Document generation from 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. Non-transitory computer-readable-readable media having computer-executable instructions embodied thereon that when executed, provide a method for enhanced natural language processing, the method comprising:
receiving a voice conversation associated with an individual;
parsing and extracting at least one clinical condition within the voice conversation using one or more natural language processing techniques;
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;
verifying each concept of the one or more clinical concepts within the voice conversation by searching structured data in one or more validation sources;
validating at least one concept of the one or more clinical concepts by determining that structured data in at least one of the one or more validation sources is determined to correspond to the at least one concept of the one or more clinical concepts within the voice conversation;
identifying an error within at least one concept of the one or more clinical concepts of the voice conversation based on the one or more validation sources; and
generating one or more outputs that include the at least one concept of the one or more concepts that is determined to be validated based on the one or more validation sources and an indication of the error, wherein the indication of the error includes each of the error, at least a portion of the voice conversation related to the error, and at least a portion of the structured data from the one or more validation sources conflicting with the voice conversation.
2. The media of claim 1 , wherein the one or more validation sources includes an integrated device.
3. The media of claim 1 , wherein the one or more validation sources includes an electronic health record (EHR) for the individual.
4. The media of claim 1 , wherein the at least one concept of the one or more concepts that is determined to be validated is a documentation-type item to be directly documented into an electronic health record (EHR) for the individual.
5. The media of claim 1 , wherein the one or more outputs comprises a document.
6. The media of claim 5 , wherein the document is a referral document.
7. A computerized method, the method comprising: receiving a voice conversation associated with an individual;
parsing and extracting at least one clinical condition within the voice conversation using one or more natural language processing techniques;
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;
verifying each concept of the one or more clinical concepts within the voice conversation by searching structured data in one or more validation sources;
validating at least one concept of the one or more clinical concepts by determining that structured data in at least one of the one or more validation sources is determined to correspond to the at least one concept of the one or more clinical concepts within the voice conversation;
determining an error within the one or more clinical concepts of the voice conversation based on the one or more validation sources; and
generating one or more outputs that include the one or more concepts determined to be validated based on the one or more validation sources and an indication of the error within the one or more clinical concepts of the voice conversation, wherein the indication of the error includes each of the error, at least a portion of the voice conversation related to the error, and at least a portion of the structured data from the one or more validation sources conflicting with the voice conversation.
8. The method of claim 7 , wherein the one or more validation sources includes an integrated device.
9. The method of claim 7 , wherein the one or more validation sources includes an electronic health record (EHR) for the individual.
10. The method of claim 7 , wherein the at least one concept of the one or more concepts that is determined to be validated comprises a documentation-type item to be directly documented into an electronic health record (EHR) for the individual.
11. The method of claim 7 , wherein the validated output is one or more outputs comprises a document.
12. The method of claim 11 , wherein the document is a referral document.
13. A system comprising:
one or more processors to:
receive a voice conversation associated with an individual;
parse and extracting at least one clinical condition within the voice conversation using one or more natural language processing techniques;
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;
verify each concept of the one or more clinical concepts within the voice conversation by searching structured data in one or more validation sources;
validate at least one concept of the one or more clinical concepts by determining that structured data in at least one of the one or more validation sources is determined to correspond to the at least one concept of the one or more clinical concepts within the voice conversation;
determine an error within the one or more clinical concepts of the voice conversation based on the one or more validation sources; and
generate one or more outputs that include the one or more concepts determined to be validated based on the one or more validation sources and an indication of the error within the one or more clinical concepts of the voice conversation, wherein the indication of the error includes each of the error, at least a portion of the voice conversation related to the error, and at least a portion of the structured data from the one or more validation sources conflicting with the voice conversation.
14. The system of claim 13 , wherein the one or more processors can further identify, within the voice conversation, a speaker, a role of the speaker, and a time stamp of a voice input of the voice conversation.