Systems and methods for determination of patient true state for risk management
Systems and methods for managing audit risks utilizing the true state of the patient are provided. A number of medical records for a patient are subjected to predictive modeling for various conditions (known as patient ‘true state’). The true state is then cross referenced by the eligible Medicare documentation, and any findings that are being submitted to MediCare for reimbursement. The result of this cross referencing is the ability to classify each finding and/or true state into a “green, “yellow”, or “red zone”. The green zone is where the finding, documentation and true state are in good alignment. A red zone is where the finding and the true state are entirely at odds. The yellow zone is where the findings and the true state are in agreement, but where there is still audit risk that may be resolved through one or more “opportunities”.
1. A health information system comprising:
a first pass analyzer in communication with at least one processor, wherein the at least one processor causes the first pass analyzer to:
infer a true state for a patient by applying a predictive model to medical concepts of a plurality of medical records for the patient, wherein the inferred true state is a condition of the patient; and
classify each of at least one coder finding into one of at least three confidence groups by cross-referencing the inferred true state with the at least one coder finding; and
a data warehouse manager in communication with the at least one processor, wherein the at least one processor causes configured to:
generate a structured data set including data values corresponding to the inferred true state and each classified coder finding with the respective confidence group, the structured data set enabling presentation at least one of (a) one or more of the data values in the form of a link to the plurality of medical records or (b) one or more annotations when the plurality of medical records include the one or more annotations; and
present the structured data set to a user.
2. The health information system of claim 1 further comprising a records database configured to receive the plurality of medical records for the patient.
3. The health information system of claim 1 , wherein the at least one processor further causes the first pass analyzer to identify the medical concepts in the plurality of medical records through machine learned relational clustering of medical terms.
4. The health information system of claim 1 , wherein the at least one processor further causes the first pass analyzer to cross-reference the inferred true state with MediCare eligible documentation.
5. The health information system of claim 1 , wherein the at least one processor further causes the first pass analyzer to generate a confidence level for the inferred true state.
6. The health information system of claim 1 , wherein the at least three confidence groups include a green zone, a yellow zone, and a red zone.
7. The health information system of claim 1 further comprising a validation system configured to validate the inferred true state, wherein the validation system is further configured to update the predictive model and a confidence level for the inferred true state.
8. A computer-implemented method implemented by a health information system including a data warehouse manager and a first pass analyzer, the method comprising:
inferring, by the first pass analyzer, a true state for a patient by applying a predictive model to medical concepts of a plurality of medical records for the patient, wherein the inferred true state is a condition of the patient;
classifying, by the first pass analyzer, each of at least one coder finding into one of at least three confidence groups by cross-referencing the inferred true state with the at least one coder finding;
generating, by the data warehouse manager, a structured data set including data values corresponding to the inferred true state and each classified coder finding with the respective confidence group, the structured data set enabling presentation of at least one of (a) one or more of the data values in the form of a link to the plurality of medical records or (b) one or more annotations when the plurality of medical records include the one or more annotations; and
presenting, by the data warehouse manager, the structured data set to a user.
9. The computer-implemented method of claim 8 , wherein the health information system further includes a records database configured to receive the plurality of medical records for the patient.
10. The computer-implemented method of claim 8 , wherein the first pass analyzer is further configured to identify the medical concepts in the plurality of medical records through machine learned relational clustering of medical terms.
11. The computer-implemented method of claim 8 , wherein the first pass analyzer is further configured to cross-reference the inferred true state with MediCare eligible documentation.
12. The computer-implemented method of claim 8 , wherein the first pass analyzer is further configured to generate a confidence level for the inferred true state.
13. The computer-implemented method of claim 8 , wherein the at least three confidence groups include a green zone, a yellow zone, and a red zone.
14. The computer-implemented method of claim 8 , wherein the health information system further includes a validation system configured to validate the inferred true state, wherein the validation system is further configured to update the predictive model and a confidence level for the inferred true state.
15. At least one non-transitory computer-readable storage medium having computer-executable instructions embodied thereon, wherein when executed by at least one processor of a health information system including a data warehouse manager and a first pass analyzer, the computer-executable instructions cause the at least one processor to:
infer a true state for a patient by applying a predictive model to medical concepts of a plurality of medical records for the patient, wherein the inferred true state is a condition of the patient; and
classify each of at least one coder finding into one of at least three confidence groups by cross-referencing the inferred true state with the at least one coder finding; and
generate a structured data set including data values corresponding to the inferred true state and each classified coder finding with the respective confidence group, the structured data set enabling presentation at least one of (a) one or more of the data values in the form of a link to the plurality of medical records or (b) one or more annotations when the plurality of medical records include the one or more annotations; and
present the structured data set to a user.
16. The computer-readable storage medium of claim 15 , wherein the health information system further includes a records database configured to receive the plurality of medical records for the patient.
17. The computer-readable storage medium of claim 15 , wherein the computer-executable instructions further cause the at least one processor to identify the medical concepts in the plurality of medical records through machine learned relational clustering of medical terms.
18. The computer-readable storage medium of claim 15 , wherein the computer-executable instructions further cause the at least one processor to cross-reference the inferred true state with MediCare eligible documentation.
19. The computer-readable storage medium of claim 15 , wherein the computer-executable instructions further cause the at least one processor to generate a confidence level for the inferred true state.
20. The computer-readable storage medium of claim 15 , wherein the health information system further includes a validation system configured to validate the inferred true state, wherein the validation system is further configured to update the predictive model and a confidence level for the inferred true state.