Automatic knowledge-based feature extraction from electronic medical records

A device for generating a query to extract clinical features into a set of electronic medical record (EMR) tables based on clinical knowledge, the device comprising:

• at least one processor;
• a memory operatively coupled to the at least one processor;
• and
• a set of computer program instructions stored in the memory and executed by the at least one in order to perform actions of:
• determining at least one clinical feature to be extracted from a set of EMR tables;
• obtaining a knowledge tree for the at least one clinical feature, the knowledge tree being constructed according to a set of clinical knowledge data associated with the at least one clinical feature, wherein the knowledge tree represents one or more rules defining the at least one clinical feature;
• obtaining, independent of the knowledge tree, an EMR graph corresponding to a set of EMR tables;
• generating a plurality of sub-queries based on the knowledge tree and the EMR graph;
• and
• composing at least one query for extracting the at least one clinical feature from the set of EMR tables by combining the plurality of sub-queries according to the knowledge tree.

A computer program product for generating a query to extract clinical features into a set of electronic medical record (EMR) tables based on clinical knowledge, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by at least one processor, to cause the at least one processor to perform a method comprising:

• determining at least one clinical feature to be extracted from a set of EMR tables;
• obtaining a knowledge tree for the at least one clinical feature, the knowledge tree being constructed according to a set of clinical knowledge data associated with the at least one clinical feature, wherein the knowledge tree represents one or more rules defining the at least one clinical feature;
• obtaining, independent of the knowledge tree, an EMR graph corresponding to a set of EMR tables, wherein the EMR graph comprises a set of table nodes and a set of attribute nodes, the set of table nodes and the set of attribute nodes representing a structure of each EMR table in the set of EMR tables and a reference relationship among attributes of set of EMR tables;
• generating a plurality of sub-queries based on the knowledge tree and the EMR graph;
• and
• composing at least one query for extracting the at least one clinical feature from the set of EMR tables by combining the plurality of sub-queries according to the knowledge tree.

A computer-implemented method for generating a query to extract clinical features from a set of electronic medical record (EMR) tables based on clinical knowledge, the computer-implemented method comprising:

• determining at least one clinical feature to be extracted from a set of EMR tables;
• obtaining a knowledge tree for the at least one clinical feature, the knowledge tree being constructed according to a set of clinical knowledge data associated with the at least one clinical feature, wherein the knowledge tree represents one or more rules defining the at least one clinical feature;
• obtaining, independent of the knowledge tree, an EMR graph corresponding to a set of EMR tables by converting the set of EMR tables to an equivalent graph representation;
• generating a plurality of sub-queries based on the knowledge tree and the EMR graph based on identifying a plurality of single-concept subtrees of the knowledge tree;
• composing at least one query for extracting the at least one clinical feature from the set of EMR tables by combining the plurality of sub-queries according to the knowledge tree;
• and
• searching for the at least one clinical feature within the set of EMR tables utilizing the at least one query.

A computer program product for generating a query to extract clinical features from a set of electronic medical record (EMR) tables based on clinical knowledge, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by at least one processor, to cause the at least one processor to perform a method comprising:

• determining at least one clinical feature to be extracted from a set of EMR tables;
• obtaining a knowledge tree for the at least one clinical feature, the knowledge tree being constructed according to a set of clinical knowledge data associated with the at least one clinical feature, wherein the knowledge tree represents one or more rules defining the at least one clinical feature;
• obtaining, independent of the knowledge tree, an EMR graph corresponding to a set of EMR tables by converting the set of EMR tables to an equivalent graph representation;
• generating a plurality of sub-queries based on the knowledge tree and the EMR graph based on identifying a plurality of single-concept subtrees of the knowledge tree;
• composing at least one query for extracting the at least one clinical feature from the set of EMR tables by combining the plurality of sub-queries according to the knowledge tree;
• and
• searching for the at least one clinical feature within the set of EMR tables utilizing the at least one query.