Patents by Inventor Shahram Ebadollahi

Shahram Ebadollahi 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: 10832821
    Abstract: A system and method for providing a temporally dynamic model parameter include building a model parameter by minimizing a loss function based on patient measurements taken at a plurality of time points. Temporally related values of the model parameter are identified, using a processor, having a same type of patient measurement taken at different time points. At least one value of the model parameter and temporally related values of the at least one value are selected to provide a temporally dynamic model parameter.
    Type: Grant
    Filed: August 19, 2013
    Date of Patent: November 10, 2020
    Assignee: International Business Machines Corporation
    Inventors: Shahram Ebadollahi, Jianying Hu, Jimeng Sun, Fei Wang, Jiayu Zhou
  • Publication number: 20190348178
    Abstract: Performing an operation comprising generating, by a computing system based on data received from a plurality of data sources, a data model describing a patient, wherein the data comprises medical history data of the patient and observation data received by the computing system during observation of at least one medical professional, generating, by the computing system and based on the model applied to the received data, a plurality of candidate diagnoses for the patient, executing, by the computing system, a plurality of simulations of a plurality of candidate treatments generated by the computing system based on the model, and identifying a first candidate treatment of the plurality of candidate treatments that reduces an uncertainty value of the data model below a threshold.
    Type: Application
    Filed: May 9, 2018
    Publication date: November 14, 2019
    Inventors: Maria Eleftherou, Chung-Sheng Li, Shahram Ebadollahi, Francisco Curbera
  • Publication number: 20190198174
    Abstract: Patient assistant systems are provided. In various embodiments, health data of a user is read from one or more data source. A cohort of the user is determined based on a primary diagnosis of the user. The health data of the user includes the primary diagnosis. A co-morbidity of the primary diagnosis within the cohort is determined. One or more predictor of the co-morbidity within the cohort is determined. Assistance information is provided to the user based on the one or more predictor. The assistance information includes the predictor and one or more recommendation to mitigate the co-morbidity.
    Type: Application
    Filed: December 22, 2017
    Publication date: June 27, 2019
    Inventors: Soroush Abbaspour, Francisco P. Curbera, Daniel M. Dias, Shahram Ebadollahi, Maria Eleftheriou
  • Publication number: 20190189025
    Abstract: A system provides an intervention for a user and comprises at least one processor. The system monitors behavior and context of a user to generate a behavior history. One or more models are utilized to determine an intervention for the user to induce a behavior modification, wherein the one or more models map interventions to user context and behavior and utilize the behavior history to determine an effective intervention for the user. The intervention is provided to the user and feedback is received in response to the intervention. The one or more models are updated based on the feedback. Embodiments of the present invention further include a method and computer program product for providing an intervention to a user in substantially the same manner described above.
    Type: Application
    Filed: December 20, 2017
    Publication date: June 20, 2019
    Inventors: Marie Angelopoulos, Shahram Ebadollahi, Stewart T. Sill, Michal Rosen-Zvi, Ching-Hua Chen, James V. Codella, Si Sun
  • Publication number: 20180082023
    Abstract: Mechanisms are provided to implement secure distributed patient consent and patient information management that addresses the competing needs for efficient access to electronic medical records by authorized parties while maintaining protection of privacy of patient health related information and complying with governing regulations. The mechanisms of the illustrative embodiments implement a tamper-proof and immutable ledger storage system to manage patient consent information and distribution of patient information based on the patient consent information. The ledger storage system operates in conjunction with a master patient record index (MPRI) component to enable the exchange of patient information among health providers once consent has been granted by the patient.
    Type: Application
    Filed: August 9, 2017
    Publication date: March 22, 2018
    Inventors: Francisco P. Curbera, Shahram Ebadollahi, Maria Eleftheriou, Ramesh Gopinath, Krishna C. Ratakonda, Paul C. Tang
  • Publication number: 20180082024
    Abstract: Mechanisms are provided for executing patient information transactions. The mechanism store, in a ledger storage system, for each patient, a history of patient consents associated with patient transactions in a healthcare network, comprising patient consent data structures associated with the patient information transferred between participants as part of the transaction. The mechanisms store a master patient record index (MPRI) for each of the patients. The MPRI stores record locators identifying locations of portions of patient information for the patient on different computing devices associated with different health providers. The mechanisms execute, by a transaction manager, a transaction to grant access to a portion of a patient's information based on consent information stored in the ledger storage system and record locators in the MPRI. The mechanisms update, by a ledger storage engine of the data processing system, the history of transactions based on the execution of the transaction.
