Methods and systems of a patient insurance solution as a service for gig employees
In one aspect, a method for managing a patient-provider relationship, includes the step of providing a tiered structure for patient specific financial support. The method includes the step of providing a tailored patient financial workflows for pre-care financial commitment, approvals and post-care claims adjudication. The method includes the step of providing a multiple financial support options ranging from one off patient payment commitments, revolving options for multiple commitments or a fixed monthly amount determined by the patient. The method includes the step of providing a unified master servicing agreement that coordinates and manages the patient support experience and integrates the often-disparate servicing aims for payers, providers, credit underwriters.
1. A computer-implemented method of training a machine-learning based prediction engine for patient insurance solution as a service for gig employees comprising:
collecting a dataset of Unique Personas for predicting an enrollment in high-deductible health plan (HDHP) and a Health savings account (HSA);
collecting a dataset of an on-demand fund analysis comprising a set of wage and value-based predictors of on-demand funds needed for care;
cleaning the data set of Unique Personas and the dataset of an on-demand fund analysis;
creating a first training set comprising the collected set of the data set of Unique Personas;
creating a second training set comprising the dataset of an on-demand fund analysis; and
training the machine-learning based prediction engine in the first stage using the first training set and the second training set;
collecting a data set for utilization analysis comprising a set of preventive and chronic care-based drivers for value-based incentives using on-demand funds;
cleaning the data set for utilization analysis;
creating a third training set comprising the data set for utilization analysis;
training the machine-learning based prediction engine in a first stage using the first training set, the second training set, and third training set;
with the machine-learning based prediction engine generating a financial and healthcare plan design solution for predicting outcomes;
providing a population-based approach patient financials, payments and financing by:
segmenting the set of patients based on a demographic status, a social status, a health status and financial status to predict a financial need and total borrowing capacity of each patient,
reviewing of a patient portfolio of a patient and a determining which segment-based patient financial support and shared cost arrangement is appropriate for the patient, and
displaying the financial and healthcare plan design solution for predicting outcomes for the patient; and
using the financial and healthcare plan design solution for predicting outcomes to offer the patient a personalized point-of-care payments and credit solution without financial recourse to the healthcare provider, wherein the personalized point-of-care payments and credit solution without financial recourse to the healthcare provider comprises a set of tailored patient financial workflows for pre-care financial commitment, approvals and post-care claims adjudication.
2. The computerized method of claim 1 , wherein the data set for utilization analysis further comprises a census data set, and a healthcare exchange enrollment data set.
3. The computerized method of claim 2 , wherein the data set for utilization analysis further comprises a plan enrollment and risk selection data set and a historical insurance claims data set.