System and method for handling exceptions during healthcare record processing
Methods, systems, and apparatuses to improve the handling of exceptions during the retrieval and processing of health records from various data sources are provided. During the retrieval and processing of health records, exceptions to typical behavior are recorded with context at the data extraction protocol level, at the health record level and at the level of elements with the document. Accordingly, insights may be developed and configurations, rules, or coding changes, based on the detected exceptions may be proposed. In some instances, an operator may be notified about the exceptions such that the operator may act on the insight. In some instances, the processing of extracted records (documents, messages) may be deferred until the operator has made appropriate changes to configuration, rules, or code. In some instances, the system may supplement and/or replace the operator with machine learning engines that act on the developed insights.
1. A system comprising:
at least one processor; and
a non-transitory memory storing instructions that, when executed by the at least one processor, causes the system to perform a set of operations, the set of operations comprising:
receiving a first portion of a health record from a first source system;
receiving a second portion of the health record;
analyzing the first portion of the health record for one or more exceptions, the exceptions identifying information that is:
omitted in the first portion of the health record and present in the second portion of the health record; or
formatted in the first portion of the health record differently than analogous information of the second portion of the health record; and
generating at least one insight based on the one or more exceptions, the insight to normalize the first portion of the health record with the second portion of the health record.
2. The system of claim 1 , wherein the set of operations causes the at least one insight to be displayed at a user interface of a display device.
3. The system of claim 1 , wherein the first portion of the health record comprises a data value and the one or more exceptions identifies a format of the data value by comparing the data value to a defined range.
4. The system of claim 3 , wherein:
the second portion of the health record is received from a second source system;
the defined range is based on the second source system;
the data value is outside of the defined range; and
the at least one insight reformats the data value, the reformatted data value being within the defined range.
5. The system of claim 4 , wherein the defined range is specific to a data type of the data value, the data type comprising one of an integer data type, a floating data type, a string data type, or a free text data type.
6. The system according to claim 4 , wherein the set of operations includes analyzing the first portion of the health record utilizing the reformatted data value.
7. The system of claim 1 , wherein the one or more exceptions includes at least one unexpected data element and/or an unexpected object property, the unexpected data element and/or the unexpected object property being present in the second portion of the health record and absent in the first portion of the health record.
8. The system of claim 7 , wherein the at least one insight recasts the unexpected data element and/or the unexpected object property to provide a second data element and/or property, the second data element and/or property being expected by the system.
9. The system of claim 8 , wherein the set of operations includes analyzing the first portion of the health record utilizing the second data element and/or property.
10. The system of claim 1 , wherein the one or more exceptions include an encoding of a data value.
11. The system of claim 10 , wherein the at least one insight provides a second encoding of the data value, the second encoding being expected by the system.
12. The system of claim 11 , wherein the set of operations includes analyzing the portion of the health record utilizing the second data encoding.
13. The system of claim 1 , wherein the set of operations includes:
detecting an incorrectly identified data format; and
mapping the incorrectly identified data format to a correct data format.
14. The system of claim 1 , wherein the one or more exceptions include a reference to a document that is not directly accessible by the system.
15. The system of claim 14 , wherein the at least one insight provides a means to attempt to gain access to the referenced document.
16. The system of claim 1 , wherein the one or more exceptions include coded concepts that are identified as missing or suspected of being missing.
17. The system of claim 16 , wherein the at least one insight provides a proposed data value based on at least one of a missing data value, suspected missing data value, and/or other content in the health record, wherein the proposed data value is within a range of the coded concept.
18. The system of claim 17 , wherein the proposed data value coded concept is specific to a missing or suspected missing coded concept.
19. The system of claim 1 , wherein the one or more exceptions include at least one of an identity of a patient, an insurance member, a healthcare provider, an owner of the health record, and/or an instance where a custodian of the health record cannot be at least one of determined, verified, and/or trusted by the system.
20. The system of claim 19 , wherein the at least one insight provides a second identity value that is at least one of determined, verified, and/or trusted by the system.
21. The system of claim 1 , wherein the set of operations includes at least one of:
receiving an indication to delay processing of the portion of the health record;
providing a proposed change to a processing rule associated with a data value included in the one or more exceptions;
providing a proposed change to a processing rule associated with a data field included in the health record;
receiving an indication to accept the at least one insight to modify a data element associated with the one or more exceptions; or
detecting an incorrectly identified data format; and mapping the incorrectly identified data format to a correct data format.
22. A method comprising:
receiving a first portion of a health record from a first source system;
receiving a second portion of the health record from a second source system;
analyzing the first portion of the health record for one or more exceptions, the exceptions identifying information that is:
omitted in the first portion of the health record and present in the second portion of the health record; or
formatted in the first portion of the health record differently than analogous information of the second portion of the health record; and
generating at least one insight based on the one or more exceptions, the insight to normalize the first portion of the health record with the second portion of the health record.
23. A non-transitory computer-readable medium comprising instructions that when executed by a processor, cause the processor to:
receive a first portion of a health record from a first source system;
receiving a second portion of the health record from a second source system;
analyze the first portion of the health record for one or more exceptions, the exceptions identifying information that is:
omitted in the first portion of the health record and present in the second portion of the health record; or
formatted in the first portion of the health record differently than analogous information of the second portion of the health record;
generate at least one insight based on the one or more exceptions, the insight to normalize the first portion of the health record with the second portion of the health record; and
cause the at least one insight to be displayed at a user interface of a display device.