US-12619923-B2 - Engagement learning engine

US12619923B2US 12619923 B2US12619923 B2US 12619923B2US-12619923-B2

Abstract

The engagement learning engine provides for a holistic engagement model deeply rooted in the principles of human psychology, behavioral economics and mathematical correlation after studying the behavior, attitude and preferences of patients. The attitude, awareness, willingness (AAW) framework works by first identifying root causes that are causing lack of engagement and then uses the concept of behaviorally segmented ‘Nudges’ to deliver predictable engagement overtime. The AAW framework is preferably delivered using an artificial intelligence (AI) and machine learning (ML) technology platform to create personalized patient experience there by further enhancing and improving patient engagement. Further, the AI/ML model has cognitive learning abilities from the identified patterns, patient interactions and other inputs there by creating a perpetual loop of delivering precise nudges based on individual behaviors, outcomes delivered, interaction and other factors.

Inventors

MAYANK PANT
DHRUV RASTOGI
SHRADDHA SAYANI
DOR SHLENGER
Emil Georgiev

Assignees

INVENTURUS KNOWLEDGE SOLUTIONS, INC.

Dates

Publication Date: 20260505
Application Date: 20240213

Claims (6)

1 . A payment engagement system, having a processor, for encouraging payment of medical debt by patients, the engagement system comprising: a score module for calculating, using the processor, an engagement score based on primary feedback from a user related to the medical debt; a nudge module for automatically selecting, using the processor, at least one engagement nudge from a plurality of engagement nudges based on the engagement score and automatically transmitting the at least one engagement nudge to the a device of the user; and a learning module for monitoring secondary feedback to the at least one patient nudge by the user on the device and altering subsequent patient nudges delivered to the device based on the secondary feedback, wherein the engagement score comprises a debt awareness score, a payment ability score, and a payment willingness score, wherein the debt awareness score is calculated based on a number of days a most recent payment is outstanding, wherein the payment ability score is calculated as payment ability score=Log (Tr)*(1/Tr*Tp), where Tr is a total amount owed over a predetermined time period by the user and Tp is a total amount paid over the predetermined time period by the user, and wherein the willingness score is calculated as willingness score=Ns*DelayMin (SUM(Pd)), where Ns is a number of statements in the predetermined time period provided to the user, DelayMin is the average number of days to receive payment from the user related to the number of statements.
2 . The payment engagement system according to claim 1 wherein the debt awareness score is calculated based on a number of days a most recent payment is outstanding.
3 . The payment engagement system according to claim 1 , wherein the awareness score, the ability score, and the willingness score are normalized before being combined to form the engagement score.
4 . The payment engagement system according to claim 1 , wherein the awareness score is assigned a first ranking, wherein the ability score is assigned a second ranking, and wherein the willingness score is assigned a third ranking.
5 . The payment engagement system according to claim 4 , wherein the nudge module selects the at least one engagement nudge based on the first ranking, the second ranking, or the third ranking.
6 . The payment engagement system according to claim 4 , wherein the first ranking is high, medium, or low.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Provisional Application Ser. No. 63/445,148, filed Feb. 13, 2023, the entire contents of which are hereby incorporated by reference in their entirety. FIELD OF THE INVENTION The present invention comprises a system and method for understanding and influencing behavioral drivers of key stakeholders to achieve predictable engagement outcomes in the healthcare industry (e.g., using an awareness, ability, and willingness (AAW) framework to reduce patient medical debt and improve collectability of patient share). BACKGROUND Most of the prevalent engagement solutions within healthcare today fail to deliver predictable and holistic engagement from the patients because they are solely focused on outreach instead of engagement. Patient engagement is a function of understanding their needs, awareness, ability and willingness to participate. Ability to text, email, and chat with the patient only generates outreach, which elicits what seems like early engagement but it fizzles out pretty quickly without any long term change in behavior. Another challenge with prevalent solutions is the generic nature of these engagement models which end up delivering generic content to the patients without understanding of their personalized needs and preferences. While some models use propensity to pay algorithms to predict likelihood of patients paying the outstanding bills, they are still vague, while effective in limited terms, do not holistically identify root cause driving the behavior and offer corrective long term solutions. SUMMARY Based on these limitations, a need clearly exists for a holistic engagement model deeply rooted in the principles of human psychology, behavioral economics and mathematical correlation after studying the behavior, attitude and preferences of patients. The AAW framework works by first identifying root causes that are causing lack of engagement and then uses the concept of behaviorally segmented ‘Nudges’ to deliver predictable engagement overtime. The AAW framework is preferably delivered using an artificial intelligence (AI) and machine learning (ML) technology platform to create personalized patient experience there by further enhancing and improving patient engagement. Further, the AI/ML model has cognitive learning abilities from the identified patterns, patient interactions and other inputs there by creating a perpetual loop of delivering precise nudges based on individual behaviors, outcomes delivered, interaction and other factors. It is therefore an object of the present invention to provide an AAW framework that utilizes human psychology and behavioral economics to understand root causes of disengagement and create solutions that cater to identified needs. Yet another object of the present invention is to provide personalized patient profiling based on individual preferences, behavior and attitudes. Another object of the present invention is to utilize ML to create an infinite learning engine that updates itself based on the input from interactions, behaviors, and outcome seen. It is another object of the present invention to provide personalized nudges to patients to increase engagement. It should also be obvious to one skilled in the art that the engagement learning model of the present invention has applications to other common problems in healthcare such as medicine adherence and appointment no show predictions. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 depicts a flowchart showing root causes of why patients do not engage. FIG. 2 depicts a system diagram of the engagement learning engine and its components. FIG. 3 depicts a system diagram of the engagement learning engine architecture. FIG. 4 depicts a plurality of sample nudges that may be provided to patients. DETAILED DESCRIPTION Referring first to FIG. 1, depicted is a flowchart showing likely root cause categories of why patients may not engage, especially with billing. Various aspects associated with patient behavior were analyzed to determine the root causes driving non-engagement. It was determined that the main causes for non-engagement were deficiencies in awareness, ability, and willingness (AAW). For example, many patients may have difficulty understanding different components of a bill and what their share is of the bill. Bills can often be confusing because they may detail absolute amounts or recurring charges within the same bill. Patient obligations, such as insurance deductibles, can also be difficult to understand. Many patients may also lack the ability to make payments due to various circumstances such as current financial ability or inability to access different or obscure payment methods. The most basic reason patients may not pay is that they currently cannot afford payments due to a variety of circumstances. Other times making payments may be difficult or time consuming. In certain circumstances, patients may simply be unwilling to make