Semantically augmented clinical speech processing
AssigneeCerner Innovation, Inc.
InventorsEmin Agassi, Jodi Kodish-Wachs
Life of this patent
Estimating the term…
Abstract
Methods and systems for processing of voice input to identify intents and mapped standard terminologies are provided. Using natural language processing, an intent of a voice input is identified. The intent is utilized to identify a standard terminology that maps to the intent. The standard terminology is utilized to identify information relevant to the standard terminology in a patient's electronic health record.
Claims20
A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause one or more data processors to perform a set of actions comprising:
- processing, by a speech processing and mapping system, a voice input associated with a user;
- accessing, a terminology graph comprising inter-relationships between a plurality of standard terminologies including clinical terms and non-clinical terms;
- adaptively traversing, by a gateway of the system, the terminology graph to identify and remove redundant content and to bulk load medical terminology content into a natural language processing engine associated with the one or more data processors;
- identifying, using the natural language processing engine, an intent of the user from the voice input based on the traversal of the terminology graph;
- mapping, using a semantic mapper associated with the one or more data processors, the intent to a standard terminology of the plurality of standard terminologies based on the terminology graph, to obtain a mapped standard terminology;
- identifying, based on the mapped standard terminology, at least one relevant item from a plurality of items available in an electronic record associated with the user, wherein the plurality of items is related to clinical states of the user;
- and
- generating, based on the at least one relevant item and the mapped standard terminology, action items indicating clinical findings related to the user, wherein the action items are populated in the electronic record.
A system comprising:
- one or more data processors;
- and
- a non-transitory computer-readable medium storing instructions that when executed by the one or more data processors, cause the one or more data processors to perform operations including:
- processing, by a speech processing and mapping system, a voice input associated with a user;
- accessing, a terminology graph comprising inter-relationships between a plurality of standard terminologies including clinical terms and non-clinical terms;
- adaptively traversing, by a gateway of the system, the terminology graph to identify and remove redundant content and to bulk load medical terminology content into a natural language processing engine associated with the one or more data processors;
- identifying, using the natural language processing engine associated with the one or more data processors, an intent of the user from the voice input based on the traversal of the terminology graph;
- mapping, using a semantic mapper associated with the one or more data processors, the intent to a standard terminology of the plurality of standard terminologies based on the terminology graph, to obtain a mapped standard terminology;
- identifying, based on the mapped standard terminology, at least one relevant item from a plurality of items available in an electronic record associated with the user, wherein the plurality of items is related to clinical states of the user;
- and
- generating, based on the at least one relevant item and the mapped standard terminology, action items indicating clinical findings related to the user, wherein the action items are populated in the electronic record.
A computer-implemented method comprising:
- processing, by a speech processing and mapping system, a voice input associated with a user;
- accessing, by one or more data processors of the speech processing and the mapping system, a terminology graph comprising inter-relationships between a plurality of standard terminologies including clinical terms and non-clinical terms;
- adaptively traversing, by a gateway of the system, the terminology graph to identify and remove redundant content and to bulk load medical terminology content into a natural language processing engine associated with the one or more data processors;
- identifying, using the natural language processing engine associated with the one or more data processors, an intent of the user from the voice input based on the traversal of the terminology graph;
- mapping, using a semantic mapper associated with the one or more data processors, the intent to a standard terminology of the plurality of standard terminologies based on the terminology graph, to obtain a mapped standard terminology;
- identifying, by the one or more data processors based on the mapped standard terminology, at least one relevant item from a plurality of items available in an electronic record associated with the user, wherein the plurality of items is related to clinical states of the user;
- and
- generating, by the one or more data processors based on the at least one relevant item and the mapped standard terminology, action items indicating clinical findings related to the user, wherein the action items are populated in the electronic record.
Dependencies are inferred from the claim text.