, a laptop computer, etc.), a wearable device (e.g., a watch, eyeglasses, lenses, clothing, etc.), a personal digital assistant (PDA), and / or other similar devices. As used herein, the terms "client device" and "user device" refer to any electronic device configured to communicate with one or more servers or remote devices and / or systems. A client device or user device may include a mobile device, a network-enabled appliance (e.g., a network-enabled television, a refrigerator, a thermostat, etc.), a computer, a point-of-sale system, and / or other device or system capable of communicating with a network.

[0056] As used herein, the term "computing device" may refer to one or more electronic devices configured to process data. In some examples, a computing device may include components necessary to receive, process, and output data, such as a processor, a display, a memory, an input device, a network interface, etc. A computing device may be a mobile device. By way of example, a mobile device may include a mobile phone (e.g., a smartphone or a standard mobile phone), a portable computer, a wearable device (e.g., a watch, glasses, lenses, clothing, etc.), a PDA, and / or other similar devices. A computing device may also be a desktop computer or other form of non-mobile computer.

[0057] As used herein, the terms “server” and / or “processor” may refer to or include one or more computing devices operated by or facilitating communication and processing for multiple parties in a network environment, such as the Internet, although it will be understood that communication may be readily accomplished via one or more public or private network environments, and that various other configurations are possible. Furthermore, multiple computing devices (e.g., servers, POS devices, mobile devices, etc.) communicating directly or indirectly in a network environment may constitute a “system.” As used herein, references to a “server” or “processor” may refer to a previously-mentioned server and / or processor, a different server and / or processor, and / or a combination of servers and / or processors that are referred to as performing a previous step or function. For example, as used in the specification and claims, a first server and / or a first processor stated to perform a first step or function may refer to the same or a different server and / or processor stated to perform a second step or function.

[0058] As used herein, the term "application programming interface" (API) may refer to computer code that enables communication between different systems or (hardware and / or software) components of a system. For example, an API may include function calls, functions, subroutines, communication protocols, fields, etc. that are usable and / or accessible by other systems or other (hardware and / or software) components of a system.

[0059] As used herein, the terms "user interface" or "graphical user interface" refer to a generated display, such as one or more graphical user interfaces (GUIs), with which a user can interact directly or indirectly (e.g., through a keyboard, mouse, touch screen, etc.).

[0060] Non-limiting embodiments or aspects of the present disclosure may compare a patient's medical and drug claims with those of other patients to determine likely diagnoses, drug-to-diagnosis equivalencies, and / or diagnosis severity, and use that determination to identify drug-drug combinations that reduce or minimize the cost of treatment by suggesting clinically equivalent changes to drug prescriptions. For example, non-limiting embodiments or aspects of the present disclosure may learn and understand the nuances of clinical equivalence in prescriptions. As an example, for a patient taking a 10 mg tablet of a drug that costs $X, if the same drug is currently available in a 25 mg dose, also priced at $X, a pharmacist may split the 25 mg tablet in half, saving 50%, because they know that half of the 25 mg is clinically equivalent to the 10 mg. In such an example, a non-limiting embodiment or aspect of the present disclosure may automatically learn to recognize that 10 mg is clinically equivalent to 12.5 mg (e.g., learned / trained behavior that X can be equal to Y, etc., if certain other criteria are met, etc.).

[0061]

[0023] Referring now to Figure 1, Figure 1 is a diagram of an example environment 100 in which the devices, systems, methods, and / or products described herein may be implemented. As shown in Figure 1, the environment 100 includes a transaction substitution system 102, one or more data sources 104, and / or a communication network 106. The substitution system 102 and the one or more data sources may be interconnected (e.g., establish a connection to communicate) via a wired connection, a wireless connection, or a combination of wired and wireless connections.

[0062] The replacement system 102 may include one or more devices capable of receiving information and / or data from one or more data sources 104 via a communication network 106 and / or communicating information and / or data to one or more data sources 104 via a communication network 106. For example, the replacement system 102 may include computing devices such as a server, a group of servers, and / or other similar devices.

[0063] The one or more data sources 104 may include one or more devices that can receive information and / or data from the replacement system 102 via the communications network 106 and / or that can communicate information and / or data to the replacement system 102 via the communications network 106. For example, the one or more data sources may include computing devices such as a server, a group of servers, and / or other similar devices. In some non-limiting embodiments or aspects, the one or more data sources 104 may include one or more databases.

[0064] The communication network 106 may include one or more wired and / or wireless networks. For example, the communication network 106 may include a cellular network (e.g., a Long Term Evolution (LTE) network, a third generation (3G) network, a fourth generation (4G) network, a fifth generation (5G) network, a code division multiple access (CDMA) network, etc.), a public land mobile network (PLMN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a telephone network (e.g., a public switched telephone network (PSTN)), a private network, an ad hoc network, an intranet, the Internet, a fiber optic-based network, a cloud computing network, etc., and / or combinations thereof or other types of networks.

[0065] The number and arrangement of devices and systems shown in Figure 1 are provided as an example. There may be additional, fewer, different, or differently arranged devices and / or systems relative to those shown in Figure 1. Furthermore, two or more devices and / or systems shown in Figure 1 may be implemented within a single device and / or system, or a single device and / or system shown in Figure 1 may be implemented as multiple distributed devices and / or systems. Additionally or alternatively, a set of devices and / or systems (e.g., one or more devices or systems) of environment 100 may perform one or more functions described as being performed by another set of devices and / or systems of environment 100.

[0066] 2, which is a diagram of example components of a device 200. The device 200 may correspond to one or more devices of the replacement system 102 and / or one or more devices of the one or more data sources 104. In some non-limiting embodiments or aspects, the one or more devices of the replacement system 102 and / or one or more devices of the one or more data sources 104 may include at least one device 200 and / or at least one component of the device 200. As shown in FIG. 2, the device 200 may include a bus 202, a processor 204, a memory 206, a storage component 208, an input component 210, an output component 212, and a communication interface 214.

[0067] The bus 202 may include components that enable communication between the components of the device 200. In some non-limiting embodiments or aspects, the processor 204 may be implemented in hardware, software, or a combination of hardware and software. For example, the processor 204 may include a processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), etc.), a microprocessor, a digital signal processor (DSP), and / or any processing component that can be programmed to perform a function (e.g., a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), etc.). The memory 206 may include random access memory (RAM), read-only memory (ROM), and / or another type of dynamic or static storage device that stores information and / or instructions for use by the processor 204 (e.g., flash memory, magnetic memory, optical memory).

[0068] The storage component 208 may store information and / or software related to the operation and use of the device 200. For example, the storage component 208 may include a hard disk (e.g., a magnetic disk, optical disk, magneto-optical disk, solid-state disk, etc.), a compact disk (CD), a digital versatile disk (DVD), a floppy disk, a cartridge, a magnetic tape, and / or another type of computer-readable medium along with a corresponding drive.

[0069] Input components 210 may include components that enable device 200 to receive information, such as through user input (e.g., a touchscreen display, a keyboard, a keypad, a mouse, buttons, switches, a microphone, etc.). Additionally or alternatively, input components 210 may include sensors for sensing information (e.g., a global positioning system (GPS) component, an accelerometer, a gyroscope, an actuator, etc.). Output components 212 may include components that provide output information from device 200 (e.g., a display, a speaker, one or more light-emitting diodes (LEDs), etc.).

[0070] Communications interface 214 may include transceiver-like components (e.g., a walkie-talkie, a separate receiver and transmitter, etc.) that enable device 200 to communicate with other devices, such as via a wired connection, a wireless connection, or a combination of wired and wireless connections. Communications interface 214 may enable device 200 to receive information from and / or provide information to another device. For example, communications interface 214 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wi-Fi interface, a cellular interface, a network interface, etc.

[0071] The device 200 may perform one or more processes described herein. The device 200 may perform these processes based on a processor 204 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), etc.) that may execute software instructions stored by a computer-readable medium, such as a memory 206 and / or a storage component 208. A computer-readable medium (e.g., a non-transitory computer-readable medium) is defined herein as a non-transitory memory device. A memory device includes memory space within a single physical storage device or memory space spanning multiple physical storage devices.

