Determining a genetic predisposition of a medical cause

A computing system for determining a genetic predisposition of a medical cause from a family tree analysis, comprising:

• a processor;
• a memory device coupled to the processor;
• and
• a computer readable storage device coupled to the processor, wherein the storage device contains program code executable by the processor via the memory device to implement a method, the method comprising:
• receiving, by a natural language understanding engine, medical symptoms of a patient;
• generating, by the natural language understanding engine, a set of questions from a supporting symptoms list;
• receiving, by the natural language understanding engine, medical narrations from family members of the patient represented in a family tree by asking the family members the generated set of questions;
• filtering, by a cognitive system, the medical narrations to provide a summary;
• generating, by the natural language understanding engine, insights based on the summary using a natural language processing technique;
• establishing, by the cognitive system, a linked tree of related words based on the insights;
• determining, by the cognitive system, likelihood paths through the family based on symptoms identified in the linked tree of related words;
• and
• matching, by the cognitive system, the determined likelihood paths with a known inheritance pattern of a disease to provide an alert to the family members about the disease.

A computer program product for determining a genetic predisposition of a medical cause from a family tree analysis, the computer program product comprising a computer readable storage device, and program instructions stored on the computer readable storage device, to:

• receive, by a natural language understanding engine, medical symptoms of a patient;
• generate, by the natural language understanding engine, a set of questions from a supporting symptoms list;
• receive, by the natural language understanding engine, medical narrations from family members of the patient represented in a family tree by asking the family members the generated set of questions;
• filter, by a cognitive system, the medical narrations to provide a summary;
• generate, by the natural language understanding engine, insights based on the summary using a natural language processing technique;
• establish, by the cognitive system, a linked tree of related words based on the insights;
• determine, by the cognitive system, likelihood paths through the family based on symptoms identified in the linked tree of related words;
• and
• match, by the cognitive system, the determined likelihood paths with a known inheritance pattern of a disease to provide an alert to the family members about the disease.