Natural language understanding of conversational sources
Methods and systems for natural language processing/understanding of voice conversations are provided. Using natural language processing, a clinical condition is extracted from a voice conversation. A clinical ontology identifies clinical concepts associated with the clinical conditions. The clinical concepts are classified for documentation. The clinical concepts are searched and validated from within an individual's longitudinal record.
1. One or more non-transitory computer-readable media having computer-executable instructions embodied thereon that when executed, provide a method for enhanced natural language processing, the method comprising:
receiving one or more voice inputs;
segmenting the one or more voice inputs into a plurality of segments using a preconfigured threshold;
populating a transcription with the one or more voice inputs in an unstructured format, wherein the transcription is populated by stitching the plurality of segments into a sequence;
extracting at least one clinical condition from the one or more voice inputs;
validating the at least one clinical condition extracted when the at least one clinical condition is determined to correlate to structured data in a patient's electronic health record;
identifying one or more clinical concepts related to the clinical condition using one or more clinical ontologies for the at least one clinical condition, each clinical ontology providing contextual relationships between the clinical condition and the one or more clinical concepts;
utilizing the one or more clinical concepts, populating a graphical user interface with the one or more clinical concepts into one or more classification groups, the one or more classification groups corresponding to standard classifications;
providing the graphical user interface comprising the one or more clinical concepts in the one or more classification groups and a recommended location within the patient's electronic health record where each of the one or more clinical concepts is to be documented; and
providing a notification of an error, wherein the notification includes each of the error, at least a portion of the one or more voice inputs related to the error, and at least a portion of data from one or more validation sources conflicting with the one or more voice inputs.
2. The media of claim 1 , wherein the method further comprises validating the one or more voice inputs with the one or more validation sources.
3. The media of claim 2 , wherein the one or more validation sources comprises an electronic health record for an individual associated with the one or more voice inputs.
4. The media of claim 2 , wherein the one or more validation sources is an integrated device associated with an individual associated with the one or more voice inputs.
5. The media of claim 1 , wherein the one or more classification groups includes at least problems.
6. The media of claim 1 , wherein the standard classifications are defined by a standard utilized by a source system associated with a facility in which the one or more voice inputs are identified.
7. A computerized method, the method comprising:
receiving one or more voice inputs;
segmenting the one or more voice inputs into a plurality of segments using a preconfigured threshold;
populating a transcription with the one or more voice inputs in an unstructured format, wherein the transcription is populated by stitching the plurality of segments into a sequence;
extracting at least one clinical condition from the one or more voice inputs;
validating the at least one clinical condition extracted when the at least one clinical condition is determined to correlate to structured data in a patient's electronic health record;
identifying one or more clinical concepts related to the clinical condition using one or more clinical ontologies for the at least one clinical condition, each clinical ontology providing contextual relationships between the clinical condition and the one or more clinical concepts;
utilizing the one or more clinical concepts, populating a graphical user interface with the one or more clinical concepts into one or more classification groups, the one or more classification groups corresponding to standard classifications;
providing the graphical user interface comprising the one or more clinical concepts in the one or more classification groups and a recommended location within the patient's electronic health record where each of the one or more clinical concepts is to be documented; and
providing a notification of an error, wherein the notification includes each of the error, at least a portion of the one or more voice inputs related to the error, and at least a portion of data from one or more validation sources conflicting with the one or more voice inputs.
8. The method of claim 7 , wherein the method further comprises validating the one or more voice inputs with the one or more validation sources.
9. The method of claim 8 , wherein the one or more validation sources comprises an electronic health record for an individual associated with the one or more voice inputs.
10. The method of claim 8 , wherein the one or more validation sources is an integrated device associated with an individual associated with the one or more voice inputs.
11. The method of claim 8 , further comprising identifying an error within the one or more voice inputs based on the one or more validation sources.
12. The method of claim 7 , wherein the one or more classification groups includes at least problems.
13. The method of claim 12 , wherein the standard classifications are defined by a standard utilized by a source system associated with a facility in which the one or more voice inputs are identified.
14. A system comprising:
one or more processors to:
receive one or more voice inputs;
segmenting the one or more voice inputs into a plurality of segments using a preconfigured threshold;
populate a transcription with the one or more voice inputs in a n unstructured format, wherein the transcription is populated by stitching the plurality of segments into a sequence;
extract at least one clinical condition from the one or more voice inputs;
validate the at least one clinical condition extracted when the at least one clinical condition is determined to correlate to structured data in a patient's electronic health record;
identify one or more clinical concepts related to the clinical condition using one or more clinical ontologies for the at least one clinical condition, each clinical ontology providing contextual relationships between the clinical condition and the one or more clinical concepts;
utilize the one or more clinical concepts, populating a graphical user interface with the one or more clinical concepts into one or more classification groups, the one or more classification groups corresponding to standard classifications;
provide the graphical user interface comprising the one or more clinical concepts in the one or more classification groups and a recommended location within the patient's electronic health record where each of the one or more clinical concepts is to be documented; and
providing a notification of an error, wherein the notification includes each of the error, at least a portion of the one or more voice inputs related to the error, and at least a portion of data from one or more validation sources conflicting with the one or more voice inputs.