    Type: Application
    Filed: August 9, 2017
    Publication date: March 22, 2018
    Inventors: Francisco P. Curbera, Shahram Ebadollahi, Maria Eleftheriou, Ramesh Gopinath, Krishna C. Ratakonda, Paul C. Tang
  • Patent number: 9886255
    Abstract: An application as a service provided in a secure environment. A sandbox in a user's computing environment may be created. An application may be downloaded to the user's computing environment to run within the sandbox. Data sources associated with the user's computing environment may be searched and connectivity established with data registry of the data sources based on data description received with the application. The application may be run within the sandbox using the established connectivity. Metering may be performed to monitor usage of the application at the user's computing environment.
    Type: Grant
    Filed: April 7, 2015
    Date of Patent: February 6, 2018
    Assignee: International Business Machines Corporation
    Inventors: Houtan Aghili, Ock Kee Baek, Francisco P. Curbera, Shahram Ebadollahi, Shubir Kapoor, Shilpa N. Mahatma, Ajay Mohindra, Aleksandra Mojsilovic, Gigi Y. Yuen-Reed
  • Patent number: 9760359
    Abstract: An application as a service provided in a secure environment. A sandbox in a user's computing environment may be created. An application may be downloaded to the user's computing environment to run within the sandbox. Data sources associated with the user's computing environment may be searched and connectivity established with data registry of the data sources based on data description received with the application. The application may be run within the sandbox using the established connectivity. Metering may be performed to monitor usage of the application at the user's computing environment.
    Type: Grant
    Filed: June 24, 2015
    Date of Patent: September 12, 2017
    Assignee: International Business Machines Corporation
    Inventors: Houtan Aghili, Ock Kee Baek, Francisco P. Curbera, Shahram Ebadollahi, Shubir Kapoor, Shilpa N. Mahatma, Ajay Mohindra, Aleksandra Mojsilovic, Gigi Y. Yuen-Reed
  • Patent number: 9396439
    Abstract: A system and method for a composite distance metric leveraging multiple expert judgments includes inputting a data distribution of multiple expert judgments stored on a computer readable storage medium. Base distance metrics are converted into neighborhoods for comparison, wherein each base distance metric represents an expert and each neighborhood represents an individual similarity measure of the expert. The neighborhoods are combined to leverage the local discriminalities of all base distance metrics by applying at least one iterative process to output a composite distance metric.
    Type: Grant
    Filed: March 10, 2015
    Date of Patent: July 19, 2016
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Shahram Ebadollahi, Jimeng Sun, Fei Wang
  • Publication number: 20160139903
    Abstract: An application as a service provided in a secure environment. A sandbox in a user's computing environment may be created. An application may be downloaded to the user's computing environment to run within the sandbox. Data sources associated with the user's computing environment may be searched and connectivity established with data registry of the data sources based on data description received with the application. The application may be run within the sandbox using the established connectivity. Metering may be performed to monitor usage of the application at the user's computing environment.
    Type: Application
    Filed: April 7, 2015
    Publication date: May 19, 2016
    Inventors: Houtan Aghili, Ock Kee Baek, Francisco P. Curbera, Shahram Ebadollahi, Shubir Kapoor, Shilpa N. Mahatma, Ajay Mohindra, Aleksandra Mojsilovic, Gigi Y. Yuen-Reed
  • Publication number: 20160140362
    Abstract: An application as a service provided in a secure environment. A sandbox in a user's computing environment may be created. An application may be downloaded to the user's computing environment to run within the sandbox. Data sources associated with the user's computing environment may be searched and connectivity established with data registry of the data sources based on data description received with the application. The application may be run within the sandbox using the established connectivity. Metering may be performed to monitor usage of the application at the user's computing environment.
    Type: Application
    Filed: June 24, 2015
    Publication date: May 19, 2016
    Inventors: Houtan Aghili, Ock Kee Baek, Francisco P. Curbera, Shahram Ebadollahi, Shubir Kapoor, Shilpa N. Mahatma, Ajay Mohindra, Aleksandra Mojsilovic, Gigi Y. Yuen-Reed
  • Publication number: 20150186788
    Abstract: A system and method for a composite distance metric leveraging multiple expert judgments includes inputting a data distribution of multiple expert judgments stored on a computer readable storage medium. Base distance metrics are converted into neighborhoods for comparison, wherein each base distance metric represents an expert and each neighborhood represents an individual similarity measure of the expert. The neighborhoods are combined to leverage the local discriminalities of all base distance metrics by applying at least one iterative process to output a composite distance metric.
    Type: Application
    Filed: March 10, 2015
    Publication date: July 2, 2015
    Inventors: SHAHRAM EBADOLLAHI, JIMENG SUN, FEI WANG
  • Patent number: 8996443
    Abstract: A system and method for a composite distance metric leveraging multiple expert judgments includes inputting a data distribution of multiple expert judgments stored on a computer readable storage medium. Base distance metrics are converted into neighborhoods for comparison, wherein each base distance metric represents an expert. The neighborhoods are combined to leverage the local discriminalities of all base distance metrics by applying at least one iterative process to output a composite distance metric.
