A Provincial Interoperability Journey to Streamline Resident Transitions and Improve Integrated Care between Hospital & Long-Term Care
Bibliographic record
Abstract
Background: Healthcare systems across Ontario, Canada operate using health record systems with varying data structures, code sets, and interoperability capabilities, resulting in predominantly paper-based transfer of information. For patients transferred between healthcare institutions, this means delays in sharing medical information, increased potential for medication errors, delays in treatment and care, higher readmission rates, and the need for patients to re-tell their story.Ontario hospitals and long-term care homes are now able to digitally exchange clinical information bidirectionally at points of transition through a provincial data integration delivered by Project AMPLIFI. The three-year AMPLIFI project set out to improve the continuity of care for Long-Term Care residents by streamlining transitions between care institutions, leading to safer care for Ontarians and more efficient workflows for providers. Approach: The foundation for interoperability between these fragmented healthcare systems has been created through a bidirectional exchange that facilitates discrete and read-only patient information sharing between hospital information systems (HIS) and LTC home electronic health records (EHR). Funded by the CAN Health Network, St. Joseph’s Healthcare Hamilton and PointClickCare implemented the Post-Acute Care Network Management solution as a pilot project in 2020. Proving successful and demonstrating value, the AMPLIFI team was tasked by the Ministries of Health and Long-Term Care to lead the implementation across Ontario. In collaboration with PointClickCare, the AMPLIFI team works directly with resources at hospitals and LTC homes and their vendors to form networks of connected sites. Throughout, AMPLIFI has engaged with Patient and Family Advisors and Resident Council members in the vision and goal setting of the project, and in the development of communication materials, among other deliverables, with the goal of informing residents across the province of this initiative Results: Interoperability has been made a reality between Ontario hospitals and LTC homes. AMPLIFI has successfully integrated 67 hospitals on the Epic, Oracle Health, and MEDITECH HIS with their geographic network of 452 LTC homes on PointClickCare. This required additional sub-projects to fund and develop two health information exchanges (HIEs) to bring all platforms to a state of readiness. With this, the project has also enabled hospital-to-hospital exchange amongst the Oracle Health and MEDITECH collaborative hospitals, and has paved the way for exchange between HIS platforms across Ontario, as well as a host of future interoperability and integrated care projects.AMPLIFI has supported more than 36,000 total transfers between hospital and LTC homes. Since March 2023, Oracle Health hospitals and their connected LTC homes have contributed more than 6.7 million documents to the Oracle Health HIE, with more than 32,000 views identified. Currently available benefits data shows that providers agree that AMPLIFI provides an improvement for sharing patient information (79%), improves patient safety (75%), reduces time spent communicating with external organizations (74%), and increases the amount of time providers are able to spend with patients discussing care (60%). Further utilization statistics and clinician feedback based on the use of the solution will be shared to demonstrate the impact of the project. Implications: While creating a foundation for interoperability across Ontario, additional work is required to improve and standardize the data shared to fully achieve interoperability, and truly realize benefits. Significant barriers still remain to achieving interoperability and hamper the impact of solutions. Barriers include the need for: provincial or national code set standardization; expanded use of CPOE to fully enable medication reconciliation; and adoption of more standardized clinical documentation practices to allow for consistency. This session will provide insights into the interoperability foundation and exciting future opportunities AMPLIFI has created, lessons learned from successful integrations, and will discuss the challenges that need to be overcome to achieve true interoperability.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.025 | 0.032 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.005 |
| Science and technology studies | 0.011 | 0.005 |
| Scholarly communication | 0.013 | 0.005 |
| Open science | 0.004 | 0.015 |
| Research integrity | 0.002 | 0.005 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".