A semi-autonomous approach to connecting proprietary EHR standards to FHIR
Bibliographic record
Abstract
HL7's Fast Healthcare Interoperability Resources (FHIR) standard is designed to provide a consistent way in which to represent and exchange healthcare data, such as electronic health records (EHRs). SMART--on--FHIR (SoF) technology uses this standard to augment existing healthcare data systems with a standard FHIR interface. While this is an important goal, little attention has been paid to developing mechanisms that convert EHR data structured using proprietary schema to the FHIR standard, in order to be served by such an interface. In this paper, a formal process is proposed that both identifies a set of FHIR resources that best capture the elements of an EHR, and transitions the contents of that EHR to FHIR, with a view to supporting the operation of SoF containers, and the wider interoperability of health records with the FHIR standard. This process relies on a number of techniques that enable us to understand when two terms are equivalent, in particular a set of similarity metrics, which are combined along with a series of parameters in order to enable the approach to be tuned to the different EHR standards encountered. Thus, when realised in software, the translation process is semi-autonomous, requiring only the specification of these parameters before performing an arbitrary number of future conversions. The approach is demonstrated by utilising it as part of the CONSULT project, a wider decision support system that aims to provide intelligent decision support for stroke patients.
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 | 0.036 | 0.037 |
| Meta-epidemiology (narrow) | 0.001 | 0.002 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.004 | 0.012 |
| Scholarly communication | 0.012 | 0.017 |
| Open science | 0.005 | 0.013 |
| Research integrity | 0.005 | 0.006 |
| Insufficient payload (model declined to judge) | 0.003 | 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".