Patents by Inventor Robert W. Georgantas, III

Robert W. Georgantas, III has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11894147
    Abstract: A method for predicting an unfavorable outcome for a patient admitted to a hospital, e.g., with a COVID-19 infection is described. Attributes from an electronic health record for the patient are obtained including at least findings obtained at admission, basic patient characteristics, and laboratory data. The attributes are supplied to a classifier implemented in a programmed computer which is trained to predict a risk of the unfavorable outcome. The classifier is arranged as a hierarchical combination of (a) an initial binary classifier stratifying the patient into either a high risk group or a low risk group, and (b) child classifiers further classifying the patient in a lowest risk group or a highest risk group depending how the initial binary classifier stratified the patient as either a member of the high risk or low risk group.
    Type: Grant
    Filed: September 2, 2022
    Date of Patent: February 6, 2024
    Assignee: BIODESIX, INC.
    Inventors: Thomas Campbell, Robert W. Georgantas, III, Heinrich Röder, Joanna Röder, Laura Maguire
  • Publication number: 20230005621
    Abstract: A method for predicting an unfavorable outcome for a patient admitted to a hospital, e.g., with a COVID-19 infection is described. Attributes from an electronic health record for the patient are obtained including at least findings obtained at admission, basic patient characteristics, and laboratory data. The attributes are supplied to a classifier implemented in a programmed computer which is trained to predict a risk of the unfavorable outcome. The classifier is arranged as a hierarchical combination of (a) an initial binary classifier stratifying the patient into either a high risk group or a low risk group, and (b) child classifiers further classifying the patient in a lowest risk group or a highest risk group depending how the initial binary classifier stratified the patient as either a member of the high risk or low risk group.
    Type: Application
    Filed: September 2, 2022
    Publication date: January 5, 2023
    Applicant: BIODESIX, INC.
    Inventors: Thomas CAMPBELL, Robert W. GEORGANTAS, III, Heinrich RÖDER, Joanna RÖDER, Laura MAGUIRE
  • Publication number: 20220373539
    Abstract: The present invention relates to the use of components of the IL23 pathway as biomarkers, e.g., IL22, LCN2 and combinations thereof, to stratify or identify populations of patients suffering from IL23-mediated diseases (e.g., Crohn's disease) responsive to treatment with an anti-IL23 antagonist (including, e.g., anti-IL23 antibodies or antigen-binding fragments thereof). Levels of IL23 pathway biomarkers above or below a predetermined threshold can be used, for example, (i) to determine whether a patient with an IL23-mediated disease or disorder such a Crohn's disease is eligible or non-eligible for treatment with a therapeutic agent (e.g., an anti-IL23 antibody), (ii) to determine whether treatment with a certain agent should be commenced, suspended, or modified, (iii) to diagnose whether the IL23-mediated disease is treatable or not treatable with a specific therapeutic agent, or (iv) to predict the outcome of treating the IL23-mediated disease with a specific therapeutic agent.
    Type: Application
    Filed: May 24, 2021
    Publication date: November 24, 2022
    Inventors: Robert W. Georgantas, III, Chris Morehouse, Brandon Higgs, Koustubh Ranade, Katie Streicher, William Rees, Meina Liang, Raffaella Faggioni, Jing Li, Inna Vainshtein, Yen-Wah Lee, Jingjing Chen, Robert A. Gasser, JR.
  • Patent number: 11476003
    Abstract: A method for predicting an unfavorable outcome for a patient admitted to a hospital, e.g., with a COVID-19 infection is described. Attributes from an electronic health record for the patient are obtained including at least findings obtained at admission, basic patient characteristics, and laboratory data. The attributes are supplied to a classifier implemented in a programmed computer which is trained to predict a risk of the unfavorable outcome. The classifier is arranged as a hierarchical combination of (a) an initial binary classifier stratifying the patient into either a high risk group or a low risk group, and (b) child classifiers further classifying the patient in a lowest risk group or a highest risk group depending how the initial binary classifier stratified the patient as either a member of the high risk or low risk group.
    Type: Grant
    Filed: June 10, 2021
    Date of Patent: October 18, 2022
    Assignee: BIODESIX, INC.
    Inventors: Thomas Campbell, Robert W. Georgantas, III, Heinrich Röder, Joanna Röder, Laura Maguire
  • Publication number: 20220189638
    Abstract: A method for predicting an unfavorable outcome for a patient admitted to a hospital, e.g., with a COVID-19 infection is described. Attributes from an electronic health record for the patient are obtained including at least findings obtained at admission, basic patient characteristics, and laboratory data. The attributes are supplied to a classifier implemented in a programmed computer which is trained to predict a risk of the unfavorable outcome. The classifier is arranged as a hierarchical combination of (a) an initial binary classifier stratifying the patient into either a high risk group or a low risk group, and (b) child classifiers further classifying the patient in a lowest risk group or a highest risk group depending how the initial binary classifier stratified the patient as either a member of the high risk or low risk group.
    Type: Application
    Filed: June 10, 2021
    Publication date: June 16, 2022
    Applicant: BIODESIX, INC.
