Technological Model to Optimize the Request for Radiological Studies
Bibliographic record
Abstract
Inappropriate requests for imaging studies are a frequent problem in clinical practice, leading to diagnostic errors, unnecessary costs, and patient dissatisfaction. These errors often arise from insufficient dissemination of clinical guidelines, limited training of referring physicians, and variability in request formats. The result is delayed diagnoses, duplication of studies, increased radiation exposure, and inefficient use of healthcare resources. To address this issue, technological tools such as diagnostic algorithms have been proposed to support physicians in selecting the most appropriate imaging tests, especially in time-sensitive conditions. This study evaluated a diagnostic algorithm through a cross-sectional survey of 111 participants, including physicians, residents, interns, medical students, and dental professionals. The questionnaire explored perceptions of the algorithm's clinical utility, clarity, and feasibility of integration into daily workflows. Respondents consistently highlighted its capacity to improve diagnostic accuracy, expedite decision-making, and facilitate clearer communication between physicians and radiologists. Specific strengths included its applicability to abdominal emergencies and complex scenarios such as right upper quadrant pain, jaundice, pancreatitis, and trauma. At the same time, participants pointed out challenges, including difficulties in evaluating contrast safety, limited access to high-cost imaging, and the need for broader diagnostic coverage and personalization by age group. Despite these concerns, the algorithm was positively received overall and was recognized as a useful support tool for reducing inappropriate requests, enhancing diagnostic confidence, and ultimately improving patient care.
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 | 0.007 | 0.033 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.007 | 0.005 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.012 | 0.006 |
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".