Artificial intelligence-assisted colonoscopy improves adenoma detection rates in routine colonoscopy practice: a single-center, retrospective, propensity score-matched study with concurrent controls
Bibliographic record
Abstract
BACKGROUND/AIMS: This study aimed to investigate whether a real-time artificial intelligence (AI)-assisted polyp detection system can improve adenoma detection rates (ADRs) in real-world colonoscopy practice. METHODS: This single-center, retrospective, propensity score-matched study collected data from consecutive patients who underwent colonoscopy-either AI-assisted or standard colonoscopy- between March 2023 and February 2024. Propensity score matching was conducted to adjust for baseline characteristics across the groups. RESULTS: During the study period, 1,085 patients who underwent colonoscopy were eligible for inclusion. After propensity score matching, 474 patients who underwent AI-assisted colonoscopy and 474 who underwent standard colonoscopy were included in the primary analysis. The ADR was significantly higher in the AI-assisted colonoscopy group than in the standard colonoscopy group (35.9% vs. 26.4%; p = 0.002). Additionally, the number of adenomas detected per colonoscopy was significantly higher in the AI-assisted group than in the standard group (0.69 ± 1.22 vs. 0.43 ± 0.91; p < 0.001). However, the detection rates of advanced adenomas and sessile serrated lesions did not differ significantly between the two groups. CONCLUSION: AI-assisted colonoscopy significantly improves ADRs in real-world colonoscopy practice.
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 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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".