A Sensitive Data Access Model in Support of Learning Health Systems

Abstract

Given the ever-growing body of knowledge, healthcare improvement hinges more than ever on efficient knowledge transfer to clinicians and patients. Promoted initially by the Institute of Medicine, the Learning Health System (LHS) framework emerged in the early 2000s. It places focus on learning cycles where care delivery is tightly coupled with research activities, which in turn is closely tied to knowledge transfer, ultimately injecting solid improvements into medical practice. Sensitive health data access across multiple organisations is therefore paramount to support LHSs. While the LHS vision is well established, security requirements to support them are not. Health data exchange approaches have been implemented (e.g., HL7 FHIR) or proposed (e.g., blockchain-based methods), but none cover the entire LHS requirement spectrum. To address this, the Sensitive Data Access Model (SDAM) is proposed. Using a representation of agents and processes of data access systems, specific security requirements are presented and the SDAM layer architecture is described, with an emphasis on its mix-network dynamic topology approach. A clinical application benefiting from the model is subsequently presented and an analysis evaluates the security properties and vulnerability mitigation strategies offered by a protocol suite following SDAM and in parallel, by FHIR.

Pharmacist‐led transitions of care between hospitals, primary care clinics, and community pharmacies

“…The planned study duration would have allowed for a more detailed assessment of the advantages/disadvantages of the different IT solutions implemented in each of the three participating regions so that they could eventually be successfully integrated into usual care as part of the provincial Learning Health System initiatives. 34 The recruitment of community pharmacies, varying by region from 47% to 100%, could point to the selection of more motivated clinicians to implement TOC processes. The region with 100% participation of community pharmacies was also the region with 100% participation in a previous study from our group, indicating a clear interest to pursue the development of TOC interventions.…”

“…The study was suspended due to the COVID‐19 pandemic, precluding reaching the recruitment goal, the 6‐month assessment of patient retention and the impact of the interventions on readmissions and ED visits. The planned study duration would have allowed for a more detailed assessment of the advantages/disadvantages of the different IT solutions implemented in each of the three participating regions so that they could eventually be successfully integrated into usual care as part of the provincial Learning Health System initiatives 34 . The recruitment of community pharmacies, varying by region from 47% to 100%, could point to the selection of more motivated clinicians to implement TOC processes.…”

The Prescription of Drug Ontology 2.0 (PDRO): More Than the Sum of Its Parts

“…More recently, the PARS3 platform has been developed to support learning health system activities, including physician's reflective practice (using electronic medical records, hospital emergency visits data, etc.) or rare disease research [23].…”

Artificial Intelligence for Health

“…Ecarot et al [6] noted that healthcare improvement hinges on efficient knowledge transfer to clinicians and patients. They stated that within the emerged learning health system (LHS) framework, security requirements to support LHSs are not well established.…”