Method and System for Ontology Based Analytics
AssigneeThe Board of Trustees of the Leland Stanford Junior University
InventorsNigam Shah, Paea LePendu, Srinivasan Iyer
Life of this patent
Estimating the term…
Abstract
The present invention provides a mechanism to use terminologies and ontologies for the purpose of indexing, annotating and semantically marking up existing collections of datasets. The invention further provides a system for incorporating terminologies, ontologies, and contextual annotation in specific domains, such as utilizing biomedical concept hierarchies in data analytics. The resulting rich structure supports specific mechanisms for data mining and machine learning.
Claims19
A computer-implemented method for de-identifying digital information records, comprising:
- annotating digital information records including creating timelines of patient events;
- creating contingency tables for drug-disease pairs for a plurality of patients;
- computing an odds ratio from the contingency tables;
- determining a confidence interval for a drug-disease pair.
A computer-implemented method for de-identifying digital information records, comprising:
- receiving a list of terms of interest that may exist within digital information records, wherein the list of terms do not include terms that uniquely identify an individual;
- receiving at least one digital information record corresponding to at least one individual, wherein the at least one digital information record includes information that uniquely identifies at least one individual;
- identifying an occurrence within the at least one digital information record of terms from the list of terms;
- and
- collecting the occurrence of terms as a set of terms, wherein the set of terms does not include information that uniquely identifies the at least one individual.
A computer-readable medium including instructions that, when executed by a processing unit, causes the processing unit to de-identify digital information records, by performing the steps of:
- receiving a list of terms of interest that may exist within digital information records, wherein the list of terms do not include terms that uniquely identify an individual;
- receiving at least one digital information record corresponding to at least one individual, wherein the at least one digital information record includes information that uniquely identifies at least one individual;
- identifying an occurrence within the at least one digital information record of terms from the list of terms;
- and
- collecting the occurrence of terms as a set of terms, wherein the set of terms does not include information that uniquely identifies the at least one individual.
Dependencies are inferred from the claim text.