Medical accountable provider platform
The technology described herein relates to using predictions about patients' future health care utilization and/or outcomes (e.g., patients' expected future adherence to medication regimens) and the expected economic benefits of targeted improvements in the same utilization and/or outcomes (e.g., reduced likelihood of hospitalization attributable to more consistent medication use) to implement more effective and efficient health care improvement programs. The technology described here computes which subset of patients should be included in a value-based health care provider payment scheme and what the specific bonus payment amounts should be such that expected benefits from better patient outcomes, once realized, are greater than the expected costs of the payment scheme itself.
1. A system configured to identify a patient population in a healthcare program based on, in part, a predictive function applied to characteristics of a patient, the system comprising:
a processor; and
a memory configured to store computer readable instructions that, when executed by the processor, cause the system to:
determine a list of health care providers and patients;
generate an adherence risk score for each patient using a prediction function;
apply the score to each patient in the list of patients;
identify a subset of patients from the one or more patients based on, at least, factors related to a likelihood of adherence after a given intervention is carried out; and
generate a user interface for display having at least a first view, wherein the first view includes:
an identification of at least one prescriber or an identification of at least one patient;
an itemized listing of therapy areas associated with each patient from the subset of patients, and
each line item in the itemized listing of therapy areas includes, at least, a monetary indication associated with at least one therapy in each line item.
2. The system of claim 1 , wherein the system is further caused to:
obtain one or more data files including historical data for each patient;
apply the historical data to one or more variables and generate a resultant data file; and
apply the resultant data file to a model setup procedure to generate a prediction function.
3. The system of claim 2 , wherein the model setup procedure includes dividing the resultant data file into a training data file and a validation data file, and the prediction function is generated by using the training data file over multiple statistical methods and then testing the prediction function against the validation data file.
4. The system of claim 1 , wherein
the identification of the at least one prescriber further includes a displayed portion indicating a number of patients associated with the at least one prescriber.
5. The system of claim 1 , wherein identification of the at least one patient further includes an indication of medication refill associated with a medication for the at least one patient.
6. The system of claim 1 , wherein each line item in the itemized listing further includes an identification of prescribing opportunity for the patient.
7. The system of claim 1 , wherein each line item in the line item listing of therapy areas further includes an indication of patient fill information for a medication associated with the at least one therapy.
8. The system of claim 1 , wherein the user interface includes at least a second view, wherein the user interface can be switched between the first view and the second view.
9. The system of claim 8 , wherein the second view includes:
a first portion containing an identification of a first condition, from one or more conditions associated with the patient, and an identification of at least one medication associated with the first condition.
10. The system of claim 9 , wherein the second view further includes:
an indication associated with patient outreach for the patient.
11. A method for generating a user interface, the method comprising:
generating an adherence risk score for each patient, from a plurality of patients, using a prediction function;
applying the score to each patient from the plurality of patients;
identifying a subset of patients from the plurality of patients based on, at least, factors related to a likelihood of adherence after a given intervention is carried out; and
generating a user interface for display having at least a first view, wherein the first view includes:
an itemized listing of therapies associated with subset of patients; and
an indication of prescription fill data associated with each therapy in the itemized listing of therapies, wherein
the user interface is configured to be switch from the first view to a second view, wherein the second view includes:
a first portion including identification information associated with a selected patient,
a second portion including an identification of a therapy associated with the selected patient, and
a third portion including identification of at least one medication associated with the therapy for the selected patient.
12. The method of claim 11 , wherein the second view further includes an indication associated with patient outreach for the patient.
13. The method of claim 11 , wherein the at least one medication associated with the therapy for the selected patient further includes an indication of days supply for the at least one medication.
14. The method of claim 11 , wherein the at least one medication associated with the therapy for the selected patient further includes a fill date associated with filling the at least one medication.
15. The method of claim 11 , wherein the at least one medication associated with the therapy for the selected patient further includes an identification of the prescriber of the at least one medication.
16. A system, comprising:
a processor; and
a memory configured to store computer readable instructions that, when executed by the processor, cause the system to:
generate an adherence risk score for each patient, from a plurality of patients, using a prediction function;
apply the score to each patient from the plurality of patients; and
generate a user interface for display having at least a first view, wherein the first view includes:
a first portion having a summary of therapies, wherein the summary of therapies includes an itemized listing of each therapy associated with the plurality of patients, and each therapy in the itemized listing includes an identification of the therapy and an identification of a number of patients associated with the therapy.
17. The system of claim 16 , wherein the first view further includes a second portion including a graph associated with the one or more therapies.
18. The system of claim 16 , wherein each therapy in the itemized listing includes a number associated with treatment for the therapy.
19. The system of claim 16 , wherein the user interface is configured to be updated from the first view to a second view.
20. The system of claim 19 , wherein the second view includes information associated with a medical health practice and the second view includes a portion having a listing of medical providers.