    Inventors: Thomas CAMPBELL, Robert W. GEORGANTAS, III, Heinrich RÖDER, Joanna RÖDER, Laura MAGUIRE
  • Publication number: 20220188701
    Abstract: Shapley values (SVs) have become an important tool to further the goal of explainability of machine learning (ML) models. However, the computational load of exact SV calculations increases exponentially with the number of attributes. Hence, the calculation of SVs for models incorporating large numbers of interpretable attributes is problematic. Molecular diagnostic tests typically seek to leverage information from hundreds or thousands of attributes, often using training sets with fewer instances. Methods are described for evaluate SVs using Monte Carlo sampling or exact calculation in polynomial time (i.e., reasonably quickly and efficiently) using the architecture of a ML model designed for robust molecular test generation, and without requiring classifier retraining.
    Type: Application
    Filed: June 28, 2021
    Publication date: June 16, 2022
    Applicant: BIODESIX, INC.
    Inventors: Heinrich RÖDER, Joanna Röder, Laura Maguire, Robert W. Georgantas, III, Thomas Campbell, Lelia Net
  • Publication number: 20220144935
    Abstract: The present invention relates to the use of the Chemokine (C—C motif) ligand 20 (CCL20) as a biomarker to stratify or identify populations of patients suffering from interleukin-23 (IL23)-mediated diseases (e.g., Crohn's disease) responsive to treatment with an, anti-IL23 antagonist (including, e.g., anti-IL23 antibodies). Levels of CCL20 above or below a predetermined threshold can be used, for example, (i) to determine whether a patient with an IL23-mediated disease or disorder such a Crohn's disease is eligible or non-eligible for treatment with a therapeutic agent, (ii) to determine whether treatment with a certain agent should be commenced, suspended, or modified, (iii) to diagnose whether the IL23-mediated disease is treatable or not treatable with a specific therapeutic agent, or (iv) to predict the outcome of treating the IL23-mediated disease with a specific therapeutic agent. CCL20 can be used in combination with other IL23 pathway biomarkers such as IL22 and/or lipocalin-2 (LCN2).
    Type: Application
    Filed: November 29, 2021
    Publication date: May 12, 2022
    Inventors: Robert W. Georgantas, III, Chris Morehouse, Brandon Higgs, Koustubh Ranade, Katie Streicher, William Rees, Meina Liang, Raffaella Faggioni, Jing Li, Inna Vainshtein, Yen-Wah Lee, Jingjing Chen, Robert A. Gasser, JR.
  • Patent number: 11220541
    Abstract: The present invention relates to the use of the Chemokine (C—C motif) ligand 20 (CCL20) as a biomarker to stratify or identify populations of patients suffering from interleukin-23 (IL23)-mediated diseases (e.g., Crohn's disease) responsive to treatment with an, anti-IL23 antagonist (including, e.g., anti-IL23 antibodies). Levels of CCL20 above or below a predetermined threshold can be used, for example, (i) to determine whether a patient with an IL23-mediated disease or disorder such a Crohn's disease is eligible or non-eligible for treatment with a therapeutic agent, (ii) to determine whether treatment with a certain agent should be commenced, suspended, or modified, (iii) to diagnose whether the IL23-mediated disease is treatable or not treatable with a specific therapeutic agent, or (iv) to predict the outcome of treating the IL23-mediated disease with a specific therapeutic agent. CCL20 can be used in combination with other IL23 pathway biomarkers such as IL22 and/or lipocalin-2 (LCN2).
    Type: Grant
    Filed: December 16, 2016
    Date of Patent: January 11, 2022
    Assignees: AMGEN INC., MEDIMMUNE, LLC
    Inventors: Robert W. Georgantas, III, Chris Morehouse, Brandon Higgs, Koustubh Ranade, Katie Streicher, William Rees, Meina Liang, Raffaella Faggioni, Jing Li, Inna Vainshtein, Yen-Wah Lee, Jingjing Chen, Robert A. Gasser, Jr.
  • Patent number: 11016099
    Abstract: The present invention relates to the use of components of the IL23 pathway as biomarkers, e.g., IL22, LCN2 and combinations thereof, to stratify or identify populations of patients suffering from IL23-mediated diseases (e.g., Crohn's disease) responsive to treatment with an anti-IL23 antagonist (including, e.g., anti-IL23 antibodies or antigen-binding fragments thereof). Levels of IL23 pathway biomarkers above or below a predetermined threshold can be used, for example, (i) to determine whether a patient with an IL23-mediated disease or disorder such a Crohn's disease is eligible or non-eligible for treatment with a therapeutic agent (e.g., an ant-IL23 antibody), (ii) to determine whether treatment with a certain agent should be commenced, suspended, or modified, (iii) to diagnose whether the IL23-mediated disease is treatable or not treatable with a specific therapeutic agent, or (iv) to predict the outcome of treating the IL23-mediated disease with a specific therapeutic agent.
