A109 A SIMPLE METHOD TO CALCULATE ADENOMA DETECTION RATES
Bibliographic record
Abstract
Abstract Background The adenoma detection rate (ADR) is a key indicator of the effectiveness of colonoscopy, which remains the gold standard for colorectal cancer detection. Many centers in Canada are increasingly adopting EPIC as their electronic health record system. However, the ADR calculation tool in the EPIC foundation build is not well-suited for Canadian practices, as it fails to account for colonoscopies performed due to positive fecal immunochemical tests (FIT) and relies on synoptic reporting of polyp histology by pathologists. To address this, we developed a straightforward text-based search strategy to identify adenomas in dictated pathology reports. Aims This study aims to compare the accuracy of our new ADR metric against calculations based on manual reviews of pathology reports. Methods We analyzed all screening colonoscopies conducted in Alberta from January to August 2024. For cases with specimens submitted for pathology, we examined the reports using a text string search for the terms “adenoma,” “tubular adenoma,” and “tubulovillous or villous adenoma” in the Final Diagnosis section. Reports were excluded if they contained the phrases “no adenoma,” “history of adenoma,” or “serrated adenoma.” Our reference standard was a manual review of pathology reports performed by trained polyp reconciliation nurses. Results From January to August 2024, a total of 46,364 screening colonoscopies were conducted, with 45% of the patients being female. Manual record reviews revealed that 56% of cases had at least one adenoma, 20% had at least one sessile serrated lesion, 171 cases included at least one traditional serrated adenoma, and 345 cases of colorectal cancer were detected. Using manual chart review as the reference standard, our text-based ADR metric demonstrated a sensitivity of 81% and a specificity of 70%. Conclusions The text search-based ADR metric shows promise in simplifying the calculation of ADR, especially for centers that lack synoptic pathology reporting or the capacity for manual pathology report reviews. Further research is necessary to enhance the accuracy of this metric. Funding Agencies None
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 | 0.008 | 0.053 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.017 | 0.008 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.010 | 0.004 |
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".