[0072] Software instructions may be loaded into memory 206 and / or storage component 208 via communications interface 214, from another computer-readable medium, or from another device. When executed, the software instructions stored in memory 206 and / or storage component 208 may cause processor 204 to perform one or more processes described herein. Additionally or alternatively, hardwired circuitry may be used in place of or in combination with software instructions to perform one or more processes described herein. Thus, embodiments or aspects described herein are not limited to any specific combination of hardware circuitry and software.

[0073] The memory 206 and / or storage component 208 may include a data storage or one or more data structures (e.g., databases, etc.). The device 200 may be capable of receiving information from, storing information, communicating information, or retrieving information stored in the data storage or one or more data structures in the memory 206 and / or storage component 208.

[0074] The number and arrangement of components shown in Figure 2 are provided as an example. In some non-limiting embodiments or aspects, device 200 may include additional, fewer, different, or differently arranged components relative to those shown in Figure 2. Additionally or alternatively, a set of components (e.g., one or more components) of device 200 may perform one or more functions described as being performed by another set of components of device 200.

[0075] 3A and 3B, which are flowcharts of non-limiting embodiments or aspects of a process 300 for substitution dispensing. In some non-limiting embodiments or aspects, one or more of the steps of process 300 may be performed (e.g., fully, partially, etc.) by replacement system 102 (e.g., one or more devices of replacement system 102, etc.). In some non-limiting embodiments or aspects, one or more steps of process 500 may be performed (e.g., fully, partially, etc.) by another device or group of devices, such as a user device (e.g., one or more devices of a system of user devices, etc.), separate from or including replacement system 102.

[0076] 3A, at step 302, process 300 includes obtaining claims data. For example, substitution system 102 may obtain claims data associated with at least one claim for at least one prescription associated with at least one patient. As an example, substitution system 102 may obtain claims data from one or more data sources 104 (e.g., claims databases, electronic health record (EHR) databases, etc.), patients, and / or healthcare professionals.

[0077] The claims data may include at least one of the following parameters associated with a claim and / or prescription associated with a patient: Namely, billing identifier, record identifier, patient identifier, patient name, patient date of birth, patient gender, last filled prescription data, prescription bill date, next prescription fill date, insurance payment amount, patient copayment amount, primary care provider's national provider identifier (e.g., NPI, GMC, etc.), primary care provider name, prescriber's national provider identifier (e.g., NPI, GMC, etc.), prescribed drug national and / or international drug code (e.g., NDC, MPID, PhPID, etc.), quantity of prescribed drug, number of days of prescribed drug supply, date of record identifier generation, insurance company and / or other payor, insurance plan and / or other health benefit coverage, patient insurance and / or health benefit expiration date, location and / or name of pharmacy filling the prescription, national and / or international drug code (e.g., NDC, MPID, PhPID, etc.), unique identifier providing normalized and / or standardized concept identifier name for clinical drugs (e.g., RxNorm Concept Unique Identifier (CUI), Dictionary of Medicine and Device (dm+d) identifier, Australian Medical Terminology (AMT) identifier, Drug Bank ID, etc.), drug name, or a combination thereof.

[0078] In some non-limiting embodiments or aspects, the claims data includes at least one of the following types of data: cost data, drug diagnostic data, patient diagnostic data, cost data, prospective data, or any combination thereof.

[0079] 3A, at step 304, process 300 includes determining a universal identifier associated with a prescription. For example, substitution system 102 may determine at least one universal identifier (e.g., RxNorm identifier, RxNormCUI, dm+d, AMT, etc.) for at least one prescription associated with at least one patient based on claims data. As an example, substitution system 102 may identify, for each patient, at least one active prescription associated with the patient based on the next fill date(s) of prescriptions in claims data associated with that patient that have a future date, and / or substitution system 102 may determine, for that patient, by mapping national and / or international drug codes (e.g., NDC, MPID, PhPID, etc.) of medications associated with at least one active prescription to a unique identifier (e.g., RxNormCUI, dm+d, AMT, etc.) associated with the medication (e.g., using mapping provided by the National Library of Medicine, NHS Drug Database, Drug Bank, etc.). Additionally or alternatively, if a unique identifier (e.g., RxNormCUI / RxCUI, Drug Bank ID, etc.) that normalizes national or international drug codes (e.g., NDC, MPID, etc.) to clinical drugs and / or provides standardized conceptual identifier names is not available, the substitution system 102 may be trained (e.g., by a pharmacist as an automated Levenshtein distance mapping / matching algorithm for drug names) to create an equivalent mapping of drugs and / or prescriptions to generic identifiers.

[0080] 3A , at step 306, process 300 includes obtaining medication diagnostic data. For example, substitution system 102 may obtain medication diagnostic data associated with one or more known diagnoses for one or more universal identifiers associated with one or more prescriptions. As an example, substitution system 102 may obtain medication diagnostic data from one or more data sources 104. In such an example, substitution system 102 may use a mapping (e.g., a mapping provided by the National Library of Medicine, an NHS drug database, a drug bank database, etc.) to map a unique identifier (e.g., RxNormCUI) to known diagnoses (e.g., symptoms, diseases, etc.) and / or International Classification of Diseases (ICD) codes to determine one or more known diagnoses (and / or ICD codes) for one or more universal identifiers associated with one or more prescriptions. Additionally or alternatively, if RxNormCUI to known diagnosis mapping is not available, the substitution system 102 can be trained (e.g., by a pharmacist as an automated Levenshtein distance mapping / matching algorithm on RxNormCUI) to create an equivalent mapping of generic identifiers to diagnoses.

[0081] In some non-limiting embodiments or aspects, the medication diagnostic data includes patient diagnostic data. For example, the substitution system 102 may obtain patient diagnostic data associated with one or more patients. As an example, the substitution system 102 may obtain the patient diagnostic data from one or more data sources 104. In such an example, the substitution system 102 may use a mapping that associates a patient identifier with a confirmed diagnosis (and / or the severity level of the confirmed diagnosis) for the patient associated with the patient identifier. For example, the confirmed diagnosis and / or its severity level may be provided by the patient and / or a medical professional, and / or the substitution system 102 may analyze medical claims and / or electronic health records (EHRs) associated with the patient to determine the confirmed diagnosis and / or its severity level associated with the patient.

[0082] As shown in FIG. 3A, at step 308, process 300 includes determining a possible diagnosis associated with the prescription. For example, substitution system 102 may determine at least one possible diagnosis associated with at least one prescription for at least one patient based on at least one universal identifier and medication diagnosis data. As an example, substitution system 102 may automatically determine one or more medications to be prescribed for at least one patient for at least one possible diagnosis using an iterative learning process and universal identifier to known diagnosis mapping. Further details regarding non-limiting embodiments or aspects of step 308 of process 300 are provided below with respect to FIGS. 4-6.

[0083] Reference is now also made to Figure 4, which is a flowchart of a non-limiting embodiment or aspect of a process 400 for replacement dispensing. In some non-limiting embodiments or aspects, one or more steps of process 400 may be performed (e.g., fully, partially, etc.) by replacement system 102 (e.g., one or more devices of replacement system 102, etc.). In some non-limiting embodiments or aspects, one or more steps of process 500 may be performed (e.g., fully, partially, etc.) by another device or group of devices, such as a user device (e.g., one or more devices of a system of user devices, etc.), separate from or including replacement system 102.

[0084] 4, in step 402, process 400 includes generating a unique hash associated with the patient. For example, the substitution system 102 may generate the unique hash, LikelyHASH, associated with the patient by combining a patient identifier associated with a universal identifier (such as that generated in step 304) with a diagnosis associated with the same universal identifier (such as the same RxNormCUI). As an example, the unique hash, LikelyHASH, may include an ascending list of universal identifiers (e.g., CUI, etc.) for each possible diagnosis (e.g., diabetes, ketoacidosis, etc.) for each patient.

