Systems and methods for configuring and operating de-identification systems
Systems, devices, and methods of configuring and operating a de-identification system are provided. At least one electronic data model is maintained, which includes a plurality of de-identification requirements for removing personal information from clinical data obtained in a clinical environment, the plurality of de-identification requirements including requirements applicable to at least one jurisdiction of a plurality of jurisdictions. An identifier identifying one of the jurisdictions is received. The data model is traversed to determine a subset of the de-identification requirements applicable to the identified jurisdiction. Data defining a user selection of operating parameters of the de-identification system are received. The user selection is analyzed for conformity with the subset of de-identification requirements. In response to determining the user selection conforms with the subset of de-identification requirements, a signal is generated indicating the conformity. A configuration data structure is generated including data reflective of the user selection of operating parameters.
1 . A computer-implemented method for configuring a de-identification system, the method comprising:
maintaining at least one electronic data model including a plurality of de-identification requirements for removing personal information from clinical video data obtained in a clinical environment, the plurality of de-identification requirements including requirements applicable to at least one jurisdiction of a plurality of jurisdictions, the plurality of de-identification requirements including at least a first set of de-identification requirements to remove visual or audio identifying elements and a second set of de-identification requirements to preserve visual or audio elements;
receiving an identifier identifying one of the jurisdictions;
traversing the electronic data model to determine a subset of the plurality de-identification requirements applicable to the identified jurisdiction, the electronic data model populated using a set of nested de-identification requirements, the nested de-identification requirements including at least both an umbrella jurisdiction and a sub-jurisdiction;
receiving data defining a user selection of operating parameters of the de-identification system;
analyzing the user selection for conformity with the subset of the de-identification requirements;
in response to determining the user selection conforms with the subset of the de-identification requirements, generating a signal indicating the conformity;
generating a configuration data structure including data reflective of the user selection of operating parameters; and
transforming the clinical video data using a trained machine learning model that receives as an input data set the configuration data structure representing the subset of the plurality of the de-identification requirements applicable to the identified jurisdiction and the clinical video data to generate de-identified clinical video data.
2 . The method of claim 1 , wherein the transforming of the clinical video data further includes modifying a compression rate of the generated de-identified clinical video data.
3 . The method of claim 1 , wherein the maintaining the at least one electronic data model includes:
retrieving one or more of the de-identification requirements from an electronic database, each of the one or more de-identification requirements for removing personal information being associated with a respective jurisdiction;
populating the electronic data model by associating the retrieved one or more de-identification requirements with the respective jurisdiction.
4 . The method of claim 1 , wherein:
the plurality of de-identification requirements include requirements applicable to at least one compliance regime of a plurality of compliance regimes;
the identifier identifies one of the compliance regimes; and
traversing the electronic data model to determine the subset of the de-identification requirements includes determining the subset of the de-identification requirements applicable to the identified jurisdiction and the identified compliance regime.
5 . The method of claim 1 , further comprising:
presenting an interactive user interface having a plurality of user interface elements for defining the user selection of operating parameters of the de-identification system.
6 . The method of claim 5 , wherein the user interface elements include one or more default de-identification requirements.
7 . The method of claim 5 , further comprising:
in response to determining the user selection conforms with the subset of the de-identification requirements, modifying the interactive user interface to provide a visual indicator of the conformity.
8 . The method of claim 5 , further comprising:
in response to determining the user selection does not conform with the subset of the de-identification requirements, modifying the interactive user interface to provide a warning visual indicator.
9 . The method of claim 5 , further comprising:
modifying the interactive user interface to include user interface elements for user input of additional identifiers of the de-identification system;
updating the subset of the de-identification requirements by traversing the at least one electronic data model to determine de-identification requirements applicable to the input additional identifiers.
10 . The method of claim 5 , further comprising:
in response to detecting hovering near the user interface elements, modifying the interactive user interface to include an information visual indicator associated with the hovered near user interface element.
