System and method for determining communication pathway
Systems and methods for providing an intelligent network to onboard patients to specialty medications are described herein. A server system for managing communication is configured to receive from a user at a healthcare practice, an electronic request to obtain a medical prior authorization (medPA) for a specialty drug to administer for a patient of the healthcare practice; select, using a rules service, a communication pathway to submit the medPA to a healthcare payer from a plurality of communication pathways; and initiate a connection with the healthcare payer using the selected communication pathway.
1 . A server system for managing communication, the server system comprising:
a processor; and
a memory device including instructions, which when executed by the processor, cause the processor to perform operations comprising:
receiving, at a workflow service provided by the server system, from a client application operated by a user at a healthcare practice, an electronic request to obtain a medical prior authorization (medPA) for a specialty drug to administer for a patient of the healthcare practice;
selecting, using a rules service, a communication pathway to submit the medPA to a healthcare payer from a plurality of communication pathways, wherein the rules service is configured to implement a machine-learning model trained using supervised learning on labeled medPA outcome data, the machine-learning model being configured to generate, for each of the plurality of communication pathways, an approval-probability score based on at least (a) a payer-specific historical approval-rate feature and (b) a payer-specific discrete-response-type feature, wherein the rules service selects the communication pathway having the highest approval-probability score as determined by the machine-learning model, and to use a multi-factor evaluation to sort the plurality of communication pathways using at least two of a plurality of factors, wherein the rules service and the workflow service are implemented as microservices hosted by the server system, and wherein the rules service is instantiated by the workflow service via an application programming interface; and
initiating, by the workflow service, a connection with the healthcare payer using the selected communication pathway.
2 . The server system of claim 1 , wherein the electronic request to obtain the medPA is encoded in a Hypertext Transfer Protocol (HTTP) message request for prior authorization of a patient treatment.
3 . The server system of claim 2 , wherein the Hypertext Transfer Protocol (HTTP) message request is an extended Markup Language (XML) Simple Object Access Protocol (SOAP) message.
4 . The server system of claim 2 , wherein the Hypertext Transfer Protocol (HTTP) message request is a Representational State Transfer (REST) message.
5 . The server system of claim 1 , wherein the electronic request to obtain the medPA includes patient context data.
6 . The server system of claim 5 , wherein the patient context data is received from a drug prescriber.
7 . The server system of claim 5 , wherein the patient context data is obtained from a partner system.
8 . The server system of claim 1 , wherein the rules service is configured using machine learning.
9 . The server system of claim 1 , wherein the rules service is configured to use a weighted function to sort the plurality of communication pathways.
10 . The server system of claim 9 , wherein the weighted function includes a recency weight.
11 . The server system of claim 1 , wherein the plurality of factors include one or more of: a time from medPA submission to decision, an amount of data required for the medPA submission, a follow up frequency, a denial rate, an approval rate, an approved as requested rate, a preferred user experience score, a payer discrete response type, or a recency factor.
12 . The server system of claim 1 , wherein the rules service is configured to sort the plurality of communication pathways in order of a most likely to obtain a timely response to a least likely to obtain a timely response.
13 . The server system of claim 12 , wherein initiating the connection with the healthcare payer using the selected communication pathway includes iteratively initiating connections with the healthcare payer to obtain the medPA using the sorted plurality of communication pathways.
14 . The server system of claim 13 , wherein iteratively initiating connections with the healthcare payer comprises:
attempting a first connection using a first communication pathway of the sorted plurality of communication pathways; and
attempting a second connection using a second communication pathway of the sorted plurality of communication pathways, when the first connection fails, wherein the second communication pathway is ranked lower than the first communication pathway in the sorted plurality of communication pathways.
15 . The server system of claim 12 , wherein a metric to measure whether a response is timely is based on an industry standard.
16 . The server system of claim 12 , wherein a metric to measure whether a response is timely is based on a type of communication pathway used.
17 . The server system of claim 1 , wherein the plurality of communication pathways include at least two of: a business-to-business connection, an application programming interface exposed by the healthcare payer to the server system, a facsimile channel, or a telephone representative.
18 . The server system of claim 1 , wherein the plurality of communication pathways include at least two of: an ANSI X12 EDI 278 transaction set pathway, a National Council for Prescription Drug Programs (NCPDP) communication standard pathway, a robotic process automation (RPA) communication pathway, a facsimile communication pathway, a telephone communication pathway, or a HL7 FHIR-based drug format pathway.
19 . The server system of claim 1 , wherein the medPA is included in a medical benefit verification (medBV) for the specialty drug, and wherein the instructions cause the processor to perform operations comprising:
determining whether the medPA is required as a portion of the medBV using machine learning.
20 . The server system of claim 1 , wherein the rules service is configured to sort the plurality of communication pathways according to their respective likelihood of obtaining a final disposition of a prior authentication request.
21 . The server system of claim 1 , wherein the rules service is configured to sort the plurality of communication pathways according most-likely to lead to a successful prior authorization to a least-likely to lead to a successful prior authorization.
22 . A non-transitory machine-readable medium including instructions for managing communication, which when executed by a server system, cause the server system to perform operations comprising:
receiving, at a workflow service provided by the server system, from a client application operated by a user at a healthcare practice, an electronic request to obtain a medical prior authorization (medPA) for a specialty drug to administer for a patient of the healthcare practice;
selecting, using a rules service, a communication pathway to submit the medPA to a healthcare payer from a plurality of communication pathways, wherein the rules service is configured to implement a machine-learning model trained using supervised learning on labeled medPA outcome data, the machine-learning model being configured to generate, for each of the plurality of communication pathways, an approval-probability score based on at least (a) a payer-specific historical approval-rate feature and (b) a payer-specific discrete-response-type feature, wherein the rules service selects the communication pathway having the highest approval-probability score as determined by the machine-learning model, and to use a multi-factor sort process to sort the plurality of communication pathways using at least two of a plurality of factors, wherein the rules service and the workflow service are implemented as microservices hosted by the server system, and wherein the rules service is instantiated by the workflow service via an application programming interface; and
initiating, by the workflow service, a connection with the healthcare payer using the selected communication pathway.
23 . The non-transitory machine-readable medium of claim 22 , wherein the plurality of factors include one or more of: a time from medPA submission to decision, an amount of data required for the medPA submission, a follow up frequency, a denial rate, an approval rate, an approved as requested rate, a preferred user experience score, a payer discrete response type, or a recency factor.