Homomorphic encryption in a healthcare network environment, system and methods
A system and method for homomorphic encryption in a healthcare network environment is provided and includes receiving digital data over the healthcare network at a data custodian server in a plurality of formats from various data sources, encrypting the data according to a homomorphic encryption scheme, receiving a query at the data custodian server from a data consumer device concerning a portion of the encrypted data, initiating a secure homomorphic work session between the data custodian server and the data consumer device, generating a homomorphic work space associated with the homomorphic work session, compiling, by the data custodian server, a results set satisfying the query, loading the results set into the homomorphic work space, and building an application programming interface (API) compatible with the results set, the API facilitating encrypted analysis on the results set in the homomorphic work space.
1. A system for developing predictive algorithms using private healthcare data, the system comprising:
a data custodian including an encrypted database distributed among a plurality of storage devices, the encrypted database storing a disease registry including homomorphically encrypted concomitancy and comorbidity data of a plurality of patients; and
a user device operable to access the data custodian over a cloud network, retrieve a subset of the homomorphically encrypted concomitancy and comorbidity data, and execute a predictive analytics model on the retrieved data,
wherein, in response to the user device accessing the data custodian over the cloud network, the data custodian instantiates a homomorphic work space (HWS) that has access to the homomorphically encrypted concomitancy and comorbidity data stored in the encrypted database,
wherein the data custodian provides the user device with access to the HWS via an API,
wherein the API translates a query from the user device, the subset of the homomorphically encrypted concomitancy and comorbidity data being pulled from the encrypted database and inserted into the HWS in response to the translated query, wherein the query comprises an unstructured keyword query.
2. The system of claim 1 , wherein, in response to the user device accessing the data custodian over the cloud network, the data custodian provides a public cryptographic key to the user device, the public cryptographic key having a corresponding private cryptographic key to the HWS.
3. The system of claim 1 , wherein, in response to the user device accessing the data custodian over the cloud network, the data custodian generates a structured encrypted vector from the subset of the homomorphically encrypted concomitancy and comorbidity data and sends the structured encrypted vector and the API to the user device.
4. The system of claim 1 , wherein the HWS is instantiated only at the data custodian.
5. The system of claim 1 , wherein the HWS comprises a virtual memory space distributed across one or more memory locations.
6. The system of claim 1 , wherein the HWS is built on top of homomorphic encryption primitives from a homomorphic encryption library.
7. The system of claim 1 , wherein, in response to the user device accessing the data custodian over the cloud network, the data custodian constructs a symmetric cryptographic session.
8. The system of claim 1 , wherein, in response to the user device accessing the data custodian over the cloud network, the data custodian creates a query-specific vector space with a vector containing the subset of the homomorphically encrypted concomitancy and comorbidity data.
9. The system of claim 1 , wherein the data custodian authenticates one or more anonymized operations performed on the homomorphically encrypted concomitancy and comorbidity data by the user device.
10. The system of claim 1 , further comprising a patient device operable to define a set of permissions authorizing the retrieval of the subset of the homomorphically encrypted concomitancy and comorbidity data by the user device.
11. The system of claim 1 , wherein the data custodian decrypts a result of the predictive analytics model and sends the decrypted result to the user device.
12. The system of claim 1 , wherein the API includes homomorphic encryption primitives from a homomorphic encryption library.
13. A method of supporting the development of predictive algorithms using private healthcare data, the method comprising:
storing a disease registry including homomorphically encrypted concomitancy and comorbidity data of a plurality of patients in an encrypted database of a data custodian, the encrypted database being distributed among a plurality of storage devices; and,
in response to a user device accessing the data custodian over a cloud network, providing a subset of the homomorphically encrypted concomitancy and comorbidity data to the user device for execution of a predictive analytics model on the provided data and instantiating a homomorphic work space (HWS) that has access to the homomorphically encrypted concomitancy and comorbidity data stored in the encrypted database,
wherein the data custodian provides the user device with access to the HWS via an API,
wherein the API translates a query from the user device, the subset of the homomorphically encrypted concomitancy and comorbidity data being pulled from the encrypted database and inserted into the HWS in response to the translated query, wherein the query comprises an unstructured keyword query.
14. A non-transitory computer readable storage medium on which are stored instructions executable by a processor to perform operations for supporting the development of predictive algorithms using private healthcare data, the operations comprising:
storing a disease registry including homomorphically encrypted concomitancy and comorbidity data of a plurality of patients in an encrypted database of a data custodian, the encrypted database being distributed among a plurality of storage devices; and,
in response to a user device accessing the data custodian over a cloud network, providing a subset of the homomorphically encrypted concomitancy and comorbidity data to the user device for execution of a predictive analytics model on the provided data and instantiating a homomorphic work space (HWS) that has access to the homomorphically encrypted concomitancy and comorbidity data stored in the encrypted database,
wherein the data custodian provides the user device with access to the HWS via an API,
wherein the API translates a query from the user device, the subset of the homomorphically encrypted concomitancy and comorbidity data being pulled from the encrypted database and inserted into the HWS in response to the translated query, wherein the query comprises an unstructured keyword query.
