Systems and methods for automated scribes based on knowledge graphs of clinical information

Abstract

According to certain embodiments, the present disclosure includes a method for generating a knowledge graph of clinical information for use as a reference model to semantically represent relevant information from clinical encounters. In certain embodiments, the method includes representing a clinical concern as a module of the knowledge graph. In some examples, the method includes associating at least one section node with the module, wherein each section node of the at least one section node corresponds to a clinical concept relevant to the clinical concern and associating at least one topic node with the at least one section node, wherein each topic node of the at least one topic node corresponds to a clinical topic relevant to the clinical concept. And, in certain embodiments the method includes outputting the knowledge graph of clinical information to semantically represent the relevant information from a clinical encounter associated with the clinical concern.

1 .- 17 . (canceled) 
     
     
         18 . A computer-implemented method for generating a knowledge graph of clinical information for use as a reference model to semantically represent relevant information from clinical encounters, the method comprising:
 receiving representative data of a conversation between a health care provider and a patient during an actual clinical encounter;   reducing the representative data to a set of related key concepts;   receiving a knowledge graph of clinical information, wherein the knowledge graph includes a set of nodes having specific attributes that form a clinical reference for a clinical concern, wherein the set of nodes is represented as a module of the knowledge graph of clinical information;   mapping the set of related key concepts to the knowledge graph of clinical information;   associating the set of related key concepts to the module; and   outputting the knowledge graph of clinical information to semantically represent the relevant information from the actual clinical encounter associated with the clinical concern.   
     
     
         19 . The computer-implemented method of  claim 18 , wherein the set of nodes of the knowledge graph are organized around expected clinical concepts. 
     
     
         20 . The computer-implemented method of  claim 19 , wherein the set of nodes are encoded based on at least one selected from a group consisting of relevance, related ontology, codification, hierarchy, sequence, and related expression with respect to an encounter document. 
     
     
         21 . The computer-implemented method of  claim 18 , wherein the module is related to the clinical concern. 
     
     
         22 . The computer-implemented method of  claim 21 , wherein the module includes an array of associated keywords, diagnoses, and/or affiliated specialties. 
     
     
         23 . The computer implemented method of  claim 21 , wherein the module includes one or more children sections. 
     
     
         24 . The computer-implemented method of  claim 23 , wherein the one or more children sections include at least one of one or more section nodes, one or more topic nodes, one or more sub-topic nodes, one or more attribute nodes, and one or more concept nodes. 
     
     
         25 . The computer-implemented method of  claim 23 , wherein the one or more children sections within the module reflect sequential steps within possible clinical encounters. 
     
     
         26 . The computer-implemented method of  claim 24 , wherein the one or more children sections within the module reflect one or more sequential groups of clinical concepts within each step of the one or more sequential steps that are related to a standard of care and common practice of medicine. 
     
     
         27 . The computer-implemented method of  claim 26 , wherein each clinical concept is indexed to at least one relevant clinical ontology via a representative code. 
     
     
         28 . The computer-implemented method of  claim 18 , wherein the knowledge graph comprises a searchable referential map of medical knowledge and/or standards of care. 
     
     
         29 . The computer-implemented method of  claim 28 , wherein the searchable referential map includes a ranked order of modules that conform to an input pattern of the representative data. 
     
     
         30 . The computer-implemented method of  claim 28 , wherein the searchable referential map includes a determination of matched concepts that link actual input of the representative data to expected input. 
     
     
         31 . The computer-implemented method of  claim 30 , wherein the searchable referential map includes a narrative output resulting from a union of the matched concepts and associated expression attributes. 
     
     
         32 . The computer-implemented method of  claim 28 , wherein the searchable referential map includes a confirmed set of codified and structured clinical concepts. 
     
     
         33 . The computer-implemented method of  claim 18 , further comprising associating one or more section nodes with the module, wherein each section node of the one or more section nodes corresponds to a clinical concept relevant to the clinical concern and associating one or more topic nodes with the at least one section node, wherein each topic node of the at least one topic node corresponds to a clinical topic relevant to the clinical concept. 
     
     
         34 . The computer-implemented method of  claim 33 , wherein the one or more section nodes correspond to at least one selected from a group including history of present illness, review of systems, examination, history, diagnosis, and care plan. 
     
     
         35 . The computer-implemented method of  claim 33 , wherein the at least one topic node corresponds to at least one selected from a group including onset, location, pain, alleviating factors, aggravating factors, timing, and reason for visit. 
     
     
         36 . The computer-implemented method of  claim 33 , further comprising associating one or more sub-topic nodes with the at least one topic node, wherein each sub-topic node of the one or more sub-topic nodes corresponds to a sub-topic to the clinical topic. 
     
     
         37 . The computer-implemented method of  claim 36 , further comprising associating one or more attribute nodes with the one or more sub-topic nodes, wherein each attribute node of the one or more attribute nodes corresponds to a qualifying attribute for the sub-topic. 
     
     
         38 . A computing system for generating codes, the computing system comprising:
 one or more memories having instructions thereon; and   one or more processors configured to execute the instructions and perform operations comprising:   receiving representative data of a conversation between a health care provider and a patient during an actual clinical encounter;   reducing the representative data to a set of related key concepts;   receiving a knowledge graph of clinical information, wherein the knowledge graph includes a set of nodes having specific attributes that form a clinical reference for a clinical concern, wherein the set of nodes is represented as a module of the knowledge graph of clinical information;   mapping the set of related key concepts to the knowledge graph of clinical information;   associating the set of related key concepts to the module; and   
       outputting the knowledge graph of clinical information to semantically represent the relevant information from the actual clinical encounter associated with the clinical concern.