[0085] If a patient is associated with multiple diagnoses, the patient may be associated with multiple unique hashes, LikelyHash. For example, for two example patients, Patient 1 and Patient 2, the following example unique hashes may be generated: Patient 1: LikelyHASH(CUI1,CUI2,CUI3) corresponds to possible diabetes for Patient 1; Patient 2: LikelyHASH(CUI1,CUI2,CUI5) corresponds to possible diabetes for Patient 2; and Patient 1: LikelyHASH(CUI4,CUI5) corresponds to possible ketoacidosis for Patient 1. By way of example, a unique hash, LikelyHASH, may include any number of CUIs for a particular diagnosis and / or CUIs for different diagnoses may overlap. For example, the example unique hash, LikelyHASH(CUI1,CUI2,CUI3), may also be the same as, for example, a possible ketoacidosis diagnosis for Patient 1.

[0086] 4, at step 404, process 400 includes determining whether the unique hash matches a training hash. For example, substitution system 102 may determine whether the unique hash, LikelyHASH, matches a TrainingHASH stored in the training data set. As an example, substitution system 102 may compare each unique hash, LikelyHASH, with a TrainingHASH previously stored in the training data set.

[0087] 4, at step 406, process 400 includes converting the unique hash to one or more updated hashes in response to determining that the unique hash matches the training hash. For example, substitution system 102 may convert the unique hash LikelyHASH to one or more updated hash(s) UpgradedHASH(s) in response to determining that the unique hash LikelyHASH matches one or more TrainingHASH stored in the training data set. As an example, for each match that the unique hash LikelyHASH has in the training data set, an updated hash UpgradedHASH may be generated such that a single unique hash LikelyHASH can generate multiple UpgradedHASHs.

[0088] 4, at step 408, process 400 includes, in response to determining that the unique hash does not match the training hash, maintaining the unique hash. For example, substitution system 102 may maintain the unique hash LikelyHASH (e.g., not transform the unique hash LikelyHASH) in response to determining that the unique hash LikelyHASH does not match any TrainingHASH stored in the training data set.

[0089] As shown in FIG. 4 , at step 410, process 400 includes determining whether a patient identifier associated with the unique hash (and / or updated hash) is mapped to a confirmed diagnosis. For example, the substitution system 102 may determine whether a patient identifier associated with the unique hash identifier LikelyHASH (and / or updated hash(s) UpgradedHASH(es)) is mapped to a confirmed diagnosis. As an example, the substitution system 102 may use a mapping that maps a patient identifier to a confirmed diagnosis (and / or the severity level of the confirmed diagnosis) for the patient associated with the patient identifier. For example, the confirmed diagnosis and / or its severity level may be provided by the patient and / or a medical professional, and / or the substitution system 102 may analyze medical claims and / or electronic health records (EHRs) associated with the patient to determine the confirmed diagnosis and / or its severity level associated with the patient.

[0090] 4, at step 412, process 400 includes generating a confirmed hash in response to determining that the patient identifier associated with the unique hash (and / or updated hash(s)) maps to the confirmed diagnosis. For example, substitution system 102 may generate a confirmed hash ConfirmedHASH(CUI1,CUI2,...CIUn) in response to determining that the patient identifier associated with the unique hash LikelyHASH (and / or updated hash(s) UpgradedHASH(s)) maps to the confirmed diagnosis. As an example, substitution system 102 may combine the patient identifier associated with the unique hash LikelyHASH (and / or updated hash(s) UpgradedHASH(s)) with the confirmed diagnosis associated with the same patient identifier to generate a confirmed hash ConfirmedHASH(CUI1,CUI2,...CIUn).

[0091] As shown in FIG. 4 , in step 414, process 400 may, in response to determining that the patient identifier associated with the unique hash (and / or updated hash(s)) does not map to a confirmed diagnosis, processing may proceed directly to step 502 of process 500 of FIG. 5 or may proceed directly to step 602 of process 600 of FIG. 6 . For example, substitution system 102 may, in response to determining that the patient identifier associated with the unique hash LikelyHASH (and / or updated hash(s) UpgradedHASH(s)) does not map to a confirmed diagnosis, proceed to step 418 without generating a confirmed hash. In such an example, the updated hash UpgradedHASH may be associated with a higher probability of diagnosis than the un-updated / unconverted unique hash LikelyHASH. As an example, substitution system 102 may provide a list of the updated hash(s) UpgradedHASH(s) and the unique hashes LikelyHASH.

[0092] 4, in step 416, process 400 includes, in response to generating the confirmed hash, generating a training hash for each unique hash (and / or each updated hash(s)) that matches the confirmed hash, and updating the training dataset based on the generated training hashes. For example, in response to generating the confirmed hash ConfirmedHASH, substitution system 102 may generate a training hash TrainingHASH for each unique hash LikelyHash and / or each updated hash(s) UpgradedHASH that match the confirmed hash ConfirmedHASH, and may update the training dataset based on the generated training hash TrainingHASH. As an example, if the training dataset does not already have a training hash the same as the generated training hash TrainingHASH (e.g., a matching or equivalent hash), the substitution system 102 may update the training dataset to include the generated training hash TrainingHASH; if the training dataset already has a training hash the same as the generated training hash TrainingHASH, the substitution system 102 may update the training dataset by adjusting the weighting associated with the training hash TrainingHASH (e.g., increasing the count associated with the training hash TrainingHASH in the training dataset by 1). In such an example, the substitution system 102 may provide a list of confirmed hash(s) ConfirmedHASH(s), updated hash(s) UpgradedHASH(s), and unique hashes LikelyHASH, displayed in descending order of likelihood that the hashes represent prescription medications the patient is taking for each diagnosis.

[0093] Thus, after sufficient iterations of process 400, the training hash(s) TrainingHASH(s) for each diagnosis in the training dataset may become stronger and / or more likely to be a statistically correct diagnosis, which may be reflected in the updated hash UpgradedHASH used in step 406. For example, each action taken by a clinician may turn into incremental knowledge that is refined over time; if multiple clinicians begin to dismiss or ignore potential substitutions of a particular prescription for a particular type of patient (e.g., males aged 30-40), substitution system 102 may learn to consider patient attributes associated with that particular type of patient.

[0094] Reference is now also made to Figure 5, which is a flowchart of a non-limiting embodiment or aspect of a process 500 for replacement dispensing. In some non-limiting embodiments or aspects, one or more steps of process 500 may be performed (e.g., completely, partially, etc.) by replacement system 102 (e.g., one or more devices of replacement system 102, etc.). In some non-limiting embodiments or aspects, one or more steps of process 500 may be performed (e.g., completely, partially, etc.) by another device or group of devices, such as a user device (e.g., one or more devices of a system of user devices, etc.), separate from or including replacement system 102.

[0095] 5, in step 502, process 500 includes generating a unique severity hash associated with the patient. For example, substitution system 102 may generate the unique severity hash, LikelySeverityHASH, associated with the patient by combining a patient identifier associated with a universal identifier (e.g., as generated in step 304) and the severity of a diagnosis associated with the same universal identifier (e.g., the same RxNormCUI). As an example, the unique severity hash, LikelySeverityHASH, may include an ascending list of universal identifiers (e.g., CUIs) for each possible severity of each diagnosis (e.g., mild diabetes, moderate diabetes, severe diabetes, etc.) for each patient.

[0096] If a patient is associated with multiple diagnoses, the patient may be associated with multiple unique severity hashes, LikelySeverityHASH. For example, for two example patients, Patient 1 and Patient 2, the following example unique severity hashes may be generated: Patient 1:LikelySeverityHASH(CUI1,CUI2,CUI3) corresponds to Patient 1's likely severe diabetes; Patient 2:LikelySeverityHASH(CUI1,CUI2,CUI5) corresponds to Patient 2's likely moderate diabetes; and Patient 1:LikelySeverityHASH(CUI4,CUI5) corresponds to Patient 1's likely severe ketoacidosis. By way of example, the unique severity hash, LikelySeverityHASH, may include any number of CUIs for the severity of a particular diagnosis and / or may have overlapping CUIs for diagnoses of different severity.

[0097] 5, at step 504, process 500 includes determining whether the unique severity hash matches a training severity hash. For example, substitution system 102 may determine whether the unique severity hash, LikelySeverityHASH, matches a TrainingSeverityHASH stored in the training data set. As an example, substitution system 102 may compare each unique severity hash, LikelySeverityHASH, with a TrainingSeverityHASH previously stored in the training data set.

