Patents by Inventor Bruce S. Kristal

Bruce S. Kristal 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).

  • Publication number: 20220344060
    Abstract: An improved patient monitoring system can include a processor device, a display, a first sensor in communication with the processor device, the first sensor being at least one of an electrocardiogram sensor, a pressure sensor, a blood oxygenation sensor, an image sensor, an impedance sensor, or a physiological sensor. The system can include a second sensor in communication with the processor device, the second sensor being a physiological sensor. The processor device can be configured to utilize the first accuracy, the second accuracy, the first correlation, the second correlation to determine a recommendation for fusing the first data model with the second data model.
    Type: Application
    Filed: September 4, 2020
    Publication date: October 27, 2022
    Inventors: Bruce S. KRISTAL, Matthew J. SNIATYNSKI, Derbiau Frank HSU
  • Publication number: 20140287936
    Abstract: The small molecule profiles of cells are compared to identify small molecules which are modulated in altered states. Cellular small molecule libraries, methods of identifying tissue sources, methods for treating genetic and non-genetic diseases, and methods for predicting the efficacy of drugs are also discussed.
    Type: Application
    Filed: December 13, 2013
    Publication date: September 25, 2014
    Applicants: CORNELL RESEARCH FOUNDATION, INC., METABOLON, INC.
    Inventors: Rima Kaddurah-Daouk, Bruce S. Kristal
  • Patent number: 8838511
    Abstract: Described is a system and method for training a machine learning network. The method comprises initializing at least one of nodes in a machine learning network and connections between the nodes to a predetermined strength value, wherein the nodes represent factors determining an output of the network, providing a first set of questions to a plurality of users, the first set of questions relating to at least one of the factors, receiving at least one of choices and guesstimates from the users in response to the first set of questions and adjusting the predetermined strength value as a function of the choices/guesstimates. The real and simulated examples presented demonstrate that synthetic training sets derived from expert or non-expert human guesstimates can replace or augment training data sets comprised of actual training exemplars that are too limited in size, scope, or quality to otherwise generate accurate predictions.
    Type: Grant
    Filed: December 7, 2011
    Date of Patent: September 16, 2014
    Assignee: Cornell Research Foundation, Inc.
    Inventors: Bruce S. Kristal, Rolf J. Martin
  • Publication number: 20120084238
    Abstract: Described is a system and method for training a machine learning network. The method comprises initializing at least one of nodes in a machine learning network and connections between the nodes to a predetermined strength value, wherein the nodes represent factors determining an output of the network, providing a first set of questions to a plurality of users, the first set of questions relating to at least one of the factors, receiving at least one of choices and guesstimates from the users in response to the first set of questions and adjusting the predetermined strength value as a function of the choices/guesstimates. The real and simulated examples presented demonstrate that synthetic training sets derived from expert or non-expert human guesstimates can replace or augment training data sets comprised of actual training exemplars that are too limited in size, scope, or quality to otherwise generate accurate predictions.
    Type: Application
    Filed: December 7, 2011
    Publication date: April 5, 2012
    Applicant: CORNELL RESEARCH FOUNDATION, INC.
    Inventors: Bruce S. Kristal, Rolf J. Martin
  • Patent number: 8095480
    Abstract: Described is a system and method for training a machine learning network. The method comprises initializing at least one of nodes in a machine learning network and connections between the nodes to a predetermined strength value, wherein the nodes represent factors determining an output of the network, providing a first set of questions to a plurality of users, the first set of questions relating to at least one of the factors, receiving at least one of choices and guesstimates from the users in response to the first set of questions and adjusting the predetermined strength value as a function of the choices/guesstimates. The real and simulated examples presented demonstrate that synthetic training sets derived from expert or non-expert human guesstimates can replace or augment training data sets comprised of actual training exemplars that are too limited in size, scope, or quality to otherwise generate accurate predictions.
    Type: Grant
    Filed: July 31, 2007
    Date of Patent: January 10, 2012
    Assignee: Cornell Research Foundation, Inc.
    Inventors: Bruce S. Kristal, Rolf J. Martin
  • Patent number: 7910301
    Abstract: The small molecule profiles of cells are compared to identify small molecules which are modulated in altered states. Cellular small molecule libraries, methods of identifying tissue sources, methods for treating genetic and non-genetic diseases, and methods for predicting the efficacy of drugs are also discussed.
