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 healthcare record from a first source system;
generating, by a first automated process, a first set of data items from the first healthcare record, the first automated process comprising natural language processing (NLP);
comparing the first set of data items to a second set of data items of a template;
detecting a missing data item which is absent from the first set of data items, based on the comparison with the template;
determining that an exception exists based on the detection of the missing data item;
generating an insight based on the exception;
parking, in a deferral queue, queued data comprising one or more of the insight or the exception;
comparing a number of exceptions to a threshold; and
presenting, via a graphical user interface, an indication associated with the insight, the presentation based on the comparison to the threshold.
2. The system of claim 1 , wherein the queued data comprises the exception and a plurality of further exceptions.
3. The system of claim 1 , wherein the operations comprise:
generating the missing data item based on the insight.
4. The system of claim 1 , wherein the operations comprise:
processing queued data from the deferral queue responsive to the number of exceptions of a document exceeding the threshold.
5. The system of claim 1 , wherein the operations comprise:
processing queued data from the deferral queue responsive to the number of exceptions of a healthcare record exceeding the threshold.
6. The system of claim 1 , wherein generating the missing data item comprises:
processing a non-discrete value to generate the missing data item.
7. The system of claim 1 , wherein the insight comprises:
generating a notification for conveyance to the graphical user interface indicative of the exception;
receiving an update corresponding to the missing data item; and
updating the first healthcare record.
8. The system of claim 1 , wherein the operations comprise:
receiving, from the graphical user interface, a selection of the indication; and
generating a data item based on the receipt of the selection,
wherein the indication is a suggestion associated with the insight.
9. A method, comprising:
receiving, by one or more processors, a first healthcare record from a first source system;
generating, by the one or more processors according to a first automated process, a first set of data items from the first healthcare record, the first automated process comprising natural language processing (NLP);
comparing, by the one or more processors, the first set of data items to a second set of data items of a template;
detecting, by the one or more processors, a missing data item which is absent from the first set of data items, based on the comparison with the template;
determining, by the one or more processors, that an exception exists based on the detection of the missing data item;
generating, by the one or more processors, an insight based on the exception;
parking in a deferral queue, by the one or more processors, queued data comprising one or more of the insight or the exception;
comparing, by the one or more processors, a number of exceptions to a threshold; and
presenting, via a graphical user interface by the one or more processors, an indication associated with the insight, the presentation based on the comparison to the threshold.
10. The method of claim 9 , wherein the queued data comprises the insight and a plurality of further insights.
11. The method of claim 9 , comprising:
generating, by the one or more processors, the missing data item based on the insight.
12. The method of to claim 9 , comprising:
processing, by the one or more processors, the queued data from the deferral queue responsive to the number of exceptions of a healthcare record exceeding the threshold.
13. The method of claim 9 , wherein generating the missing data item comprises:
processing, by the one or more processors, a non-discrete value to generate the missing data item.
14. The method of claim 9 , wherein the insight comprises:
generating, by the one or more processors, a notification for conveyance to the graphical user interface indicative of the exception;
receiving, by the one or more processors, an update corresponding to the missing data item; and
updating, by the one or more processors, the first healthcare record.
15. The method of claim 9 , comprising:
receiving, by the one or more processors and from the graphical user interface, a selection of the indication; and
generating, by the one or more processors, a data item based on the receipt of the selection,
wherein the indication is a suggestion associated with the insight.
16. A system comprising one or more processors, the system configured to:
receive, by the one or more processors, a first healthcare record from a first source system;
generate, by a first automated process of the one or more processors, a first set of data items from the first healthcare record, the first automated process comprising natural language processing (NLP);
compare, by the one or more processors, the first set of data items to a second set of data items of a template;
detect, by the one or more processors, a missing data item which is absent from the first set of data items, based on the comparison with the template;
determine, by the one or more processors, an exception exists based on the detection of the missing data item;
generate, by the one or more processors, an insight based on the exception;
park, in a deferral queue by the one or more processors, queued data comprising one or more of the insight or the exception;
compare, by the one or more processors, a number of exceptions to a threshold; and
present, by the one or more processors via a graphical user interface, an indication associated with the insight, the presentation based on the comparison to the threshold.
17. The system of claim 16 , comprising the one or more processors to:
process queued data from the deferral queue responsive to the number of exceptions of a document exceeding the threshold.
18. The system of claim 16 , wherein the insight comprises:
generation of a notification for conveyance to the graphical user interface indicative of the exception;
receipt of an update corresponding to the missing data item; and
generation of an updated first healthcare record.
19. The system of claim 16 , comprising the one or more processors to:
receive, from the graphical user interface, a selection of the indication; and
generate a data item based on the receipt of the selection,
wherein the indication is a suggestion associated with the insight.
20. The system of claim 16 , comprising the one or more processors to:
process queued data from the deferral queue responsive to the number of exceptions of a healthcare record or a document exceeding the threshold.