US 12,451,248 B2
Diagnosing hypoadrenocorticism from hematologic and serum chemistry parameters using machine learning algorithm
Krystle Reagan, Davis, CA (US); Chen Gilor, Davis, CA (US); and Brendan Reagan, Fort Collins, CO (US)
Assigned to The Regents of the University of California, Oakland, CA (US)
Appl. No. 17/269,248
Filed by The Regents of the University of California, Oakland, CA (US)
PCT Filed Aug. 16, 2019, PCT No. PCT/US2019/046889
§ 371(c)(1), (2) Date Feb. 17, 2021,
PCT Pub. No. WO2020/037248, PCT Pub. Date Feb. 20, 2020.
Claims priority of provisional application 62/765,031, filed on Aug. 17, 2018.
Prior Publication US 2021/0249136 A1, Aug. 12, 2021
Int. Cl. G16H 50/20 (2018.01); G06N 20/00 (2019.01); G16B 40/00 (2019.01); G16H 10/40 (2018.01)
CPC G16H 50/20 (2018.01) [G06N 20/00 (2019.01); G16B 40/00 (2019.02); G16H 10/40 (2018.01)] 17 Claims
 
1. A method for diagnosing hypoadrenocorticism comprising:
receiving, at a computer device, a plurality of bloodwork parameters associated with a patient, wherein the plurality of bloodwork parameters include parameters of complete blood count and parameters of serum chemistry;
analyzing, by the computer device, the plurality of bloodwork parameters using a trained machine learning algorithm, analyzing comprising:
cross-correlating, using the trained machine learning algorithm, the parameters of complete blood count and the parameters of serum chemistry; and
identifying, using the trained machine learning algorithm, a first set of criteria based on cross-correlating the parameters of complete blood count and the parameters of serum chemistry, wherein the first set of criteria indicates a positive hypoadrenocorticism diagnosis, or
identifying, using the trained machine learning algorithm, a second set of criteria based on cross-correlating the parameters of complete blood count and the parameters of serum chemistry, wherein the second set of criteria indicates a negative hypoadrenocorticism diagnosis;
determining, by the computer device, a hypoadrenocorticism diagnosis indicating whether the patient is positive or negative for hypoadrenocorticism using the trained machine learning algorithm based on identifying the first set of criteria or the second set of criteria as a result of cross-correlating the parameters of complete blood count and the parameters of serum chemistry, wherein the hypoadrenocorticism diagnosis is determined based on input consisting of the parameters of complete blood count and the parameters of serum chemistry; and
displaying, by the computer device, the hypoadrenocorticism diagnosis via a graphical user interface.