Systems and methods for determination of patient true state for personalized medicine
Systems and methods for personalizing medicine 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 patient personal information, previous care, and true state may be provided into a state machine in order to determine the resources needed for the patient. The medical resources may be any of laboratory services, diagnostics, therapies and medications. Using the true state information, and number of activities may be performed for the patient based upon the patient's needs. These activities include scheduling lab or diagnostic procedures in advance of an appointment, filling in documentation gaps, identifying items that require additional documentation using the true state, and tracking follow-up. It may also be beneficial to validate the true state.
1. A health information computer system comprising:
at least one memory with instructions stored thereon; and
at least one processor in communication with the at least one memory, wherein the instructions, when executed by the at least one processor, cause the at least one processor to:
perform natural language processing on a plurality of machine-readable medical records to extract terms from the plurality of machine-readable medical records;
convert the terms extracted from the plurality of machine-readable medical records into a standardized and structured data set, wherein the data set comprises hyperlinks to at least a portion of the plurality of machine-readable medical records to facilitate real-time reference from the data set to the plurality of machine-readable medical records;
cluster the terms into medical concept data;
determine a condition of a patient based on the medical concept data and at least one probabilistic model;
identify evidence associated with the condition of the patient that comprises a largest impact in the determination of the condition with respect to other evidence;
generate an output comprising an indication of the condition and at least one hyperlink of the hyperlinks associated with the evidence comprising the largest impact; and
validate the condition of the patient based on validating the evidence comprising the largest impact.
2. The health information computer system of claim 1 , wherein the instructions further cause the at least one processor to:
identify the terms in the plurality of machine-readable medical records by an analytics module.
3. The health information computer system of claim 2 , wherein the instructions further cause the at least one processor to:
analyze the plurality of machine-readable medical records by the analytics module; and
assign a confidence score to the condition based at least in part upon the plurality of machine-readable medical records.
4. The health information computer system of claim 1 , wherein the instructions further cause the at least one processor to calculate a respective impact for evidence comprising at least a portion of the medical concept data, wherein the impact is based on at least one of cost per time or audit risk per time.
5. The health information computer system of claim 1 , wherein the instructions further cause the at least one processor to cluster the terms into medical concept data based at least in part upon machine learned rules.
6. The health information computer system of claim 1 , wherein the instructions further cause the at least one processor to identify at least one medical resource for the patient based upon the condition of the patient.
7. The health information computer system of claim 1 , wherein the instructions further cause the at least one processor to, based on the condition of the patient, automatically schedule at least one of an appointment, a lab procedure, or a diagnostic procedure.
8. The health information computer system of claim 1 , wherein the instructions further cause the at least one processor to fill documentation gaps associated with the patient based on the condition of the patient.
9. The health information computer system of claim 1 , wherein the instructions further cause the at least one processor to cause display of the evidence comprising the largest impact in the determination of the condition.
10. At least one non-transitory computer-readable storage medium with instructions stored thereon that, in response to execution by at least one processor, cause the at least one processor to:
perform natural language processing on a plurality of machine-readable medical records to extract terms from the plurality of machine-readable medical records;
convert the terms extracted from the plurality of machine-readable medical records into a standardized and structured data set, wherein the data set comprises hyperlinks to at least a portion of the plurality of machine-readable medical records to facilitate real-time reference from the data set to the plurality of machine-readable medical records;
cluster the terms into medical concept data;
determine a condition of a patient based on the medical concept data and at least one probabilistic model;
identify evidence associated with the condition of the patient that comprises a largest impact in the determination of the condition with respect to other evidence;
generate an output comprising an indication of the condition and at least one hyperlink of the hyperlinks associated with the evidence comprising the largest impact and
validate the condition of the patient based on validating the evidence comprising the largest impact.
11. The at least one non-transitory computer-readable storage medium of claim 10 , wherein the instructions further cause the at least one processor to:
identify the terms in the plurality of machine-readable medical records by an analytics module.
12. The at least one non-transitory computer-readable storage medium of claim 11 , wherein the instructions further cause the at least one processor to:
analyze the plurality of machine-readable medical records by the analytics module; and
assign a confidence score to the condition based at least in part upon the plurality of machine-readable medical records.
13. The at least one non-transitory computer-readable storage medium of claim 10 , wherein the instructions further cause the at least one processor to calculate a respective impact for evidence comprising at least a portion of the medical concept data, wherein the impact is based on at least one of cost per time or audit risk per time.
14. The at least one non-transitory computer-readable storage medium of claim 10 , wherein the instructions further cause the at least one processor to cluster the terms into medical concept data based at least in part upon machine learned rules.
15. The at least one non-transitory computer-readable storage medium of claim 10 , wherein the instructions further cause the at least one processor to identify at least one medical resource for the patient based upon the condition of the patient.
16. The at least one non-transitory computer-readable storage medium of claim 10 , wherein the instructions further cause the at least one processor to, based on the condition of the patient, automatically schedule at least one of an appointment, a lab procedure, or a diagnostic procedure.
17. The at least one non-transitory computer-readable storage medium of claim 10 , wherein the instructions further cause the at least one processor to fill documentation gaps associated with the patient based on the condition of the patient.
18. The at least one non-transitory computer-readable storage medium of claim 10 , wherein the instructions further cause the at least one processor to cause display of the evidence comprising the largest impact in the determination of the condition.
19. A method for medical care implemented by a health information management system comprising at least one processor in communication with at least one memory, the method comprising:
performing natural language processing on a plurality of machine-readable medical records to extract terms from the plurality of machine-readable medical records;
converting the terms extracted from the plurality of machine-readable medical records into a standardized and structured data set, wherein the data set comprises hyperlinks to at least a portion of the plurality of machine-readable medical records to facilitate real-time reference from the data set to the plurality of machine-readable medical records;
clustering the terms into medical concept data;
determining a condition of a patient based on the medical concept data and at least one probabilistic model;
identifying evidence associated with the condition of the patient that comprises a largest impact in the determination of the condition with respect to other evidence;
generating an output comprising an indication of the condition and at least one hyperlink of the hyperlinks associated with the evidence comprising the largest impact and
validating the condition of the patient based on validating the evidence comprising the largest impact.
20. The method of claim 19 , further comprising, based on the condition of the patient, automatically scheduling at least one of an appointment, a lab procedure, or a diagnostic procedure.