Cognitive building of medical condition base cartridges based on gradings of positional statements

A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to:

• parse a natural language positional statement data structure of a received medical treatment guidelines electronic document representing a natural language positional statement corresponding to a medical condition, wherein the medical treatment guidelines electronic document comprises natural language content specifying one or more treatments for the medical condition, and wherein the natural language positional statement specifies guidance information and one or more patient attributes indicative of patients for which an action may be performed for the medical condition;
• extract the one or more patient attributes, and a grading value associated with the natural language positional statement, from the natural language positional statement data structure, wherein the grading value is a value assigned to the natural language positional statement by an oversight organization that oversees treatment of the medical condition, in accordance with a grading policy used by the oversight organization, and identifies a determination by the oversight organization of a reliability of knowledge represented in the natural language positional statement based on a quality of evidence supporting the natural language positional statement;
• generate at least one weight value associated with each of the patient attributes based on at least the grading value associated with the natural language positional statement;
• and
• provide the knowledge data structure for the medical condition, based on the extracted one or more patient attributes and the at least one weight value in association with an identifier of the action and an identifier of the medical condition, to a cognitive medical system that performs a cognitive operation on one or more electronic medical records of a patient based on the knowledge data structure.

An apparatus comprising:

• a processor;
• and
• a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to:
• parse a natural language positional statement data structure of a received medical treatment guidelines electronic document representing a natural language positional statement corresponding to a medical condition, wherein the medical treatment guidelines electronic document comprises natural language content specifying one or more treatments for the medical condition, and wherein the natural language positional statement specifies guidance information and one or more patient attributes indicative of patients for which an action may be performed for the medical condition;
• extract the one or more patient attributes, and a grading value associated with the natural language positional statement, from the natural language positional statement data structure, wherein the grading value is a value assigned to the natural language positional statement by an oversight organization that oversees treatment of the medical condition, in accordance with a grading policy used by the oversight organization, and identifies a determination by the oversight organization of a reliability of knowledge represented in the natural language positional statement based on a quality of evidence supporting the natural language positional statement;
• generate at least one weight value associated with each of the patient attributes based on at least the grading value associated with the natural language positional statement;
• and
• provide the knowledge data structure for the medical condition, based on the extracted one or more patient attributes and the at least one weight value in association with an identifier of the action and an identifier of the medical condition, to a cognitive medical system that performs a cognitive operation on one or more electronic medical records of a patient based on the knowledge data structure.