A workstation-integrated peer review quality assurance program: pilot study
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
BACKGROUND: The surrogate indicator of radiological excellence that has become accepted is consistency of assessments between radiologists, and the technique that has become the standard for evaluating concordance is peer review. This study describes the results of a workstation-integrated peer review program in a busy outpatient radiology practice. METHODS: Workstation-based peer review was performed using the software program Intelerad Peer Review. Cases for review were randomly chosen from those being actively reported. If an appropriate prior study was available, and if the reviewing radiologist and the original interpreting radiologist had not exceeded review targets, the case was scored using the modified RADPEER system. RESULTS: There were 2,241 cases randomly assigned for peer review. Of selected cases, 1,705 (76%) were interpreted. Reviewing radiologists agreed with prior reports in 99.1% of assessments. Positive feedback (score 0) was given in three cases (0.2%) and concordance (scores of 0 to 2) was assigned in 99.4%, similar to reported rates of 97.0% to 99.8%. Clinically significant discrepancies (scores of 3 or 4) were identified in 10 cases (0.6%). Eighty-eight percent of reviewed radiologists found the reviews worthwhile, 79% found scores appropriate, and 65% felt feedback was appropriate. Two-thirds of radiologists found case rounds discussing significant discrepancies to be valuable. CONCLUSIONS: The workstation-based computerized peer review process used in this pilot project was seamlessly incorporated into the normal workday and met most criteria for an ideal peer review system. Clinically significant discrepancies were identified in 0.6% of cases, similar to published outcomes using the RADPEER system. Reviewed radiologists felt the process was worthwhile.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.017 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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 it