    Type: Grant
    Filed: September 16, 2016
    Date of Patent: May 25, 2021
    Assignees: AMGEN INC., MEDIMMUNE, LLC
    Inventors: Robert W. Georgantas, III, Chris Morehouse, Brandon Higgs, Koustubh Ranade, Katie Streicher, William Rees, Meina Liang, Raffaella Faggioni, Jing Li, Inna Vainshtein, Yen-Wah Lee, Jingjing Chen, Robert A. Gasser, Jr.
  • Publication number: 20200262907
    Abstract: The present invention relates to the use of the Chemokine (C—C motif) ligand 20 (CCL20) as a biomarker to stratify or identify populations of patients suffering from interleukin-23 (IL23)-mediated diseases (e.g., Crohn's disease) responsive to treatment with an, anti-IL23 antagonist (including, e.g., anti-IL23 antibodies). Levels of CCL20 above or below a predetermined threshold can be used, for example, (i) to determine whether a patient with an IL23-mediated disease or disorder such a Crohn's disease is eligible or non-eligible for treatment with a therapeutic agent, (ii) to determine whether treatment with a certain agent should be commenced, suspended, or modified, (iii) to diagnose whether the IL23-mediated disease is treatable or not treatable with a specific therapeutic agent, or (iv) to predict the outcome of treating the IL23-mediated disease with a specific therapeutic agent. CCL20 can be used in combination with other IL23 pathway biomarkers such as IL22 and/or lipocalin-2 (LCN2).
    Type: Application
    Filed: December 16, 2016
    Publication date: August 20, 2020
    Inventors: Robert W. Georgantas, III, Chris Morehouse, Brandon Higgs, Koustubh Ranade, Katie Streicher, William Rees, Meina Liang, Raffaella Faggioni, Jing Li, Inna Vainshtein, Yen-Wah Lee, Jinging Chen, Robert A. Gasser, JR.
  • Publication number: 20180252728
    Abstract: The present invention relates to the use of components of the IL23 pathway as biomarkers, e.g., IL22, LCN2 and combinations thereof, to stratify or identify populations of patients suffering from IL23-mediated diseases (e.g., Crohn's disease) responsive to treatment with an anti-IL23 antagonist (including, e.g., anti-IL23 antibodies or antigen-binding fragments thereof). Levels of IL23 pathway biomarkers above or below a predetermined threshold can be used, for example, (i) to determine whether a patient with an IL23-mediated disease or disorder such a Crohn's disease is eligible or non-eligible for treatment with a therapeutic agent (e.g., an ant-IL23 antibody), (ii) to determine whether treatment with a certain agent should be commenced, suspended, or modified, (iii) to diagnose whether the IL23-mediated disease is treatable or not treatable with a specific therapeutic agent, or (iv) to predict the outcome of treating the IL23-mediated disease with a specific therapeutic agent.
    Type: Application
    Filed: September 16, 2016
    Publication date: September 6, 2018
    Inventors: Robert W. Georgantas, III, Chris Morehouse, Brandon Higgs, Koustubh Ranade, Katie Streicher, William Rees, Meina Liang, Raffaella Faggioni, Jing Li, Inna Vainshtein, Yen-Wah Lee, Jingjing Chen, Robert A. Grasser, JR.
  • Patent number: 10006026
    Abstract: Disclosed herein is a method for producing a recombinant polypeptide in a mammalian cell culture in which the mammalian cells have a modified microRNA activity level. In one embodiment, a microRNA activity level is increased. In another embodiment, a microRNA activity level is decreased. In a more particular embodiment, the mammalian cells have a reduced miRNA-let-7a activity level.
    Type: Grant
    Filed: March 12, 2014
    Date of Patent: June 26, 2018
    Assignee: MedImmune, LLC
    Inventors: Katie Streicher, Jonathan Jacobs, Robert W. Georgantas, III, Lydia Greenlees, Koustubh Ranade, Michael Bowen
  • Publication number: 20160024502
    Abstract: Disclosed herein is a method for producing a recombinant polypeptide in a mammalian cell culture in which the mammalian cells have a modified microRNA activity level. In one embodiment, a microRNA activity level is increased. In another embodiment, a microRNA activity level is decreased. In a more particular embodiment, the mammalian cells have a reduced miRNA-let-7a activity level.
    Type: Application
    Filed: March 12, 2014
    Publication date: January 28, 2016
    Applicant: Medlmmune, LLC
    Inventors: Katie STREICHER, Jonathan JACOBS, Robert W. GEORGANTAS, III, Lydia GREENLEES, Koustubh RANADE, Michael BOWEN
  • Patent number: 7799528
    Abstract: The invention is based at least in part on the discovery of novel group of genes and/or their encoded gene products that are differentially represented in two substantially enriched CD34+/CD38?/Lin? and CD34+/[CD38/Lin]++ hematopoietic cell populations isolated from normal human bone marrow, cord blood, and peripheral blood stem cell preparations.
    Type: Grant
    Filed: August 9, 2005
    Date of Patent: September 21, 2010
    Assignee: The Johns Hopkins University
    Inventors: Curt I. Civin, Robert W. Georgantas, III