11 . The method of claim 5 , further comprising:
populating the interactive user interface with an input interface for receiving new de-identification requirements;
updating the at least one electronic data model with the received new de-identification requirements.
12 . The method of claim 5 , wherein the presenting the interactive user interface comprises:
determining one or more operating parameters in response to the determining the subset of the de-identification requirements; and
populating the interactive user interface with the determined one or more operating parameters.
13 . The method of claim 1 , wherein the de-identification requirements include contractual obligations, and the determined one or more operating parameters include one or more face de-identification algorithms.
14 . The method of claim 1 , wherein the user selection of operating parameters of the de-identification system includes a user selection of a quality assurance process.
15 . A non-transitory computer readable tangible storage medium, when executed by a processor, cause the processor to perform a computer-implemented method for configuring a de-identification system, the method comprising:
maintaining at least one electronic data model including a plurality of de-identification requirements for removing personal information from clinical video data obtained in a clinical environment, the plurality of de-identification requirements including requirements applicable to at least one jurisdiction of a plurality of jurisdictions, the plurality of de-identification requirements including at least a first set of de-identification requirements to remove visual or audio identifying elements and a second set of de-identification requirements to preserve visual or audio elements;
receiving an identifier identifying one of the jurisdictions;
traversing the electronic data model to determine a subset of the plurality of de-identification requirements applicable to the identified jurisdiction, the electronic data model populated using a set of nested de-identification requirements, the nested de-identification requirements including at least both an umbrella jurisdiction and a sub-jurisdiction;
receiving data defining a user selection of operating parameters of the de-identification system;
analyzing the user selection for conformity with the subset of the de-identification requirements;
in response to determining the user selection conforms with the subset of the de-identification requirements, generating a signal indicating the conformity;
generating a configuration data structure including data reflective of the user selection of operating parameters; and
transforming the clinical video data using a trained machine learning model that receives as an input data set the configuration data structure representative of the subset of the plurality of the de-identification requirements applicable to the identified jurisdiction and the clinical video data to generate de-identified clinical video data.
16 . A computer-implemented system for configuring a de-identification system, the computer-implemented system comprising:
a processor connected to a non-transitory computer readable storage medium with executable instructions for causing the processor to:
maintain at least one electronic data model including a plurality of de-identification requirements for removing personal information from clinical video data obtained in a clinical environment, the plurality of de-identification requirements including requirements applicable to at least one jurisdiction of a plurality of jurisdictions, the plurality of de-identification requirements including at least a first set of de-identification requirements to remove visual or audio identifying elements and a second set of de-identification requirements to preserve visual or audio elements;
receive an identifier identifying one of the jurisdictions;
traverse the electronic data model to determine a subset of the de-identification requirements applicable to the identified jurisdiction, the electronic data model populated using a set of nested de-identification requirements, the nested de-identification requirements including at least both an umbrella jurisdiction and a sub-jurisdiction;
receive data defining a user selection of operating parameters of the de-identification system;
analyze the user selection for conformity with the subset of the de-identification requirements;
in response to determining the user selection conforms with the subset of the de-identification requirements, generate a signal indicating the conformity; and
generate a configuration data structure including data reflective of the user selection of operating parameters; and
transform the clinical video data using a trained machine learning model that receives as an input data set the configuration data structure representative of the subset of the plurality of the de-identification requirements applicable to the identified jurisdiction and the clinical video data to generate de-identified clinical video data.
17 . The system of claim 16 , wherein the clinical video data includes at least one of audio data, video data, audio-video data, device data, or text data.
18 . The system of claim 16 , wherein:
the plurality of de-identification requirements include requirements applicable to at least one compliance regime of a plurality of compliance regimes; and
the identifier identifies one of the compliance regimes.
19 . The system of claim 16 , wherein the executable instructions further cause the processor to:
present an interactive user interface having a plurality of user interface elements for defining the user selection of operating parameters of the de-identification system.
20 . The system of claim 19 , wherein the user interface elements include one or more default de-identification requirements.