FIELD: information technology.
SUBSTANCE: invention relates to methods of recognition and analysis. The technical result consists in increasing the accuracy of identifying adverse events from unstructured text records of the patient's medical history. A method for determining adverse events from unstructured text records of patient medical records, which consists in analyzing unstructured records of electronic medical records of patients using an algorithm for determining and classifying a medical concept characterizing an adverse event, obtaining unstructured text medical data, and combining them into a plurality of texts; carry out tokenization of texts into words, delete words that occur less often than a specified number of times, the remaining words lead to the initial form and correct typos in them, identify the defined medical concept in the set of remaining words and name it, delete words for which the measure of context proximity is below a given threshold , in selected nouns, adjectives, verbs, signs of the concept being defined are found, indicating its functions, on the basis of the above algorithm, adverse events associated with a disease or medical intervention are identified in the patient's electronic medical record.
EFFECT: in increasing the accuracy of identifying adverse events from unstructured text records of the patient's medical history.
4 cl, 1 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD FOR EXTRACTING INFORMATION FROM UNSTRUCTURED TEXTS WRITTEN IN NATURAL LANGUAGE | 2020 |
|
RU2751993C1 |
METHOD FOR ATTRIBUTION OF PARTIALLY STRUCTURED TEXTS FOR FORMATION OF NORMATIVE-REFERENCE INFORMATION | 2020 |
|
RU2750852C1 |
NAMED ENTITIES FROM THE TEXT AUTOMATIC EXTRACTION | 2014 |
|
RU2665239C2 |
METHOD FOR AUTOMATIC SEMANTIC CLASSIFICATION OF NATURAL LANGUAGE TEXTS | 2013 |
|
RU2538304C1 |
CONTEXT-BASED METHOD OF ASSESSING MANIFESTATION DEGREE OF NOTION IN TEXT FOR SEARCH SYSTEMS | 2007 |
|
RU2348072C1 |
METHOD FOR AUTOMATED ANALYSIS OF TEXT AND SELECTION OF RELEVANT RECOMMENDATIONS TO IMPROVE READABILITY THEREOF | 2021 |
|
RU2769427C1 |
RETRIEVAL OF INFORMATION OBJECTS USING A COMBINATION OF CLASSIFIERS ANALYZING LOCAL AND NON-LOCAL SIGNS | 2018 |
|
RU2686000C1 |
RECOVERY OF TEXT ANNOTATIONS RELATED TO INFORMATION OBJECTS | 2017 |
|
RU2665261C1 |
AUTOMATED LEGAL ADVICE SYSTEM CONTROL METHOD | 2019 |
|
RU2718978C1 |
METHOD OF POSITIONING TEXT IN KNOWLEDGE SPACE BASED ON ONTOLOGY SET | 2009 |
|
RU2476927C2 |
Authors
Dates
2023-05-12—Published
2022-02-15—Filed