    Type: Grant
    Filed: September 23, 2013
    Date of Patent: March 31, 2015
    Assignee: International Business Machines Corporation
    Inventors: Shahram Ebadollahi, Jimeng Sun, Fei Wang
  • Publication number: 20150019232
    Abstract: Systems and methods for patient identification include identifying a set of mature drugs similar to a target drug using a processor based on a drug similarity measure. A plurality of outcome models are constructed for each mature drug in the set based on real-world evidence, the plurality of outcome models representing a patient response to each mature drug. A patient response to the target drug is predicted based on the outcome models to identify patients for the target drug.
    Type: Application
    Filed: July 10, 2013
    Publication date: January 15, 2015
    Inventors: Shahram Ebadollahi, Jianying Hu, Jimeng Sun, Fei Wang, Ping Zhang
  • Publication number: 20150019239
    Abstract: Systems and methods for patient identification include identifying a set of mature drugs similar to a target drug using a processor based on a drug similarity measure. A plurality of outcome models are constructed for each mature drug in the set based on real-world evidence, the plurality of outcome models representing a patient response to each mature drug. A patient response to the target drug is predicted based on the outcome models to identify patients for the target drug.
    Type: Application
    Filed: August 19, 2013
    Publication date: January 15, 2015
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Shahram Ebadollahi, Jianying Hu, Jimeng Sun, Fei Wang, Ping Zhang
  • Publication number: 20140236545
    Abstract: A system and method for providing a temporally dynamic model parameter include building a model parameter by minimizing a loss function based on patient measurements taken at a plurality of time points. Temporally related values of the model parameter are identified, using a processor, having a same type of patient measurement taken at different time points. At least one value of the model parameter and temporally related values of the at least one value are selected to provide a temporally dynamic model parameter.
    Type: Application
    Filed: August 19, 2013
    Publication date: August 21, 2014
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Shahram Ebadollahi, Jianying Hu, Jimeng Sun, Fei Wang, Jiayu Zhou
  • Publication number: 20140236544
    Abstract: A system and method for providing a temporally dynamic model parameter include building a model parameter by minimizing a loss function based on patient measurements taken at a plurality of time points. Temporally related values of the model parameter are identified, using a processor, having a same type of patient measurement taken at different time points. At least one value of the model parameter and temporally related values of the at least one value are selected to provide a temporally dynamic model parameter.
    Type: Application
    Filed: February 19, 2013
    Publication date: August 21, 2014
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Shahram Ebadollahi, Jianying Hu, Jimeng Sun, Fei Wang, Jiayu Zhou
  • Patent number: 8799286
    Abstract: A system and method for processing data includes organizing medical information in a concept frame data structure, which is adapted to include medical measurements and related metadata. The medical information is analyzed to extract further information using information extractors and to store extracted medical information in the concept frame data structure. References are stored to appropriate visualization methods along with an associated concept in the concept frame data structure.
    Type: Grant
    Filed: October 23, 2008
    Date of Patent: August 5, 2014
    Assignee: International Business Machines Corporation
    Inventors: James W. Cooper, Youssef Drissi, Shahram Ebadollahi, Anthony Tom Levas
  • Publication number: 20140195260
    Abstract: A plurality of actual outcome data points, including actual outcomes for a plurality of episodes of a process, are obtained for the process. A practitioner-independent baseline outcome is also obtained for the process. For each given one of the actual outcome data points, the given one of the actual outcome data points is equated to the practitioner entity-independent baseline outcome multiplied by a plurality of unknown participating practitioner entity outcome indices for each of a plurality of participating practitioner entities. Each of the participating practitioner entity outcome indices is raised to an exponent including a corresponding one of a plurality of unknown participating practitioner entity type indices, to obtain a plurality of equations. The plurality of equations are solved to obtain estimated values of the unknown participating practitioner entity outcome indices and estimated values of the unknown participating practitioner entity type indices.
    Type: Application
    Filed: December 30, 2013
    Publication date: July 10, 2014
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Jianying Hu, Fei Wang, Robert K. Sorrentino, Shahram Ebadollahi
  • Patent number: 8660857
    Abstract: A recommendation system and method includes extracting patient features for a current patient to generate representation of the current patient. The patient features for the current patient are compared to physician features of one or more physicians and patient-to-physician features of a group of patients from medically related records. Outcome measures associated with physicians are compared related to a current query. A future outcome for patient, physician pairs are predicted for the current patient based upon at least one predictive model constructed from the features and outcome measures to output.
    Type: Grant
    Filed: October 27, 2010
    Date of Patent: February 25, 2014
    Assignee: International Business Machines Corporation
    Inventors: Shahram Ebadollahi, Jianying Hu, Martin S. Kohn, Jonathan D. Laserson, Hani Neuvirth-Telem, Lavi Shpigelman, Robert K. Sorrentino