Development of an automated system for clinical study recruitment
Bibliographic record
Abstract
IntroductionThe AFTER AKI study was developed to evaluate implementation of a clinical decision support initiative for acute kidney injury patients. Recruitment relies on staff observing changes in serum creatinine, discussing the study with patients, and then alerting study personnel for consenting patients – a process that misses many eligible patients. Objectives and ApproachTo improve the efficiency of patient recruitment, we sought to develop an automated system to alert nurses on participating wards when patients on their wards met the study criteria with minimal risk of a data breech. To accomplish this, data from several databases were linked: Calgary Laboratory Services (CLS; a subsidiary of Alberta Health Services (AHS)) Data refreshed daily to capture serum creatinine labs AHS Analytics Data Warehouse Admission/Discharge/Transfer (ADT) data to determine patient location in hospital on previous day Discharge Abstract Database (DAD) to exclude patients with prior renal transplant ResultsThe data were linked using the following process: Daily procedure scheduled to flag patients who met the lab criteria on the previous day using CLS laboratory data. The identified patients were located by hospital and ward using ADT data, and to exclude patients with a prior renal transplant. Only non-transplant patients located one of the study wards were retained. Cumulative patient list updated with new patients and dates. Tableau report created and securely released to ward clerk to enable clerk to view new patients each day for their assigned wards and discuss study with them as an impartial third party. Consenting patients can then be approached by study personnel to discuss in more detail. Conclusion/ImplicationsA system was successfully created to enable an automated process for patient identification in a clinical trial. Patient privacy was protected by applying user-level security when disseminating reports to ensure that only health care providers within a patient’s ‘circle of care’ had access to necessary information.
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 | 0.034 | 0.074 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.008 | 0.004 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.006 | 0.004 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.029 | 0.019 |
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".