Transparent reporting on multi-site studies about algorithms for linked health data: A systematic review of Health Data Research Network Canada’s Algorithms Inventory
Bibliographic record
Abstract
ObjectiveMulti-site studies that use routinely-collected, linked health data often rely on validated algorithms to harmonize definitions of health conditions or other population characteristics across sites. If algorithm validation is not practicable, feasibility studies that assess whether an algorithm can be consistently and accurately implemented across sites, are recommended. We investigated the transparency of reporting on multi-site algorithm feasibility studies found in Health Data Research Network (HDRN) Canada’s Algorithms Inventory. ApproachPublished, multi-site Canadian feasibility studies about chronic or infectious disease algorithms were assessed using an adaptation of the RECORD (REporting of studies Conducted using Observational Routinely collected health Data) and STROBE (STrengthening the Reporting of OBservational studies in Epidemiology) guidelines. Reviewers were trained on a subset of studies. The remainder were independently assessed by two reviewers and quality checks were conducted. Results were descriptively summarized. ResultsThirty published multi-site algorithm feasibility studies were reviewed; the majority were conducted in four or more sites, and 83% assessed chronic disease algorithms. Almost one-fifth (17%) of the studies did not justify the methods used to assess algorithm feasibility. However, the majority (>95%) addressed potential sources of bias and discussed algorithm generalizability. ConclusionsWe observed accurate and complete reporting of most elements of multi-site algorithm feasibility studies conducted in Canada. These studies provided important information about availability of data elements, generalizability, and potential algorithm uses. ImplicationsTransparent reporting of algorithm feasibility studies facilitates algorithm reuse, enhances the credibility and reproducibility of study findings, and promotes collaboration within the data linkage community.
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
Direct model labels (unvalidated)
Per-model category and study-design labels from the labeling rounds. They are machine output, unvalidated, and the disagreement between models ships as data. No study design here is MEDLINE-validated yet.
| Model arm | Categories | Study design | Confidence |
|---|---|---|---|
| gemma | Metaresearch Domain: Reporting · Genre: Review About the Canadian research system: yes · About a Canadian topic: yes | Systematic review | low |
| gpt | Metaresearch Domain: Reporting · Genre: Review About the Canadian research system: no · About a Canadian topic: yes | Systematic review | low |
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 | 0.579 | 0.832 |
| Meta-epidemiology (narrow) | 0.003 | 0.004 |
| Meta-epidemiology (broad) | 0.009 | 0.009 |
| Bibliometrics | 0.036 | 0.055 |
| Science and technology studies | 0.006 | 0.010 |
| Scholarly communication | 0.016 | 0.010 |
| Open science | 0.011 | 0.010 |
| Research integrity | 0.005 | 0.005 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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, unvalidatedLabeled directly by 2 models reading the full record.
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".