Clinerion’s Patient Recruitment System (PRS) uses a hybrid cloud infrastructure to search patients’ EHRs and identify eligible candidates for clinical research. With an ontology-based approach, PRS extracts unstructured data that fits specific criteria from connected hospitals, aggregates and de-identifies the information, and compares it across all electronic information sources using artificial intelligence, machine learning, natural language processing, and other advanced informatics methodologies.

The PRS hybrid cloud architecture is driven by requirements for patient privacy and data security, scalability, and flexibility. PRS comprises two types of installations, PRS Nodes in local intranets, hosting patient data; and the PRS Cloud, which orchestrates the overall system and holds job requests (e.g. search query requests). Data are only sent via intranet to the local PRS Node instead of to a central cloud.

The particular benefits arising from the use of cloud computing are in the areas of patient privacy and data security, and scalability and flexibility:

  • There is no direct inbound connection from the PRS Cloud to the PRS Nodes, which makes the system very secure. The PRS Nodes cannot be hacked for patient data. Patient data – pseudonymized, in any case – stays on local intranets and only report data (aggregated counts of query results) are sent from the PRS Nodes to the PRS Cloud.
  • Using XEN Server cloud technology also allows PRS to achieve virtualization – we can add virtual machines whenever needed and thus optimize resource allocation. This leads to easy scalability, both of size of patient data per PRS Node, as well as number of parallel requests to PRS applications/GUI in the PRS Cloud. We can easily scale the overall system to support and process queries over millions of data records. Each PRS Node has the data from one hospital. Adding another hospital means just adding one more PRS Node, so the overall system is linearly scalable.

Clinerion has been named a Finalist in the BIG Stratus Awards for Cloud Computing, recognizing Patient Recruitment System as a unique solution that takes advantage of cloud technologies.

Benefits of the Hybrid Network

The hospital is in control of patient data

  • The key for de-identification of patients is fully in hospital hands.
  • No patient data leaves the hospital and hospital infrastructure.
  • Rapid internal analysis of patient data for own management purposes possible at any time.

The system is user-friendly and scalable:

  • Trial teams create/improve query criteria within hours/minutes independently form IT-support.
  • No limitation on number of queries (trials) running in parallel as PRS holds mirrored data of hospital information system.