[0098] 5, at step 506, process 500 includes converting the unique severity hash to one or more updated severity hashes in response to determining that the unique severity hash matches the training severity hash. For example, substitution system 102 may convert the unique severity hash LikelySeverityHASH to one or more updated severity hashes UpgradedSeverityHASH(es) in response to determining that the unique severity hash LikelySeverityHASH matches one or more TrainingSeverityHASH stored in the training data set. As an example, for each match that the unique severity hash LikelySeverityHASH has in the training data set, an updated severity hash UpgradedSeverityHASH may be generated, such that a single unique severity hash LikelySeverityHASH may generate multiple UpgradedSeverityHASHes.

[0099] 5, at step 508, process 500 includes, in response to determining that the unique severity hash does not match the training severity hash, maintaining the unique severity hash. For example, substitution system 102 may maintain the unique severity hash LikelySeverityHASH (e.g., not transform the unique severity hash LikelySeverityHASH) in response to determining that the unique severity hash LikelySeverityHASH does not match any TrainingSeverityHASH stored in the training dataset.

[0100] 5, at step 510, process 500 includes determining whether a patient identifier associated with the unique severity hash (and / or updated severity hash) maps to the confirmed severity of the diagnosis. For example, substitution system 102 may determine whether a patient identifier associated with the unique severity hash identifier LikelySeverityHASH (and / or updated severity hash(s) UpgradedSeverityHASH(s)) maps to the confirmed severity of the diagnosis. As an example, substitution system 102 may use a mapping that maps a patient identifier to the confirmed severity of the diagnosis of the patient associated with that patient identifier. For example, the confirmed severity of the diagnosis may be provided by the patient and / or a medical professional, and / or substitution system 102 may analyze a medical claim associated with the patient to determine the confirmed severity of the diagnosis associated with the patient.

[0101] 5, at step 512, process 500 includes generating a confirmed severity hash in response to determining that the patient identifier associated with the unique severity hash (and / or updated severity hash(s)) maps to the confirmed severity of the diagnosis. For example, substitution system 102 may generate a confirmed severity hash ConfirmedSeverityHASH(CUI1,CUI2,...CIUn) in response to determining that the patient identifier associated with the unique severity hash LikelySeverityHASH (and / or updated severity hash(s) UpgradedSeverityHASH(s)) maps to the confirmed severity of the diagnosis. As an example, the replacement system 102 may combine a patient identifier associated with a unique severity hash LikelySeverityHASH (and / or updated severity hash(s) UpgradedSeverityHASH(s)) with the confirmed severity of a diagnosis associated with the same patient identifier to generate a confirmed severity hash ConfirmedSeverityHASH(CUI1,CUI2,...CIUn).

[0102] As shown in Figure 5, in step 514, process 500 may, in response to a determination that the patient identifier associated with the unique severity hash (and / or updated severity hash(s)) does not map to the confirmed severity of the diagnosis, processing may proceed directly to step 602 of process 600 of Figure 6. For example, in response to a determination that the patient identifier associated with the unique severity hash LikelySeverityHASH (and / or updated severity hash(s) UpgradedSeverityHASH(s)) does not map to the confirmed severity of the diagnosis, substitution system 102 may proceed to step 518 without generating a confirmed severity hash. In such an example, the updated severity hash UpgradedSeverityHASH may be associated with the severity of the diagnosis with a higher probability than the un-updated / unconverted unique severity hash LikelySeverityHASH. As an example, the replacement system 102 may provide a list of updated severity hashes(s) UpgradedSeverityHASH(s) and unique severity hashes LikelySeverityHASH.

[0103] 5, in step 516, process 500 includes, in response to generating the confirmed severity hash, generating a training severity hash for each unique severity hash (and / or each updated severity hash(s)) that matches the confirmed severity hash, and updating the training dataset based on the generated training severity hashes. For example, in response to generating the confirmed severity hash, ConfirmedSeverityHASH, the replacement system 102 may generate a training severity hash, TrainingSeverityHASH, for each unique severity hash, LikelySeverityHash, and / or each updated severity hash, UpgradedSeverityHASH(s), that matches the confirmed severity hash, ConfirmedHASH, and may update the training dataset based on the generated training hash, TrainingSeverityHASH. As an example, if the same (e.g., matching or equivalent) training severity hash as the generated training severity hash TrainingSeverityHASH is not already stored in the training dataset, the replacement system 102 may update the training dataset to include the generated training severity hash TrainingSeverityHASH, and if the same training severity hash as the generated training severity hash TrainingSeverityHASH is already stored in the training dataset, the replacement system 102 may update the training dataset by adjusting the weighting associated with the training severity hash TrainingSeverityHASH (e.g., increasing the count associated with the training severity hash TrainingSeverityHASH in the training dataset by 1).In such an example, the replacement system 102 may provide a list of confirmed severity hashes(s) ConfirmedSeverityHASH(s), updated severity hashes(s) UpgradedSeverityHASH(s), and unique severity hashes LikelySeverityHASH, where the severity hashes are displayed in descending order of likelihood representing the prescription medications the patient is taking for each diagnosis and the severity of that diagnosis.

[0104] Thus, after sufficient iterations of process 500, the training severity hash(s) TrainingSeverityHASH(es) for each severity of each diagnosis in the training dataset will be more powerful and / or more likely to be statistically correct diagnostic severity, which may be reflected by the updated severity hashes UpgradedSeverityHASH used in step 506. For example, taking into account the severity of the diagnosis may enable clinically equivalent prescriptions to be determined based on the severity of the patient's unique medical condition. As an example, each patient with moderate Crohn's disease may receive drug ABC, and / or a patient with severe Crohn's disease may receive drugs DEF+XYZ.

[0105] [Example of clinical equivalence based on diagnostic severity] In the example of a patient diagnosed with Rheumatoid Arthritis, if the substitution system 102 does not consider or know the severity, the severity system 102 may determine that substituting Ibuprofen for Humira is clinically equivalent for cost purposes, resulting in the following outputs / substitutions: Highest Cost: Humira 40 mg - $100 / month; Lower Cost Option 1: Enbrel 50 mg - $75 / month; Lower Cost Option 2: Methotrexate 2.5 mg and hydroxychloroquine sulfate 200 mg - $50 / month; Lower Cost Option 3: Methotrexate 2.5 mg - $25 / month; Lower Cost Option 4: Ibuprofen 800 mg - $10 / month. However, if the substitution system 102 knew and took into account the severity, the output / substitution could change because the substitution system 102 could learn that ibuprofen is not clinically equivalent for a severe diagnosis of rheumatoid arthritis, which could result in the following output / substitution: Highest Cost: Humira 40 mg - $100 / month, Lower Cost Option 1: Enbrel 50 mg - $75 / month, Lower Cost Option 2: Methotrexate 2.5 mg and Hydroxychloroquine Sulfate 200 mg - $50 / month.

[0106] Reference is now also made to Figure 6, which is a flowchart of a non-limiting embodiment or aspect of a process 600 for replacement dispensing. In some non-limiting embodiments or aspects, one or more steps of process 600 may be performed (e.g., completely, partially, etc.) by replacement system 102 (e.g., one or more devices of replacement system 102, etc.). In some non-limiting embodiments or aspects, one or more steps of process 600 may be performed (e.g., completely, partially, etc.) by another device or group of devices, such as, for example, a user device (e.g., one or more devices of a system of user devices, etc.), separate from or including replacement system 102.

[0107] As shown in FIG. 6 , in step 602, process 600 includes determining whether a hash matches a confirmed hash. For example, the substitution system 102 may process a list of confirmed hashes (ConfirmedHASH(ies)), updated hashes (UpgradedHASH(ies)), and unique hashes (LikelyHASH) and / or a list of confirmed severity hashes (ConfirmedSeverityHASH(ies)), updated severity hashes (UpgradedSeverityHASH(ies), and unique severity hashes (LikelySeverityHASH) to determine whether each hash and / or severity hash matches a confirmed hash / severity hash. As an example, if confirmed patient-to-diagnosis data is available, the substitution system 102 may perform step 602 to clean the hash data by removing known bad hashes (e.g., medications that are not equivalent to the diagnosis hash, hashes without a matching diagnosis, etc.). If confirmed patient-to-diagnosis data is not available, the substitution system 102 may proceed directly to step 608.

