US 12,125,314 B2
Systems and methods for machine learning-based identification of sepsis
Hooman H. Rashidi, Davis, CA (US); and Nam K. Tran, Davis, CA (US)
Assigned to The Regents of the University of California, Oakland, CA (US)
Appl. No. 17/635,972
Filed by The Regents of the University of California, Oakland, CA (US)
PCT Filed Aug. 20, 2020, PCT No. PCT/US2020/047282
§ 371(c)(1), (2) Date Feb. 16, 2022,
PCT Pub. No. WO2021/035098, PCT Pub. Date Feb. 25, 2021.
Claims priority of provisional application 62/889,959, filed on Aug. 21, 2019.
Prior Publication US 2022/0292876 A1, Sep. 15, 2022
Int. Cl. G06V 40/16 (2022.01); G06F 16/9535 (2019.01)
CPC G06V 40/171 (2022.01) [G06F 16/9535 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method for training machine learning systems for early recognition of sepsis, comprising:
collecting, by a computing device, a set of biomarker and vital sign measurements of a population with a known clinical diagnosis;
applying, by the computing device, one or more transformations to each biomarker and vital sign measurement including standardization to create a modified set of biomarker and vital sign measurements;
creating, by the computing device, a first training set comprising a subset of the modified set of biomarker and vital sign measurements;
training, by the computing device, a machine learning system using the first training set; and
validating, by the computing device, the machine learning system using a second subset of the modified set of biomarker and vital sign measurements as a test set.