US 11,854,701 B2
Time window-based platform for the rapid stratification of blunt trauma patients into distinct outcome cohorts
Gregory M. Constantine, Baden, PA (US); Timothy Billiar, Presto, PA (US); Qi Mi, Pittsburgh, PA (US); Rami Namas, Bethel Park, PA (US); Lukas Schimunek, Rimbach (DE); and Yoram Vodovotz, Sewickley, PA (US)
Assigned to University of Pittsburgh—Of the Commonwealth System of Higher Education, Pittsburgh, PA (US)
Filed by University of Pittsburgh—Of the Commonwealth System of Higher Education, Pittsburgh, PA (US)
Filed on Sep. 13, 2021, as Appl. No. 17/473,726.
Application 17/473,726 is a continuation of application No. 15/971,519, filed on May 4, 2018, abandoned.
Claims priority of provisional application 62/502,018, filed on May 5, 2017.
Prior Publication US 2022/0215963 A1, Jul. 7, 2022
Int. Cl. G16H 50/30 (2018.01); G16H 20/10 (2018.01); G16H 50/20 (2018.01); G16H 50/70 (2018.01); G16B 20/20 (2019.01); G16B 40/00 (2019.01); G16B 40/30 (2019.01); G16H 70/40 (2018.01)
CPC G16H 50/30 (2018.01) [G16B 20/20 (2019.02); G16B 40/00 (2019.02); G16B 40/30 (2019.02); G16H 20/10 (2018.01); G16H 50/20 (2018.01); G16H 50/70 (2018.01); G16H 70/40 (2018.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method of determining risk of developing multiple organ dysfunction (MOD) in a trauma patient, comprising:
generating, with a processor, a dataset of stored values comprising an aMODD2-D5 value for a statistically-significant number of patients and a diagnosis of a nosocomial infection, the aMODD2-D5 value comprising a MOD score, obtained on days 2-5 following a trauma injury based on a machine learning model trained with a regression analysis, the regression analysis applied to a panel of biomarkers, the panel of biomarkers comprising one or more of interleukin 6, interleukin 8/CCL8, interleukin 10, IFN-γ inducible protein (IP)-10, plasma levels of soluble ST2, monokine induced by gamma interferon, monocyte chemotactic protein (MCP)-1, chloride, CO2, creatinine, partial thromboplastin time (PTT), and platelet count, and one or more polymorphisms selected from:
homozygous (AA) for a cytosine (C) at rs10741668, or a polymorphism in linkage disequilibrium therewith, where D′>0.75 or R2>0.75;
homozygous for a guanine (G) at rs10790334, or a polymorphism in linkage disequilibrium therewith, where D′>0.75 or R2>0.75;
homozygous for a C at rs2065418, or a polymorphism in linkage disequilibrium therewith, where D′>0.75 or R2>0.75;
heterozygous (AB) for a G at rs2241777, or a polymorphism in linkage disequilibrium therewith, where D′>0.75 or R2>0.75;
heterozygous for a thymine (T) at rs3134287, or a polymorphism in linkage disequilibrium therewith, where D′>0.75 or R2>0.75;
heterozygous for an adenine (A) at rs3098223, or a polymorphism in linkage disequilibrium therewith, where D′>0.75 or R2>0.75; and
heterozygous for a T at rs906790, or a polymorphism in linkage disequilibrium therewith, where D′>0.75 or R2>0.75;
calculating, with a processor and based on the dataset of stored values, a threshold aMODD2-D5 value indicative of a risk of developing MOD;
generating, with the machine learning model, a MOD score for days 2-5 following a trauma injury experienced by a trauma patient;
calculating, with a processor and based on the MOD scores generated by the machine learning model, an aMODD2-D5 value for the trauma patient;
determining, with a processor and based on the threshold, whether the trauma patient's aMODD2-D5 value meets the calculated threshold and thus whether the trauma patient has a clinically-relevant risk of developing MOD; and
generating, with a processor, an output indicating whether the patient is expected to experience a risk of MOD.