A17 COMPARING ENDOSCOPIST DIAGNOSIS OF COLORECTAL POLYPS ASSISTED BY ARTIFICIAL INTELLIGENCE (CADX) VS CADX WITHOUT ENDOSCOPIST INPUT: A RANDOMIZED CONTROLLED TRIAL
Bibliographic record
Abstract
Abstract Background Artificial intelligence-based optical diagnosis systems (CADx) have been developped to assist in eliminating the need for histologic diagnosis of diminutive colorectal polyps (resect-and-discard and diagnose-and-leave strategies). However, these systems have not yet been implemented in routine clinical practice. Aims We were interested in evaluating the performance of CADx without human input to diagnoses performed by endoscopists assisted by CADx. Methods We performed a randomized clinical trial of patients undergoing elective colonoscopies at the CHUM. Patients were randomized into two arms: 1) optical diagnosis of colorectal polyps using CADx without human input; 2) endoscopists performed optical diagnosis after consulting a real-time CADx diagnosis (Human in the Loop [HiL]). Primary outcome was accuracy in optical diagnosis for both arms. Results 467 patients were randomized (229 in the CADx group, 238 in the HiL group). Overall accuracy for optical diagnosis was 76.3% in the CADx group and 70.5% in the HiL group (p=0.19). Sensitivity, specificity, PPV and NPV for adenoma diagnosis were 89.7%, 58.4%, 82.2%, and 72.5% respectively in the CADx group vs 85.3%, 69.6%, 81.8%, and 74.8% in the HiL group. Sensitivity, specificity, PPV and NPV did not differ significantly between the two groups. Conclusions Optical diagnosis of colorectal polyps had similar accuracy when using CADx without human input compared to endoscopist-based diagnosis assisted by CADx. Resect and discard and diagnose and leave strategies can therefore potentially be implemented without need for endoscopist optical diagnosis. Funding Agencies CAGFujifilm
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 | 0.006 | 0.010 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.006 | 0.004 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.005 | 0.004 |
| Insufficient payload (model declined to judge) | 0.008 | 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".