Utility of rapid database searching for quality assurance: 'detective work' in uncovering radiology coding and billing errors
Bibliographic record
Abstract
When the first quarter of 2010 Department of Radiology statistics were provided to the Section Chiefs, the authors (SH, BC) were alarmed to discover that Ultrasound showed a decrease of 2.5 percent in billed examinations. This seemed to be in direct contradistinction to the experience of the ultrasound faculty members and sonographers. Their experience was that they were far busier than during the same quarter of 2009. The one exception that all acknowledged was the month of February, 2010 when several major winter storms resulted in a much decreased Hospital admission and Emergency Department visit rate. Since these statistics in part help establish priorities for capital budget items, professional and technical staffing levels, and levels of incentive salary, they are taken very seriously. The availability of a desktop, Web-based RIS database search tool developed by two of the authors (WK, WB) and built-in database functions of the ultrasound miniPACS, made it possible for us very rapidly to develop and test hypotheses for why the number of billable examinations was declining in the face of what experience told the authors was an increasing number of examinations being performed. Within a short time, we identified the major cause as errors on the part of the company retained to verify billable Current Procedural Terminology (CPT) codes against ultrasound reports. This information is being used going forward to recover unbilled examinations and take measures to reduce or eliminate the types of coding errors that resulted in the problem.
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 | 0.038 | 0.162 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.021 | 0.010 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.005 | 0.005 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.003 |
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".