[0108] 6, in step 604, process 600 includes converting the hash to the confirmed hash in response to a determination that the hash matches the confirmed hash. For example, in response to updated hash(s) UpgradedHASH(s) / unique hash LikelyHASH and / or updated severity hash(s) / unique severity hash LikelySeverityHASH matching the confirmed hash(s) ConfirmedHASH(s) and / or ConfirmedSeverityHASH(s), the substitution system 102 may convert the updated hash(s) UpgradedHASH(s) / unique hash LikelyHASH and / or updated severity hash(s) UpgradedSeverityHASH(s) / unique severity hash LikelySeverityHASH to the confirmed hash(s) ConfirmedHASH(s) and / or ConfirmedSeverityHASH(s).

[0109] 6, at step 606, process 600 includes removing or deleting the hash in response to determining that the hash does not match the confirmed hash. For example, replacement system 102 may remove or delete the updated hash(s) UpgradedHASH(s) / unique hash LikelyHASH and / or updated severity hash(s) UpgradedSeverityHASH(s) / unique hash LikelySeverityHASH in response to the updated hash(s) UpgradedHASH(s) / unique hash LikelyHASH and / or updated severity hash(s) UpgradedSeverityHASH(s) / unique severity hash LikelySeverityHASH not matching the confirmed hash(s) ConfirmedHASH(s) and / or ConfirmedSeverityHASH(s).

[0110] 6, in step 608, process 600 includes determining whether the hash matches the training hash. For example, substitution system 102 can process a list of confirmed hash(s) ConfirmedHASH(s), updated hash(s) UpgradedHASH(s), and unique hashes LikelyHASH and / or a list of confirmed severity hashes ConfirmedSeverityHASH(s), updated severity hashes UpgradedSeverityHASH(s), and unique severity hashes LikelySeverityHASH, and determine whether each hash and / or severity hash matches the training hash / training severity hash. As an example, if there is no diagnosis match (based on a sufficient number of prescribing physicians refusing substitutions (e.g., discovered entries, etc.) and / or pharmacists (e.g., keyed entries, etc.) removing medications that match the diagnosis), substitution system 102 can use the training dataset to remove the hash(s).

[0111] 6, at step 610, process 600 includes converting the hash to a training hash in response to determining that the hash matches the training hash. For example, in response to updated hash(s) UpgradedHASH(s) / unique hash LikelyHASH and / or updated severity hash(s) UpgradedSeverityHASH(s) / unique hash LikelySeverityHASH matching the training hash TrainingHASH(s) and / or TrainingSeverityHASH(s), the substitution system 102 may convert the updated hash(s) UpgradedHASH(s) / unique hash LikelyHASH and / or updated severity hash(s) UpgradedSeverityHASH(s) / unique severity hash LikelySeverityHASH to the training hash(s) TrainingHASH(s) and / or TrainingSeverityHASH(s).

[0112] 6, at step 612, process 600 includes removing or deleting the hash in response to determining that the hash does not match the training hash. For example, replacement system 102 may remove or delete the updated hash(s) UpgradedHASH(s) / unique hash LikelyHASH and / or updated severity hash(s) UpgradedSeverityHASH(s) / unique hash LikelySeverityHASH in response to the updated hash(s) UpgradedHASH(s) / unique hash LikelyHASH and / or updated severity hash(s) UpgradedSeverityHASH(s) / unique hash LikelySeverityHASH not matching the training hash TrainingHASH(s) and / or TrainingSeverityHASH(s).

[0113] Thus, the output of the substitution system 102 from process 600 may include hashes that are discovered to be more likely to reflect drug-diagnosis equivalence, or, if patient-to-diagnosis data is not available in step 602, may include newly discovered hashes for which the substitution system 102 has not been pre-trained on drug-diagnosis equivalence.

[0114] Referring again to FIG. 3A , at step 310, process 300 includes determining costs associated with the diagnosis. For example, the substitution system 102 may determine at least one cost associated with at least one possible diagnosis associated with at least one prescription based on claims data. As an example, the substitution system 102 may determine the at least one cost based on a current cost associated with the at least one prescription and a future cost associated with the at least one prescription, where the future cost differs from the current cost. In such an example, the substitution system 102 may determine a daily patient cost for the entire hash associated with the patient by obtaining a sum of insurance and / or other pharmacy benefit payer payments and / or copayments and / or other payment arrangement (e.g., flat-rate payments, drug deductibles, etc.) payments paid for each drug in the hash and dividing the sum by the number of days between the minimum and maximum next-to-date settlement dates. For example, the output of the substitution system 102 from step 310 may include the patient identifier, the hash (e.g., (ConfirmedHASH / ConfirmedSeverityHASH, UpgradedHASH / UpgradedSeverityHASH, and / or LikelyHASH / LikelySeverityHASH) and the determined cost per day.

[0115] The costs associated with diagnosis and / or prescription may include at least one of the following costs: current financial costs (e.g., dollars, euros, etc.), time costs (e.g., time taken to take / receive medication, etc.), expected outcome-to-cost ratios, side effect costs (e.g., level of severity of side effects associated with the medication, etc.), future financial costs (e.g., it may be economically advantageous to pay a little more initially to avoid anticipated greater financial costs in the future, e.g., to change the prescription to pay X+5 initially to avoid potentially paying X+100 in the future), patient satisfaction costs, or a combination thereof.

[0116] In some non-limiting embodiments or aspects, the substitution system 102 uses a future dataset that includes future data associated with future drug prices (e.g., known future negotiated drug pricing provided by insurance companies or other pharmaceutical benefit payers, announced pharmaceutical company price increases, etc.) and future clinically equivalent drugs coming to market (e.g., generic substitutes for existing drugs being released, etc.). For example, the future data may include at least one of the following parameters: drug name, future price associated with the drug, future effective / available date associated with the drug, diagnostic or equivalent drugs for the drug, or any combination thereof.

[0117] 3B , at step 312, process 300 includes determining a predicted total cost. For example, the substitution system 102 may determine, for a patient, a predicted total cost per diagnosis per day for each of the medications associated with each hash associated with the patient's patient identifier. As an example, the substitution system 102 may determine the expected future daily patient cost for the entire hash by taking the sum of the expected / predicted insurance amounts paid and / or copayments and / or other payment arrangement amounts paid for each medication in the hash and dividing the sum by the typical number of days between the minimum and maximum next-deal dates. For example, the output of the substitution system 102 from step 312 may include the patient identifier, the hash (e.g., ConfirmedFutureHASH / ConfirmedFutureSeverityHASH, upgradedFutureHASH / UpgradedFutureSeverityHASH, and / or likelyFutureHASH / LikelyFutureSeverityHASH), and the predicted total cost.

[0118] As shown in FIG. 3B , at step 314, process 300 includes determining past and future total costs. For example, substitution system 102 may determine the past (from step 310) and future (from step 312) total costs of medication regimens for a given diagnosis for patients for an organization (e.g., insurer, pharmacy payer, cohort, corporation, accountable care organization, etc.) and for individual lines of business of the organization (e.g., gold plan, silver plan, public or private coverage, etc.). As an example, substitution system 102 may count, for each unique group hash, the total number of patients associated with that hash and the total daily costs for that hash. In such an example, substitution system 102 may store the commonly prescribed medications available in a given line of business or national formulary, details of future formularies, and / or details of upcoming drug releases from insurers or other pharmacy payers for each line of business or pharmacy payer group. For example, substitution system 102 may receive and / or determine which medications and dosages may be used for substitution purposes for a given patient from among all possible medications to avoid suggesting substitutions that may not be available to the patient due to line of business contract restrictions or pharmacy benefit management, leading to a false learning cycle. In such an example, the output of substitution system 102 from step 314 may include the hash, the number of patients associated with the hash, and / or the daily cost.

