US 12,334,220 B1
Clinical decision support system using phenotypic features
Douglas S. McNair, Seattle, WA (US); John Christopher Murrish, Overland Park, KS (US); and Kanakasabha Kailasam, Olathe, KS (US)
Assigned to CERNER INNOVATION, INC., Kansas City, MO (US)
Filed by CERNER INNOVATION, INC., Kansas City, KS (US)
Filed on Nov. 19, 2021, as Appl. No. 17/531,337.
Application 17/531,337 is a continuation of application No. 15/291,792, filed on Oct. 12, 2016, granted, now 11,183,302.
Claims priority of provisional application 62/240,515, filed on Oct. 12, 2015.
This patent is subject to a terminal disclaimer.
Int. Cl. G16H 50/20 (2018.01); G16H 10/60 (2018.01); G16H 50/70 (2018.01)
CPC G16H 50/20 (2018.01) [G16H 10/60 (2018.01); G16H 50/70 (2018.01)] 20 Claims
OG exemplary drawing
 
1. A method for generating one or more sequence itemset models to determine whether a human patient has clinical conditions, the method comprising:
acquiring data associated with at least one electronic health record for a first set of clinical condition patients and a first set of control patients;
determining a first codeset for the data associated with at least one electronic health record for the first set of clinical condition patients and the first set of control patients;
analyzing the first codeset to identify a first statistically significant sequence itemset for a first clinical condition that is supported by the first set of clinical condition patients and is not supported by the first set of control patients, wherein the first statistically significant sequence itemset has a first confidence value of at least 0.10 within a first epoch duration that depends on patient age;
acquiring data associated with at least one electronic health record for a second set of clinical condition patients and a second set of control patients;
determining a second codeset for the data associated with at least one electronic health record for the second set of clinical condition patients and the second set of control patients;
analyzing the second codeset to identify a second statistically significant sequence itemset for a second clinical condition that is supported by the second set of clinical condition patients and is not supported by the second set of control patients, wherein the second statistically significant sequence itemset has a second confidence value of at least 0.10 within a second epoch duration that depends on patient age;
wherein the first epoch duration differs from the second epoch duration; and
generating the one or more sequence itemset models using the first statistically significant sequence itemset and the second statistically significant sequence itemset to analyze an electronic health record of a human patient to provide an output for determining whether the human patient has the first clinical condition or the second clinical condition.