Back to results
US 10,095,761 B2Granted
System and method for text extraction and contextual decision support
AssigneeMedcpu, Inc.
InventorsEyal Ephrat, Noam Velan, Dani Cohen
Life of this patent
Estimating the term…
Abstract
A contextual analysis system that extracts data elements from an unstructured text input; determines whether the extracted data elements are relevant to a predetermined context; and determines, for the extracted elements deemed as relevant, whether the information contained in the relevant data elements complies with a guideline.
Claims14
A computer implemented method for automatically generating a medical decision for a patient having an associated electronic medical record, the method comprising:
- retrieving, with at least one computer processor, an electronic medical record data structure defining a patient condition, the patient condition associated with a context;
- retrieving, with the at least one computer processor, a voice input associated with the patient condition and a time stamp;
- generating, with the at least one computer processor executing a speech-to-text process, a text input data structure based on the voice input;
- tokenizing, with the at least one computer processor executing a natural language processing process, the text input to obtain a plurality of tokens including a first token and a second token;
- querying, with the at least one computer processor, a concept database for a first concept associated with the first token;
- querying, with the at least one computer processor, the concept database for a second concept associated with the second token;
- determining, with the at least one computer processor, that the first concept is associated with a time-based trigger based on the time stamp and the context;
- generating, with the at least one computer processor, a sequence comprising the first concept and the second concept;
- querying, with the at least one computer processor, a guideline database to obtain a guideline associated with the time-based trigger;
- generating, with the at least one computer processor, a determination that the sequence does not comply with the guideline;
- generating, with the at least one computer processor, a prompt describing a course of action for treating the patient based on the determination;
- and
- wherein the patient is treated according to the course of action.
10 more elements
A system for automatically generating a medical decision for a patient having an associated electronic medical record, the system comprising:
- at least one data processor;
- and
- memory storing instructions which, when executed by the at least one data processor, result in operations comprising:
- retrieving, with at least one computer processor, an electronic medical record data structure defining a patient condition, the patient condition associated with a context;
- retrieving, with the at least one computer processor, a voice input associated with the patient condition and a time stamp;
- generating, with the at least one computer processor executing a speech-to-text process, a text input data structure based on the voice input;
- tokenizing, with the at least one computer processor executing a natural language processing process, the text input to obtain a plurality of tokens including a first token and a second token;
- querying, with the at least one computer processor, a concept database for a first concept associated with the first token;
- querying, with the at least one computer processor, the concept database for a second concept associated with the second token;
- determining, with the at least one computer processor, that the first concept is associated with a time-based trigger based on the time stamp and the context;
- generating, with the at least one computer processor, a sequence comprising the first concept and the second concept;
- querying, with the at least one computer processor, a guideline database to obtain a guideline associated with the time-based trigger;
- generating, with the at least one computer processor, a determination that the sequence does not comply with the guideline;
- and
- generating, with the at least one computer processor, a prompt describing a course of action for treating the patient based on the determination.
12 more elements
A non-transitory computer program product storing instructions which, when executed by at least one data processor forming part of at least one computing system, result in operations for automatically generating a medical decision for a patient having an associated electronic medical record, the operations comprising:
- retrieving, with at least one computer processor, an electronic medical record data structure defining a patient condition, the patient condition associated with a context;
- retrieving, with the at least one computer processor, a voice input associated with the patient condition and a time stamp;
- generating, with the at least one computer processor executing a speech-to-text process, a text input data structure based on the voice input;
- tokenizing, with the at least one computer processor executing a natural language processing process, the text input to obtain a plurality of tokens including a first token and a second token;
- querying, with the at least one computer processor, a concept database for a first concept associated with the first token;
- querying, with the at least one computer processor, the concept database for a second concept associated with the second token;
- determining, with the at least one computer processor, that the first concept is associated with a time-based trigger based on the time stamp and the context;
- generating, with the at least one computer processor, a sequence comprising the first concept and the second concept;
- querying, with the at least one computer processor, a guideline database to obtain a guideline associated with the time-based trigger;
- generating, with the at least one computer processor, a determination that the sequence does not comply with the guideline;
- and
- generating, with the at least one computer processor, a prompt describing a course of action for treating the patient based on the determination.
9 more elements
Dependencies are inferred from the claim text.