[0119] As shown in FIG. 3B , in step 316, process 300 includes determining that the group hash includes a threshold number of patients. For example, substitution system 102 may determine that a group hash (e.g., at least one possible diagnosis associated with at least one prescription) includes at least a threshold number of patients. As an example, substitution system 102 may determine the threshold number of patients based on a percentage of the total number of patients analyzed by substitution system 102 and taking into account the statistical likelihood of a diagnosis for a given patient population. In such an example, output of substitution system 102 from step 314 may include the hash, the number of patients, and the daily cost. Note that if the threshold number of patients is not met in step 314, the hash may be added to the training dataset for future consideration without being output for current use in step 318.

[0120] As shown in FIG. 3B , at step 318, process 300 includes determining at least one potential substitute prescription for at least one prescription. For example, substitution system 102 may use a machine learning model trained based on a training dataset for at least one possible diagnosis to determine at least one potential substitute prescription for at least one prescription associated with the at least one possible diagnosis. As an example, substitution system 102 may generate potential rules for substitution of drug(s) for a prescription in which a high-cost hash is replaced with a more economical, lower-cost hash to achieve similar clinical efficacy for similar severity of diagnosis. In such an example, substitution system 102 may generate a drug substitution for a drug(s) using at least one of the following conditions: That is, clinically equivalent drug(s) exist, lower-cost alternative drug(s) or drug(s) dosages have been determined by substitution system 102, the likely diagnosis(ies) support substitution of the severity of the alternative diagnosis, the patient can reduce expected treatment costs (and / or improve treatment quality) by starting a prescription for a lower-cost drug for the new diagnosis, or any combination thereof. For example, substitution system 102 may generate a list of one(or more) drug groups based on descending order of hash likelihood (confirmed, updated, likely) to be used in place of one(or more) alternative drugs for a given diagnosis and alternative severity, and / or substitution system 102 may order or rank these results based on likelihood and overall economic savings, respectively, where savings meet a pre-calculated minimum threshold.

[0121] The substitution system 102 may generate machine learning models (e.g., estimators, classifiers, predictive models, detector models, etc.) using machine learning techniques, including, for example, supervised and / or unsupervised techniques such as decision trees (e.g., gradient-boosted decision trees, random forests, etc.), logistic regression, artificial neural networks (e.g., convolutional neural networks, etc.), Bayesian statistics, learning automata, hidden Markov modeling, linear classifiers, quadratic classifiers, association rule learning, etc. The machine learning models may be trained to provide an output including at least one alternative prescription (e.g., a list of one or more drug groups based on descending order of hash likelihood (confirmed, updated, probable), etc.) in response to input including at least one prescription associated with at least one diagnosis (e.g., at least one prescription associated with a given diagnosis and any severity, group hash, etc.). For example, the substitution system 102 may train a model based on training data (e.g., training datasets, training hashes, etc.) associated with one or more prescriptions for one or more diagnoses for one or more patients. In such an example, the substitution may include a probability score associated with the substitution. For example, the substitution may include a probability that the substitution is a more economical, lower-cost drug(s) that provides similar clinical effectiveness for a similar diagnosis / severity of diagnosis.

[0122] In some non-limiting embodiments, the substitution system 102 may store the model (e.g., store the model for later use). In some non-limiting embodiments or aspects, the substitution system 102 may store the model in a data structure (e.g., a database, a linked list, a tree, etc.). In some non-limiting embodiments, the data structure is located within the substitution system 102 or external to (e.g., remote from) the substitution system 102 (e.g., in a data source 104, etc.).

[0123] A potential alternative prescription (or potentially discovered rule) may include at least one of the following: a different drug than the drug associated with the at least one prescription (e.g., a single drug versus a single drug substitution, a single drug versus a multiple drug substitution, a multiple drug versus a single drug substitution, etc.), a different dosage than the dose associated with the at least one prescription, instructions to stop using the drug associated with the at least one prescription, a different formulation of the same drug associated with the at least one prescription (e.g., tablet versus capsule, oral delivery versus injectable delivery, etc.), a different packaging of the same drug associated with the at least one prescription (e.g., over-the-counter, generic, brand name, etc.), or any combination thereof.

[0124] Referring also to Figure 7, Figure 7 illustrates exemplary potential rules 700 that may be discovered by process 300. These rules may also consider and / or suggest the age or sex of the patient receiving the prescription, any other additional diagnoses of the patient, the expected duration of each higher and lower cost medication regimen, the clinical safety and quality of care (e.g., side effects, etc.) of the medication regimen, and / or restrictions on drugs available in drug formularies available at the business unit or national level.

[0125] With particular reference to Example 3 in Figure 7, the substitution system may substitute a medication(s) for a missing medication(s). For example, the substitution system 102 may use the following criteria to substitute a medication(s) for a missing medication(s): the patient has multiple prescriptions, which allows the system to determine that the patient is alive and still a member of another eligible group (e.g., citizenship) for the insurance company or drug benefit; the patient has not switched to another medication(s) for the same diagnosis; the substitution system 102 has not received new claims data for a predetermined period of time since the next fill date; and the system recognizes that a sufficient number of patients have been "discontinued," a predetermined threshold is met, allowing the substitution system 102 to identify potential discontinuation rules that may be possible.

[0126] With particular reference to Example 4 of FIG. 7 , the substitution system may initiate a prescription at a lower cost for a new diagnosis. For example, the substitution system 102 may train prescribers on cost savings. As an example, if two drugs are used to treat the same diagnosis and one drug is more expensive than the other, the substitution system 102 may identify when the prescriber typically initiates a new prescription with the lower-cost drug for a newly diagnosed patient, and the substitution system 102 may consider the prescriber “trained” on the potential discovered rule. Identifying the prescriber's habits may identify opportunities to educate the prescriber on better / cost-saving habits. Initiating a prescription at a lower cost for a new diagnosis may also result in a positive reinforcement (e.g., an increment of +1) of the corresponding hash in the training dataset. In such an example, the substitution system 102 may initiate a prescription at a lower cost for a new diagnosis using the following criteria: That is, a prescriber is prescribing a higher-cost drug(s) for a given diagnosis, the substitution system 102 identifies the new patient's diagnosis, the prescriber begins prescribing the lower-cost drug(s) for the new patient's diagnosis, and a threshold for a new prescription of the lower-cost drug(s) for the new patient's diagnosis is met. Similarly, immediately beginning prescribing a lower-cost drug (for a given diagnosis) may prevent or delay the need for a much higher-cost drug later due to an increased severity of the diagnosis. Identifying such patients and suggesting substituting a lower-cost drug for the higher-cost substitution "None" reduces overall treatment costs and potentially improves quality of care. Example 4, for example, may be used to achieve this scenario; e.g., as previously described herein, it may be economically advantageous to change the prescription to initially pay X+5 to avoid paying a potential cost of X+100 in the future.

[0127] Thus, when comparing potential rules generated by non-limiting embodiments or aspects of the present disclosure to manually generated potential rules created by pharmacists / PharmD's, non-limiting embodiments or aspects of the present disclosure may independently discover 90% of the rules that pharmacists may otherwise discover, and may independently discover rules that pharmacists may not otherwise discover and over 254% more drug substitutions for savings.

[0128] 3B, at step 320, process 300 includes providing savings information. For example, substitution system 102 may provide at least one user (e.g., a prescriber) with savings information associated with at least one potential alternative prescription for at least one prescription associated with at least one possible diagnosis. As one example, the substitution system 102 may determine opportunities to multiply the cost savings difference between the higher-cost drug(s) and the lower-cost drug(s) by a factor (e.g., 1%, 5%, etc.), determine whether the patient's copayment or other payment arrangement (e.g., a flat rate, a drug deductible, etc.) may limit the patient's willingness to agree to a lower-cost substitution (e.g., determine whether the patient's cost burden, if any, may limit the patient's willingness to agree to a substitution), and if the substitution system determines that the copayment or other payment arrangement may limit the patient's willingness to substitute the drug(s), follow a process to flag the cost savings opportunity as a potential reimbursement of the copayment or other payment arrangement and suggest payment by sending a message to the patient and / or discussing the opportunity with the prescriber. In such an example, the output of the substitution system 102 from step 320 may include the cost savings opportunity for each patient along with a flag indicating whether the copayment or other payment arrangement may limit the patient's willingness to substitute the drug. For example, the substitution system 102 may display the savings opportunity to the prescriber in an application and / or send a message (e.g., email, SMS message, etc.) to the prescriber that includes the savings opportunity.

