US 12,148,513 B2
Medical indication determination using neural network prediction engine
Henrik Johansson, El Cerrito, CA (US); Tom Conti, Monona, WI (US); Tate Campbell, Richmond, CA (US); Bardia Afshin, Walnut Creek, CA (US); Justin Schield, Madison, WI (US); Daniel Anderson, Madison, WI (US); and Jared Lindaman, Rockton, IL (US)
Assigned to CHANGE HEALTHCARE HOLDINGS LLC, Nashville, TN (US)
Filed by Change Healthcare Holdings LLC, Nashville, TN (US)
Filed on Mar. 31, 2020, as Appl. No. 16/836,575.
Prior Publication US 2021/0304857 A1, Sep. 30, 2021
Int. Cl. G16H 10/60 (2018.01); G06F 40/30 (2020.01); G06N 3/08 (2023.01); G16H 40/63 (2018.01); G16H 40/67 (2018.01); G16H 50/30 (2018.01)
CPC G16H 10/60 (2018.01) [G06F 40/30 (2020.01); G06N 3/08 (2013.01); G16H 40/63 (2018.01); G16H 40/67 (2018.01); G16H 50/30 (2018.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving, by one or more processors, first information associated with a patient, second information associated with a provider, and third information associated with an order issued by the provider;
performing, by the one or more processors and using one or more layers of an artificial intelligence engine that comprises a multi-layer neural network, feature extraction on the first information, the second information, and the third information to reduce a dimensionality thereof;
determining, by the one or more processors and using the artificial intelligence engine that is trained using a data set that includes information on evidence based guidelines that support medical indication selection, a probability that a medical indication corresponds to the order based on the feature extraction from the first information, the second information, and the third information having the reduced dimensionality; and
automatically communicating, by the one or more processors and to an order entry system for entry therein, without input from the provider, an automatic selection of the medical indication when the probability exceeds a threshold.