Electronic Procedural Reporting for Colonoscopy; Challenges (Discrepancies) in Data Entry and Report Generation
Bibliographic record
Abstract
Aims: Computerized reporting systems that generate standardized endoscopy reports are available and facilitate easy retrieval of data for quality assurance review. We aim to compare the accuracy of extracted database fields in our reporting system (endoPRO) for key measures of quality to the final edited endoscopy report for colonoscopy procedures. Methods: In a retrospective analysis, we compared data retrieved from endoPRO to the final colonoscopy reports at Hamilton Health Sciences (HHS). The data included demographics, indications for procedures, bowel prep quality, findings, extent of exam, and recommendations. Discrepancies, changes or missing information pertaining to key quality indicators for colonoscopies were recorded. Results: In total, 1843 colonoscopy procedures were done at HHS from January to March 2010, and reports for 592 colonoscopies, randomly selected, were analyzed for this study. Discrepancies were seen in: Indication – 34 cases (5.7%), Assistants present during colonoscopy – 94 cases (15.9%), Quality of bowel preparation – 35 cases (5.9%), Findings & impressions – 38 cases (6.4%) including polyps, inflammation, diverticulosis and haemorrhoids. Conclusions: Our study demonstrates the variability between data found in patients’ final colonoscopy reports and data retrieved from the endoscopy databases. Structured endoscopy reporting and the use of databases facilitate quality assurance but editing of procedure reports after structured data entry compromises accuracy of the data in key quality measures. Inaccurate or incomplete data recording will compromise the enhancements in quality assurance that would accrue otherwise from regular audit processes.
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 | 0.422 | 0.719 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.008 | 0.011 |
| Science and technology studies | 0.002 | 0.005 |
| Scholarly communication | 0.007 | 0.007 |
| Open science | 0.005 | 0.007 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.001 | 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, 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".