[0129] A savings opportunity may include at least one of the following parameters: patient name, patient date of birth, patient gender, high-cost drug(s), days' supply of drug(s), last fill date of drug(s), next scheduled fill date of drug(s), prescriber's name, insurance company or other pharmacy benefit payer, patient payment amount, lower-cost drug(s), date the savings opportunity was discovered, potential savings from using substitutions, or a combination thereof. In some non-limiting embodiments or aspects, a savings opportunity may include one or more of the following meta-details: current status of the savings opportunity (e.g., ready, completed, rejected - patient refused, rejected - patient not accepted, rejected - opportunity inaccurate, etc.), savings opportunity history and feedback, notes regarding the drug(s) involved, or a combination thereof.

[0130] 3B, at step 322, process 300 includes receiving user input associated with at least one potential alternative prescription. For example, substitution system 102 may receive user input associated with at least one potential alternative prescription for at least one prescription associated with at least one possible diagnosis from at least one user (e.g., a prescriber). As an example, the prescriber may verify agreement with the at least one potential alternative prescription (e.g., discovered potential rule(s)).

[0131] 3B, at step 324, process 300 includes updating the training dataset. For example, substitution system 102 may update the training dataset to include at least one potential alternative prescription (e.g., discovered potential rule(s), etc.). As an example, substitution system 102 may update the training dataset to include at least one potential alternative prescription (e.g., discovered potential rule(s), etc.) in response to a large number of prescribers verifying that they do not agree with at least one potential alternative prescription (e.g., discovered potential rule(s), etc.) that does not meet a threshold number. In such an example, if a high percentage of prescribers (e.g., a percentage meeting a threshold percentage) verify that they do not agree with at least one potential alternative prescription (e.g., a discovered potential rule(s), a substitution, etc.), the substitution system 102 may update the training dataset to eliminate the possibility that this substitution or alternative prescription is recommended, and if a low percentage of prescribers (e.g., a percentage not meeting a threshold percentage) verify that they do not agree with at least one potential alternative prescription (and / or verify that they do not agree with at least one potential alternative prescription), the substitution system 102 may update the training dataset to eliminate the possibility that this substitution or alternative prescription is recommended.

[0132] The replacement system 102 may determine whether to update the training dataset using a list of confirmed hash(s) ConfirmedHASH(s), updated hash(s) UpgradedHASH(s), and unique hashes LikelyHASH and / or a list of confirmed severity hashes ConfirmedSeverityHASH(s), updated severity hashes UpgradedSeverityHASH(s), unique severity hashes LikelySeverityHASH (e.g., using the output of steps 416 and / or 516, using automated training, etc.), using an updated training dataset updated based on user input (e.g., trained by a prescriber, etc.), and / or using a training process described in further detail herein below (e.g., training by a pharmacist or other trusted source, etc.). When compared to the automatically discovered substitutions or rules (e.g., output of steps 416 and / or 516), the pharmacist's decision may be given the highest "confidence" or weighting (e.g., probability, etc.), and a relatively higher "confidence" or weighting (e.g., probability, etc.) may be given to the prescriber's decision, which may effectively provide a system in which a vote may be made for or against a given potential discovered rule and associated hash(s). For example, the substitution system 102 may determine at least one probability associated with the at least one potential diagnosis based on at least one possible diagnosis and a training dataset, and the at least one probability may be input into at least one machine learning model to determine at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis.

[0133] The learned threshold may determine the amount of “credibility” or weight votes required for a hash to no longer be considered or accepted for a diagnosis and associated alternative prescription / potential discovered rule. The substitution system 102 may continually learn and discover additional hashes and potential discovered rules, so acceptance at a given time may not mean permanent acceptance. For example, if 20 prescribers accept a cost-saving opportunity (e.g., by providing user input confirming at least one potential alternative prescription for at least one prescription associated with at least one possible diagnosis) (and thus associated potential discovered rules and hashes) and make a substitution for the patient, the substitution system 102 may “override” a single pharmacist who rejected a discovered rule for clinical validity reasons. The hash may be sent back to the training dataset to influence future potential discovered rules. In such an example, the output of the substitution system 102 in step 322 may include a final hash, FinalHASH(CUI1,CUI2,...), along with the diagnosis and the severity of the alternative diagnosis.

[0134] As shown in FIG. 3B , at step 326, the process 300 includes training a machine learning model based on an updated training dataset. For example, the substitution system 102 may train (e.g., retrain, update, etc.) the machine learning model based on the updated training dataset. As an example, the machine learning model may be trained to provide an output including at least one alternative prescription (e.g., a list of one or more drug groups based on descending hash likelihood (confirmed, updated, possible), potential discovered rules, etc.) in response to an input including an updated training dataset (e.g., a training dataset updated to include at least one prescription associated with at least one diagnosis / final hash, etc.). For example, the substitution system 102 may train the model based on the updated training data (e.g., the updated training dataset, training hash, final hash, etc.). In such an example, the alternative prescription or potential discovered rule may include a probability score associated with the alternative prescription. For example, the alternative prescription may include a probability that the alternative prescription is a more economical, lower-cost drug(s) that provides similar clinical effectiveness for a similar diagnosis / diagnosis severity. In such examples, the substitution system 102 may store the updated model (e.g., store the updated model for later use). In such examples, the substitution system 102 may continuously train and / or update the machine learning model when new claims data is received for new prescriptions for new and / or existing patients and / or when prescribers and / or pharmacists accept or reject proposed rules for substitution prescriptions.

[0135] Thus, each substitution prescription or potential discovered rule, along with each associated diagnosis and each associated hash (and included drug(s)), is provided (e.g., displayed, etc.) along with the ability of the pharmacist (and / or other trusted source) to reject a potential discovered rule (and associated hash) for a given diagnosis. The pharmacist may be able to reject a rule based on criteria such as clinical effectiveness, safety of the drug(s) or drug(s) combination, future cost concerns, etc. (e.g., the pharmacist believes a low-cost drug will increase in price in the near future (when future projected cost data is not otherwise available), thereby negating the savings, etc.). The rejection reason provided by the pharmacist for a potential discovered rule can determine how the substitution system 102 handles future potential discovered rule suggestions; by the pharmacist's failure to reject a potential discovered rule, the substitution system 102 may assume that the pharmacist has implicitly accepted the potential discovered rule. In this manner, training may be based on any trusted clinical interactions (e.g., from a physician, from a pharmacist, from a nurse, etc.) and / or data analysis by the substitution system 102.

[0136] While embodiments or aspects have been described in detail for purposes of illustration and description, it should be understood that such detail is for that purpose only and that the embodiments or aspects are not limited to the disclosed embodiments or aspects, but rather are intended to cover modifications and equivalent arrangements within the spirit and scope of the appended claims. For example, it should be understood that the present disclosure contemplates that, to the extent possible, one or more features of any embodiment or aspect may be combined with one or more features of any other embodiment or aspect. Indeed, any of these features may be combined in ways not specifically recited in the claims and / or disclosed in the specification. Although each dependent claim listed below may depend directly on only one claim, the disclosure of possible implementations includes each dependent claim in combination with all other claims in the claim set.

