Methods and system to estimate retail prescription waiting time

1. A computer-implemented method, executed by a processor, to estimate the waiting time for filling a prescription medication for a patient, the method comprising:

training, by a processor, a machine learning model to predict an estimated waiting time for filling the prescription medication for the patient using, for each of a plurality of previously filled prescriptions, (i) a set of characteristics of each previously filled prescription, and (ii) a fill time for each previously filled prescription,

wherein the set of characteristics of each previously filled prescription includes at least one of: prescription information, medication information, usage information, pharmacy stock information, a number of patients currently waiting for a prescription medication to be filled, or a number of prescriptions waiting to be filled;

receiving, with a processor, a prescription for a medication for a patient;

receiving, with the processor, a request for an estimated waiting time for filling the prescription medication for the patient;

identifying, by the processor, a set of characteristics of the prescription medication for the patient;

applying, by the processor, the set of characteristics of the prescription medication to the machine learning model to predict the estimated waiting time for filling the prescription medication for the patient; and

providing, by the processor, an indication of the estimated waiting time for display on a client device.

2. The method of claim 1 , further comprising:

determining, by the processor, whether to contact the prescriber to decrease the estimated waiting time; and

in response to determining that contacting the prescriber decreases the estimated waiting time, providing, by the processor, a recommendation to the patient to contact the prescriber for display on the client device, wherein the recommendation includes an estimated amount of waiting time saved by contacting the prescriber.

3. The method of claim 2 , further comprising:

determining, by the processor, that the prescription has not been filled and that the expected amount of waiting time has been exceeded; and

providing, by the processor, an automatic attempt to contact the prescriber.

4. The method of claim 1 , further comprising:

receiving, with the processor, a requested pharmacy location for retrieving the prescription medication for the patient.

5. The method of claim 4 , further comprising:

identifying, by the processor, a set of characteristics of the requested pharmacy location; and

applying, by the processor, the set of characteristics of the requested pharmacy location to the machine learning model to determine the estimated waiting time for filling the prescription medication for the patient.

6. The method of claim 4 , further comprising:

identifying, by the processor, one or more alternative pharmacy locations within a threshold distance of the requested pharmacy location;

for each of the one or more alternative pharmacy locations:

identifying, by the processor, a set of characteristics of the alternative pharmacy location; and

applying, by the processor, the set of characteristics of the alternative pharmacy location to the machine learning model to determine the estimated waiting time for filling the prescription medication for the patient; and

providing, by the processor, an indication of one of the one or more alternative pharmacy locations which has a shorter estimated waiting time than the estimated waiting time for filling the prescription medication at the requested pharmacy location for display on the client device.

7. The method of claim 1 , wherein the prescription is received from the patient.

8. The method of claim 1 , further comprising receiving, from the client device in response to the providing of the estimated waiting time, a request to fulfill the prescription.

9. The method of claim 1 , wherein training the machine learning model includes applying gradient boosting.

10. The method of claim 1 , further comprising:

training the machine learning model with data from a first subset of the plurality of previously filled prescriptions; and

validating the machine learning model with data from a second subset of the plurality of previously filled prescriptions.

11. A non-transitory computer-readable storage medium comprising instructions that, when executed, cause a processor to:

train a machine learning model to predict an estimated waiting time for filling a prescription medication for a patient using, for each of a plurality of previously filled prescriptions, (i) a set of characteristics of each previously filled prescription, and (ii) a fill time for each previously filled prescription,

wherein the set of characteristics of each previously filled prescription includes at least one of: prescription information, medication information, usage information, pharmacy stock information, a number of patients currently waiting for a prescription medication to be filled, or a number of prescriptions waiting to be filled;

receive a prescription for a medication for a patient;

receive a request for an estimated waiting time for filling the prescription medication for the patient;

identify a set of characteristics of the prescription medication for the patient;

apply the set of characteristics of the prescription medication to the machine learning model to predict the estimated waiting time for filling the prescription medication for the patient; and

provide an indication of the estimated waiting time for display for filling the prescription medication for the patient on a client device.

12. The non-transitory computer-readable storage medium of claim 11 , wherein the instructions further cause the processor to:

determine whether to contact the prescriber to decrease the estimated waiting time; and

in response to determining that contacting the prescriber decreases the estimated waiting time, provide a recommendation to the patient to contact the prescriber for display on the client device, wherein the recommendation includes an estimated amount of waiting time saved by contacting the prescriber.

13. The non-transitory computer-readable storage medium of claim 11 , wherein the instructions further cause the processor to:

receive a requested pharmacy location for retrieving the prescription medication for the patient.

14. The non-transitory computer-readable storage medium of claim 13 , wherein the instructions further cause the processor to:

identify a set of characteristics of the requested pharmacy location; and

apply the set of characteristics of the requested pharmacy location to the machine learning model to determine the estimated waiting time for filling the prescription medication for the patient.

15. The non-transitory computer-readable storage medium of claim 14 , wherein the instructions further cause the processor to:

identify one or more alternative pharmacy locations within a threshold distance of the requested pharmacy location;

for each of the one or more alternative pharmacy locations:

identify a set of characteristics of the alternative pharmacy location; and

apply the set of characteristics of the alternative pharmacy location to the machine learning model to determine the estimated waiting time for filling the prescription medication for the patient; and

provide an indication of one of the one or more alternative pharmacy locations which has a shorter estimated waiting time than the estimated waiting time for filling the prescription medication at the requested pharmacy location for display on the client device.

16. The non-transitory computer-readable storage medium of claim 11 , wherein the prescription is received from the patient.

17. The non-transitory computer-readable storage medium of claim 11 , wherein the instructions further cause the processor to:

receive, from the client device in response to the providing of the estimated waiting time, a request to fulfill the prescription.

18. The non-transitory computer-readable storage medium of claim 11 , wherein the instructions further cause the processor to:

train the machine learning model with data from a first subset of the plurality of previously filled prescriptions; and

validate the machine learning model with data from a second subset of the plurality of previously filled prescriptions.