US 12,266,448 B2
Medical indication determination using heterogeneous data in a clinical decision support system
Changsung Moon, Kirkland, WA (US); and Feili Yu, Shoreline, WA (US)
Assigned to Change Healthcare Holdings LLC, Nashville, TN (US)
Filed by Change Healthcare Holdings LLC, Nashville, TN (US)
Filed on Nov. 30, 2021, as Appl. No. 17/538,273.
Prior Publication US 2023/0170092 A1, Jun. 1, 2023
Int. Cl. G16H 50/20 (2018.01); G06F 16/334 (2025.01)
CPC G16H 50/20 (2018.01) [G06F 16/334 (2019.01)] 17 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving, by one or more processors, input information associated with an examination order for a patient, the input information comprising first information associated with a plurality of variables and second information associated with a free-text query for the examination order;
generating, by the one or more processors and a first artificial intelligence (AI) model based on the plurality of variables, a plurality of variable vectors, respectively;
generating, by the one or more processors and a second AI model based on the free-text query, a free-text query vector;
aggregating, by the one or more processors, the plurality of variable vectors with the free-text query vector to generate an examination order vector;
generating, by the one or more processors, a knowledge graph associating the plurality of variables with a plurality of medical indications;
initializing, by the one or more processors, a neural network based at least in part on the knowledge graph;
determining, by the one or more processors and the neural network and based on the examination order vector, a set of medical indications corresponding to the examination order; and
automatically storing, by the one or more processors, an indication of the set of medical indications in an electronic medical record system.