15. A system for developing predictive algorithms using private healthcare data, the system comprising:
a data custodian including an encrypted database distributed among a plurality of storage devices, the encrypted database storing a disease registry including homomorphically encrypted concomitancy and comorbidity data of a plurality of patients; and
a user device operable to access the data custodian over a cloud network, retrieve a subset of the homomorphically encrypted concomitancy and comorbidity data, and execute a predictive analytics model on the retrieved data,
wherein, in response to the user device accessing the data custodian over the cloud network, the data custodian instantiates a homomorphic work space (HWS) that has access to the homomorphically encrypted concomitancy and comorbidity data stored in the encrypted database,
wherein the data custodian provides the user device with access to the HWS via an API,
wherein, in response to the user device accessing the data custodian over the cloud network, the data custodian generates a structured encrypted vector from the subset of the homomorphically encrypted concomitancy and comorbidity data and sends the structured encrypted vector and the API to the user device.
16. The system of claim 15 , wherein the API translates a query from the user device, the subset of the homomorphically encrypted concomitancy and comorbidity data being pulled from the encrypted database and inserted into the HWS in response to the translated query.
17. The system of claim 15 , wherein, in response to the user device accessing the data custodian over the cloud network, the data custodian provides a public cryptographic key to the user device, the public cryptographic key having a corresponding private cryptographic key to the HWS.
18. The system of claim 15 , wherein the HWS is instantiated only at the data custodian.
19. The system of claim 15 , wherein the HWS comprises a virtual memory space distributed across one or more memory locations.
20. The system of claim 15 , wherein the HWS is built on top of homomorphic encryption primitives from a homomorphic encryption library.
21. The system of claim 15 , wherein, in response to the user device accessing the data custodian over the cloud network, the data custodian constructs a symmetric cryptographic session.
22. The system of claim 15 , wherein, in response to the user device accessing the data custodian over the cloud network, the data custodian creates a query-specific vector space with a vector containing the subset of the homomorphically encrypted concomitancy and comorbidity data.
23. The system of claim 15 , wherein the data custodian authenticates one or more anonymized operations performed on the homomorphically encrypted concomitancy and comorbidity data by the user device.
24. The system of claim 15 , further comprising a patient device operable to define a set of permissions authorizing the retrieval of the subset of the homomorphically encrypted concomitancy and comorbidity data by the user device.
25. The system of claim 15 , wherein the data custodian decrypts a result of the predictive analytics model and sends the decrypted result to the user device.
26. The system of claim 15 , wherein the API includes homomorphic encryption primitives from a homomorphic encryption library.
27. A method of supporting the development of predictive algorithms using private healthcare data, the method comprising:
storing a disease registry including homomorphically encrypted concomitancy and comorbidity data of a plurality of patients in an encrypted database of a data custodian, the encrypted database being distributed among a plurality of storage devices; and,
in response to a user device accessing the data custodian over a cloud network, providing a subset of the homomorphically encrypted concomitancy and comorbidity data to the user device for execution of a predictive analytics model on the provided data and instantiating a homomorphic work space (HWS) that has access to the homomorphically encrypted concomitancy and comorbidity data stored in the encrypted database,
wherein the data custodian provides the user device with access to the HWS via an API,
wherein, in response to the user device accessing the data custodian over the cloud network, the data custodian generates a structured encrypted vector from the subset of the homomorphically encrypted concomitancy and comorbidity data and sends the structured encrypted vector and the API to the user device.
28. A non-transitory computer readable storage medium on which are stored instructions executable by a processor to perform operations for supporting the development of predictive algorithms using private healthcare data, the operations comprising:
storing a disease registry including homomorphically encrypted concomitancy and comorbidity data of a plurality of patients in an encrypted database of a data custodian, the encrypted database being distributed among a plurality of storage devices; and,
in response to a user device accessing the data custodian over a cloud network, providing a subset of the homomorphically encrypted concomitancy and comorbidity data to the user device for execution of a predictive analytics model on the provided data and instantiating a homomorphic work space (HWS) that has access to the homomorphically encrypted concomitancy and comorbidity data stored in the encrypted database,
wherein the data custodian provides the user device with access to the HWS via an API,
wherein, in response to the user device accessing the data custodian over the cloud network, the data custodian generates a structured encrypted vector from the subset of the homomorphically encrypted concomitancy and comorbidity data and sends the structured encrypted vector and the API to the user device.