    Type: Grant
    Filed: March 27, 2007
    Date of Patent: March 22, 2011
    Assignees: Metabolon, Inc., Cornell Research Foundation, Inc.
    Inventors: Rima Kaddurah-Daouk, Bruce S. Kristal
  • Patent number: 7635556
    Abstract: The small molecule profiles of cells are compared to identify small molecules which are modulated in altered states. Cellular small molecule libraries, methods of identifying tissue sources, methods for treating genetic and non-genetic diseases, and methods for predicting the efficacy of drugs are also discussed.
    Type: Grant
    Filed: February 17, 2006
    Date of Patent: December 22, 2009
    Assignees: Cornell Research Foundation, Inc., Metabolon, Inc.
    Inventors: Rima Kaddurah-Daouk, Bruce S. Kristal
  • Patent number: 7553616
    Abstract: The small molecule profiles of cells are compared to identify small molecules which are modulated in altered states. Cellular small molecule libraries, methods of identifying tissue sources, methods for treating genetic and non-genetic diseases, and methods for predicting the efficacy of drugs are also discussed.
    Type: Grant
    Filed: March 27, 2007
    Date of Patent: June 30, 2009
    Assignees: Metabolon, Inc., Cornell Research Foundation, Inc.
    Inventors: Rima Kaddurah-Daouk, Bruce S. Kristal
  • Patent number: 7550260
    Abstract: The small molecule profiles of cells are compared to identify small molecules which are modulated in altered states. Cellular small molecule libraries, methods of identifying tissue sources, methods for treating genetic and non-genetic diseases, and methods for predicting the efficacy of drugs are also discussed.
    Type: Grant
    Filed: March 27, 2007
    Date of Patent: June 23, 2009
    Assignees: Metabolon, Inc., Cornell Research Foundation, Inc.
    Inventors: Rima Kaddurah-Daouk, Bruce S. Kristal
  • Publication number: 20090037351
    Abstract: Described is a system and method for training a machine learning network. The method comprises initializing at least one of nodes in a machine learning network and connections between the nodes to a predetermined strength value, wherein the nodes represent factors determining an output of the network, providing a first set of questions to a plurality of users, the first set of questions relating to at least one of the factors, receiving at least one of choices and guesstimates from the users in response to the first set of questions and adjusting the predetermined strength value as a function of the choices/guesstimates. The real and simulated examples presented demonstrate that synthetic training sets derived from expert or non-expert human guesstimates can replace or augment training data sets comprised of actual training exemplars that are too limited in size, scope, or quality to otherwise generate accurate predictions.
    Type: Application
    Filed: July 31, 2007
    Publication date: February 5, 2009
    Inventors: Bruce S. Kristal, Rolf J. Martin
  • Publication number: 20090017464
    Abstract: The small molecule profiles of cells are compared to identify small molecules which are modulated in altered states. Cellular small molecule libraries, methods of identifying tissue sources, methods for treating genetic and non-genetic diseases, and methods for predicting the efficacy of drugs are also discussed.
    Type: Application
    Filed: July 30, 2008
    Publication date: January 15, 2009
    Applicants: Cornell Research Foundation, Inc., Metabolon Inc.
    Inventors: Rima KADDURAH-DAOUK, Bruce S. KRISTAL
  • Publication number: 20080119517
    Abstract: Compositions and methods used for preventing mitochondrial component-based diseases are disclosed herein. In particular, heterocyclic compositions and methods that are directed toward protecting against changes in mitochondrial permeability transition that could result in cell death.
    Type: Application
    Filed: December 4, 2007
    Publication date: May 22, 2008
    Applicants: Cornell Research Foundation, Inc., Brigham and Women's Hospital, Inc.
    Inventors: Bruce S. Kristal, Robert Friedlander, M. Flint Beal
  • Patent number: 6558955
    Abstract: Disorders are diagnosed by analyzing biological samples of ad libitum-fed and dietary-restricted individuals to generate frequency distribution patterns representative of molecular constituents of the samples, and comparing the patterns.
    Type: Grant
    Filed: February 8, 2000
    Date of Patent: May 6, 2003
    Assignees: Esa Inc., Board of Regents, University of Texas Systems, Cornell Research Foundation, Inc.
    Inventors: Bruce S. Kristal, Wayne R. Matson, Paul E. Milbury