Claims

1. 1. A computer-implemented method comprising: obtaining claims data associated with at least one claim for at least one prescription associated with at least one patient; determining at least one universal identifier for the at least one prescription associated with the at least one patient based on the claims data; obtaining medication diagnostic data associated with one or more known diagnoses for one or more universal identifiers associated with one or more prescriptions; determining at least one possible diagnosis associated with the at least one prescription for the at least one patient based on the at least one universal identifier and the medication diagnostic data; determining at least one cost associated with the at least one possible diagnosis associated with the at least one prescription based on the claims data; determining, for the at least one possible diagnosis, at least one potential alternative prescription to the at least one prescription associated with the at least one possible diagnosis using a machine learning model trained based on a training dataset; providing at least one user with savings information associated with the at least one potential alternative prescription to the at least one prescription associated with the at least one possible diagnosis; receiving user input from the at least one user associated with the at least one potential alternative prescription to the at least one prescription associated with the at least one possible diagnosis; updating the training dataset to include the at least one possible diagnosis associated with the at least one potential alternative prescription as at least one trained diagnosis based on the user input; training the machine learning model based on the updated training dataset; 1. A computer-implemented method comprising:

2. determining whether the at least one possible diagnosis is consistent with one or more confirmed diagnoses in a confirmed dataset; In response to determining that the at least one possible diagnosis matches one or more confirmed diagnoses in a confirmed dataset, one of: (i) updating the training dataset to include the at least one possible diagnosis associated with the at least one prescription as one or more trained diagnoses; and (ii) updating the trained dataset by adjusting a weight associated with at least one existing trained diagnosis in the training dataset. The computer-implemented method of claim 1 further comprising:

3. determining a severity level associated with the at least one possible diagnosis based on the at least one possible diagnosis and the confirmed dataset, the severity level being input into the machine learning model to determine the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis. The computer-implemented method of claim 2 further comprising:

4. 4. The computer-implemented method of claim 3, wherein the at least one potential alternative prescription is associated with the same severity level as the at least one prescription for the at least one possible diagnosis.

5. determining at least one probability associated with the at least one possible diagnosis based on the at least one possible diagnosis and the training dataset, wherein the at least one probability is input into the machine learning model to determine the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis. The computer-implemented method of claim 1 further comprising:

6. 2. The computer-implemented method of claim 1, wherein the at least one potential alternative prescription includes at least one of: a different drug than the drug associated with the at least one prescription; a different dose than the dose associated with the at least one prescription; instructions to discontinue use of the drug associated with the at least one prescription; a different formulation of the same drug associated with the at least one prescription; different packaging of the same drug associated with the at least one prescription; or any combination thereof.

7. 10. The computer-implemented method of claim 1, wherein the at least one cost is further determined based on a current cost associated with the at least one prescription and a future cost associated with the at least one prescription, the future cost being different from the current cost.

8. 1. A system comprising: obtaining claims data associated with at least one claim for at least one prescription associated with at least one patient; determining at least one universal identifier for the at least one prescription associated with the at least one patient based on the claims data; obtaining pharmacodiagnostic data associated with one or more known diagnoses for one or more universal identifiers associated with one or more prescriptions; determining at least one probable diagnosis associated with the at least one prescription for the at least one patient based on the at least one universal identifier and the medication diagnostic data; determining at least one cost associated with the at least one possible diagnosis associated with the at least one prescription based on the claims data; determining, for the at least one possible diagnosis, at least one potential alternative prescription to the at least one prescription associated with the at least one possible diagnosis using a machine learning model trained based on a training dataset; providing at least one user with savings information associated with the at least one potential alternative prescription to the at least one prescription associated with the at least one possible diagnosis; receiving user input from the at least one user associated with the at least one potential alternative prescription to the at least one prescription associated with the at least one possible diagnosis; updating the training dataset to include the at least one possible diagnosis associated with the at least one potential alternative prescription as at least one trained diagnosis based on the user input; training the machine learning model based on the updated training dataset; 1. A system comprising one or more processors programmed and / or configured to:

9. the one or more processors: determining whether the at least one possible diagnosis is consistent with one or more confirmed diagnoses in a confirmed dataset; In response to determining that the at least one possible diagnosis matches one or more confirmed diagnoses in a confirmed dataset, one of: (i) updating the trained dataset to include the at least one possible diagnosis associated with the at least one prescription as one or more trained diagnoses; and (ii) updating the trained dataset by adjusting a weight associated with at least one existing trained diagnosis in the trained dataset.

9. The system of claim 8, further programmed and / or configured to:

10. the one or more processors: determining a severity level associated with the at least one possible diagnosis based on the at least one possible diagnosis and the confirmed dataset, the severity level being input into the machine learning model to determine the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis; 10. The system of claim 9, further programmed and / or configured to:

11. 11. The system of claim 10, wherein the at least one potential alternative prescription is associated with the same severity level as the at least one prescription for the at least one possible diagnosis.

12. the one or more processors: determining at least one probability associated with the at least one possible diagnosis based on the at least one possible diagnosis and the training dataset, wherein the at least one probability is input into the machine learning model to determine the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis; 9. The system of claim 8, further programmed and / or configured to:

13. 9. The system of claim 8, wherein the at least one potential alternative prescription includes at least one of a different drug than the drug associated with the at least one prescription, a different dose than the dose associated with the at least one prescription, instructions to discontinue use of the drug associated with the at least one prescription, a different formulation of the same drug associated with the at least one prescription, different packaging of the same drug associated with the at least one prescription, or any combination thereof.

14. 10. The system of claim 8, wherein the at least one cost is further determined based on a current cost associated with the at least one prescription and a future cost associated with the at least one prescription, the future cost being different from the current cost.

15. 1. A computer program comprising at least one non-transitory computer-readable medium comprising program instructions, the ... obtaining claims data associated with at least one claim for at least one prescription associated with at least one patient; determining at least one universal identifier for the at least one prescription associated with the at least one patient based on the claims data; obtaining pharmacodiagnostic data associated with one or more known diagnoses for one or more universal identifiers associated with one or more prescriptions; determining at least one probable diagnosis associated with the at least one prescription for the at least one patient based on the at least one universal identifier and the medication diagnostic data; determining at least one cost associated with the at least one possible diagnosis associated with the at least one prescription based on the claims data; determining, for the at least one possible diagnosis, at least one potential alternative prescription to the at least one prescription associated with the at least one possible diagnosis using a machine learning model trained based on a training dataset; providing at least one user with savings information associated with the at least one potential alternative prescription to the at least one prescription associated with the at least one possible diagnosis; receiving user input from the at least one user associated with the at least one potential alternative prescription to the at least one prescription associated with the at least one possible diagnosis; updating the training dataset to include the at least one possible diagnosis associated with the at least one potential alternative prescription as at least one trained diagnosis based on the user input; training the machine learning model based on the updated training dataset; A computer program characterized by causing a computer to perform the following.

16. The program instructions, when executed by the at least one processor, cause the at least one processor to: determining whether the at least one possible diagnosis is consistent with one or more confirmed diagnoses in a confirmed dataset; In response to determining that the at least one possible diagnosis matches one or more confirmed diagnoses in a confirmed dataset, one of: (i) updating the trained dataset to include the at least one possible diagnosis associated with the at least one prescription as one or more trained diagnoses; and (ii) updating the trained dataset by adjusting a weight associated with at least one existing trained diagnosis in the trained dataset.

16. The computer program of claim 15, further comprising:

17. The program instructions, when executed by the at least one processor, cause the at least one processor to: determining a severity level associated with the at least one possible diagnosis based on the at least one possible diagnosis and the confirmed dataset, wherein the severity level is input into the machine learning model to determine the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis, the at least one potential alternative prescription being associated with the same severity level as the at least one prescription for the at least one possible diagnosis; 17. The computer program of claim 16, further comprising:

18. The program instructions, when executed by the at least one processor, cause the at least one processor to: determining at least one probability associated with the at least one possible diagnosis based on the at least one possible diagnosis and the training dataset, wherein the at least one probability is input into the machine learning model to determine the at least one potential alternative prescription for the at least one prescription associated with the at least one possible diagnosis; 16. The computer program of claim 15, further comprising:

19. 16. The computer program product of claim 15, wherein the at least one potential alternative prescription comprises at least one of a different drug than the drug associated with the at least one prescription, a different dose than the dose associated with the at least one prescription, instructions to discontinue use of the drug associated with the at least one prescription, a different formulation of the same drug associated with the at least one prescription, different packaging of the same drug associated with the at least one prescription, or any combination thereof.

20. 16. The computer program product of claim 15, wherein the at least one cost is further determined based on a current cost associated with the at least one prescription and a future cost associated with the at least one prescription, the future cost being different from the current cost.

Images