Patents by Inventor Peter Daniel Larson

Peter Daniel Larson 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).

  • Systems and methods for automatic bias monitoring of cohort models and un-deployment of biased models
    Patent number: 11848081
    Abstract: Systems and methods are disclosed for monitoring models for bias. In one implementation, a system for automatically assessing a deployed model for selection of a cohort may include a processing device programmed to: apply the deployed model to data representing a first plurality of individuals, the data including at least one characteristic of the first plurality of individuals; based on the application, select a subset of the first plurality of individuals as a cohort; receive data representing a second plurality of individuals labeled as within the cohort, the data including the at least one characteristic of the second plurality of individuals; compare the selected subset and the second plurality of individuals along the at least one characteristic; and determine whether the comparison results in a difference between the selected subset and the second plurality of individuals greater than a threshold.
    Type: Grant
    Filed: May 6, 2019
    Date of Patent: December 19, 2023
    Assignee: Flatiron Health, Inc.
    Inventors: Benjamin Edward Birnbaum, Joshua Daniel Haimson, Lucy Dao-Ke He, Melissa Hedberg, Nathan Coleman Nussbaum, Paul Stephen Richardson, Katharina Nicola Seidl-Rathkopf, Evan Eino Estola, Peter Daniel Larson
  • Systems and methods for automatic bias monitoring of cohort models and un-deployment of biased models
    Patent number: 11694777
    Abstract: Systems and methods are disclosed for monitoring models for bias. In one implementation, a system for automatically assessing a deployed model for selection of a cohort may include a processing device programmed to: apply the deployed model to data representing a first plurality of individuals, the data including at least one characteristic of the first plurality of individuals; based on the application, select a subset of the first plurality of individuals as a cohort; receive data representing a second plurality of individuals labeled as within the cohort, the data including the at least one characteristic of the second plurality of individuals; compare the selected subset and the second plurality of individuals along the at least one characteristic; and determine whether the comparison results in a difference between the selected subset and the second plurality of individuals greater than a threshold.
    Type: Grant
    Filed: October 5, 2018
    Date of Patent: July 4, 2023
    Assignee: Flatiron Health, Inc.
    Inventors: Benjamin Edward Birnbaum, Joshua Daniel Haimson, Lucy Dao-Ke He, Melissa Hedberg, Nathan Coleman Nussbaum, Paul Stephen Richardson, Katharina Nicola Seidl-Rathkopf, Evan Eino Estola, Peter Daniel Larson
  • SYSTEMS AND METHODS FOR AUTOMATIC BIAS MONITORING OF COHORT MODELS AND UN-DEPLOYMENT OF BIASED MODELS
    Publication number: 20200058382
    Abstract: Systems and methods are disclosed for monitoring models for bias. In one implementation, a system for automatically assessing a deployed model for selection of a cohort may include a processing device programmed to: apply the deployed model to data representing a first plurality of individuals, the data including at least one characteristic of the first plurality of individuals; based on the application, select a subset of the first plurality of individuals as a cohort; receive data representing a second plurality of individuals labeled as within the cohort, the data including the at least one characteristic of the second plurality of individuals; compare the selected subset and the second plurality of individuals along the at least one characteristic; and determine whether the comparison results in a difference between the selected subset and the second plurality of individuals greater than a threshold.
    Type: Application
    Filed: October 5, 2018
    Publication date: February 20, 2020
    Applicant: Flatiron Health, Inc.
    Inventors: Benjamin Edward Birnbaum, Joshua Daniel Haimson, Lucy Dao-Ke He, Melissa Hedberg, Nathan Coleman Nussbaum, Paul Stephen Richardson, Katharina Nicola Seidl-Rathkopf, Evan Eino Estola, Peter Daniel Larson
  • SYSTEMS AND METHODS FOR AUTOMATIC BIAS MONITORING OF COHORT MODELS AND UN-DEPLOYMENT OF BIASED MODELS
    Publication number: 20200058383
    Abstract: Systems and methods are disclosed for monitoring models for bias. In one implementation, a system for automatically assessing a deployed model for selection of a cohort may include a processing device programmed to: apply the deployed model to data representing a first plurality of individuals, the data including at least one characteristic of the first plurality of individuals; based on the application, select a subset of the first plurality of individuals as a cohort; receive data representing a second plurality of individuals labeled as within the cohort, the data including the at least one characteristic of the second plurality of individuals; compare the selected subset and the second plurality of individuals along the at least one characteristic; and determine whether the comparison results in a difference between the selected subset and the second plurality of individuals greater than a threshold.
    Type: Application
    Filed: May 6, 2019
    Publication date: February 20, 2020
    Applicant: Flatiron Health, Inc.
    Inventors: Benjamin Edward Birnbaum, Joshua Daniel Haimson, Lucy Dao-Ke He, Melissa Hedberg, Nathan Coleman Nussbaum, Paul Stephen Richardson, Katharina Nicola Seidl-Rathkopf, Evan Eino Estola, Peter Daniel Larson